Ctrlk
WebsitePress Kit
For the complete documentation index, see llms.txt. This page is also available as Markdown.

CLI Changelog

Latest version = 0.95.0

0.95.0

New Features

  • Delete an API key by name - tessl api-key delete <name-or-id> accepts either the key name or its ID, matching the pattern already used elsewhere. Interactive selection still works when no argument is given

  • Skill removal guidance - asking to unpublish, archive or delete a skill now explains that skills are published inside a plugin and lists the three real removal paths, and tessl skill --help carries the same tip

  • Uncollected file warnings in review - tessl review run and tessl review fix now name the skill files that were not sent to the reviewer, so content that scored low because it never reached the judge is visible

  • Out-of-workspace path warnings - tessl scenario view flags generated scenarios whose task or criteria reference a home-directory or absolute path, which can never score above zero because the grader only sees the workspace

Improvements

  • Credit warnings on stderr - credit warnings print to stderr instead of stdout, so they no longer sit inside a command's own output. TESSL_CREDIT_WARNING_STREAM accepts off, stderr or stdout to override the choice

  • Upgrade path in the agent credit footer - the out-of-credits and over-limit states now point at /usage, where the balance and the upgrade link live

  • Pricing links - credit and upgrade calls to action point at /pricing

  • Credit checks on the MCP surface - the MCP server now runs the same credit preflight as the CLI, closing a path where a blocked organization could still spend credits

  • Score composition in review output - review results show how a score was composed, per judge, rather than only a final number

  • Organization default model for agent sessions - tessl agent picks up an organization's configured session model when no --model flag and no persisted default are set

  • Review hands off to fix - after a quality review, tessl review run points at tessl review fix as the next step when the review found something to act on. The MCP review_view tool carries the same signal as a nextStep field

  • Fix runs stop at a reachable score - the default fix threshold drops from 100 to 90, so a run can finish early instead of burning every improve iteration on a target a review almost never hits. The MCP surface no longer holds its own defaults and reports the config the server resolved

Bug Fixes

  • Review scores render against the rubric's own scale instead of a hardcoded denominator of 3, so a 1 to 5 rubric no longer reports the wrong total

  • tessl skill review --json carries the deprecation notice in its payload, and the post-apply hint points at tessl review run instead of the deprecated command

  • A logged-out global install of registry content is refused when the global context is managed by an organization policy, closing a path where logging out skipped the organization's managed requirements

  • tessl install -g labels the resolved policy scope org: instead of mislabeling it workspace:

  • Auto permission mode no longer fails at startup for organizations whose model catalog omits gpt-5.4-mini. The classifier falls back to the resolved session model

  • Reasoning models in the gpt-5.6 family route through the OpenAI Responses API, fixing a gateway 400 when a request carried both a function tool and a reasoning effort

  • Skill inventory upload accepts internal as a repository visibility, so GitHub Enterprise organization-internal repositories are no longer rejected

0.94.0

New Features

  • Credit usage meter - tessl org usage shows your organization's plan, credits used against the allowance, and when the current window started. Pass --org to name an organization, --json for the raw credit account

  • /usage and /cost in the agent - /usage shows the same meter without leaving the session, /cost shows what the session has cost in credits with the token counts underneath, and a credits: N left segment on the footer refreshes each turn

  • Commands report what a run cost - every command that waits for a run prints the credits it consumed once billing settles, and ... view commands report the cost of the run they inspect. The figure comes from the server, so it matches what you are billed

  • Credit guardrails on billable commands - a one-line notice when you are over your allowance but still allowed to proceed, and a hard stop with an upgrade link when you are not. Both are suppressed under --json so structured output stays parseable

  • Scoped reviews - new repeatable --path flag on tessl change review restricts the review to files matching a pathspec

Improvements

  • Security grades read Tessl's own levels - tessl search, tessl tile info and the security review output now render the Tessl security level and per-finding severity. A clean result reads "Passed", an unscanned one reads "N/A", low-severity findings group into their own section below higher severities, and an unrecognized level renders as-is instead of failing. --json keeps the previous fields alongside the new ones

  • Eval fixtures are bounded to the run - tessl eval run and publish-time evals now refuse scenario fixtures and packed symlinks that resolve outside the run's repository or scenarios boundary, so an eval can no longer archive files from elsewhere on the machine. tessl eval lint reports the same. Out-of-boundary directory fixtures and symlinks are opt-in via tessl eval run --allow-unsafe-fixture-paths, or --allow-unsafe-eval-fixture-paths on tessl skill publish and tessl plugin publish. A scenario include must always resolve inside its own scenario, with no override

  • A project's .env can no longer redirect the CLI's own state - TESSL_GLOBAL_DIR, TESSL_BINARY_BASE_URL, TESSL_AUTO_UPDATE_INTERVAL_MINUTES and TESSL_DISABLE_UPDATE are ignored when they come from a .env file in the working directory. Values set in your shell are unaffected

  • Workspace resolved from a plugin manifest - working inside a plugin directory that has .tessl-plugin/plugin.json but no tessl.json no longer prompts for --workspace; the workspace is read from the plugin name

  • Declared skills scanned as real files - tessl inventory import now scans skills declared in tile.json / plugin.json the same way it scans any other SKILL.md in the repository, so they carry their body and frontmatter instead of being recorded as bare references. Their names now come from frontmatter (or the containing directory) rather than being prefixed with the plugin name, and a declared skill whose file is missing from the scanned tree is no longer recorded at all

  • workspace_list reports what you can do - the MCP tool now returns allowedActions per workspace, so a caller can filter to the workspaces it has permission to act on before trying

Bug Fixes

  • Failing commands print one error line. Previously the same message appeared twice, with two different cross glyphs

  • tessl change verify --recursive --github now emits GitHub Actions annotations for every root. Warning-level findings from a recursive run previously only appeared in the raw job log

  • Out-of-credits and other expected failures from the review_run, review_fix and uninstall MCP tools are reported as errors rather than crashes

  • The MCP workspace_list_members tool explains that your role cannot view members, instead of failing generically

  • A cached version entry dated in the future is treated as expired, so it can no longer suppress the update check indefinitely

  • The path-containment check no longer misreads directory names that begin with two dots, and anchors relative targets on the boundary root

0.93.0

New Features

  • Severity grading on review findings - tessl change review now grades every finding nit / minor / major / critical by default; pass --no-grade to turn it off

  • Finding attribution - each tessl change review finding names the reviewer skill that produced it

  • Explicit review range - new --head flag on tessl change review to review a specific commit range instead of the inferred one

  • Publish-access filter - new --has-publish-access flag on tessl workspace list to show only workspaces you can publish to

  • Plugin Creator in Tessl Agent - the agent now ships with the Plugin Creator skills for authoring plugins

Improvements

  • Symlink guard for MCP config - the CLI warns and asks for confirmation before writing MCP configuration through a symlink that points outside your project

  • Local-execution notice - installing a plugin that ships an MCP command which runs on your machine now tells you at install time

  • Global installs respect --agent - the --agent scope is honored when installing context globally

  • CLAUDE_CONFIG_DIR support - installing global Claude Code context now honors CLAUDE_CONFIG_DIR

  • Clearer permission prompt - the session-scope option in the agent permission prompt has a clearer label

  • Clearer MCP review tools - review_run, review_view, and review_fix describe what they do and what to expect

  • Keys revoked on logout - tessl logout revokes the device's LLM keys

Bug Fixes

  • Fixed concurrent auto-updates leaving behind a dangling symlink

  • Fixed a race when two installs ran at once by staging npm installer downloads

  • tessl change verify now fetches the diff base itself in shallow and CI checkouts instead of failing

  • Install sync no longer fails when a skill entry is missing from the manifest

  • Search results now render when ranking data is unavailable

  • Review scores now use the rubric scale reported by the API instead of assuming a fixed scale

Removals

  • tessl context library and its query_library_docs MCP tool have been removed. They were deprecated and have no replacement.

0.92.0

New Features

  • Hooks in plugins - Plugins can now declare cross-agent hooks via hooks / nativeHooks in plugin.json. See the plugin configuration docs.

Improvements

  • Signed release verification - CLI installation and self-update now verify against a cryptographically signed release manifest before extraction.

0.91.0

New Features

  • Agent-readiness report - run /agent-ready in the tessl agent to scan your repository and surface what to improve.

  • tessl launch resume - resume an interrupted or completed cloud launch run.

  • Signed release verification - the installer verifies the release signature before installing.

Improvements

  • Agent works without native search tools - uses fd / rg when available and falls back to a basic code implementation when they are not installed.

  • Verify cache relocated - now stored at ~/.tessl/verify-cache, so cached results are shared across projects instead of living in each checkout.

  • Auto-detect workspace - tessl review run / review fix read the workspace from tessl.json instead of always prompting.

  • tessl launch list now shows the workspace and the run's creator.

  • tessl eval list consolidates injected context into a single column.

  • Credit errors link to top-up - an out-of-credits error now points to the upgrade / top-up flow.

  • Explicit, persistent agent setup - tessl init now records selected agents in tessl.json for reproducible installs across machines. Re-run tessl init on an existing project to update the list.

  • Clearer permission prompts - prompts are deduped per tool call, bash paths are classified by read/write/delete, external and sensitive-path actions route through the auto classifier, and auto-mode prompt wording is combined.

Changes

  • Separate --agent and --model flags - compound --agent <agent>:<model> tuples are now split into --agent <agent> --model <model>. The old form still works but is deprecated and warns.

Bug Fixes

  • Installer validates the remote release version before installing.

  • Generic hook command/args aligned to the exec / shell forms.

0.90.0

Breaking Changes

  • tessl review <target> (without run) no longer runs a review - it now shows the review command group's help instead. Use tessl review run <target> (or tessl review run quality <target>).

New Features

  • tessl review run quality / tessl review run security - tessl review run is now a subcommand group: quality (the default, unchanged behavior) scores a skill against a rubric, and security runs a Snyk-powered security scan - replacing the standalone tessl security-review command. tessl review list, view, and retry now work across both kinds from a single unified history, with a --fail-on flag mirroring --threshold for security scans. tessl review run <target> continues to work exactly as before - it's shorthand for tessl review run quality <target>.

  • Clone skills from GitLab and Bitbucket sources - Skill installation and inventory scanning now support GitLab and Bitbucket repository sources, not just GitHub.

Bug Fixes

  • Fixed tessl agent ignoring a saved default model from settings.json on startup.

  • tessl agent - Fixed session approval matching for external paths when multiple patterns are involved.

0.89.0

New Features

  • tessl agent out in Open Beta - It helps you build and optimize your software factory one workflow at a time.

  • tessl change commands to aid with automated code reviews

    • tessl change risk - Assess PR/diff risk and decide whether human review is required.

    • tessl change verify - Verify code against configured verifiers.

    • tessl change review - Review the current diff with reviewer skills and emit structured review data.

    • Use tessl agent to set them up!

  • tessl launch skill - Run skills using your preferred agent in order to automate parts of your workflow with skills.

  • tessl mcp proxy - Connect to MCP servers through an MCP gateway set-up in a workspace’s settings.

Improvements

  • Clearer error when --skill can't apply - tessl install --skill <name> now fails fast with an actionable message when given zero sources or more than one source, instead of silently installing nothing.

  • Friendlier model-lock message on eval runs - Selecting a non-default model on a Free plan now produces a single, clear message explaining how to proceed, instead of a raw 403 Forbidden.

Bug Fixes

  • Fixed relative file: sources (e.g. tessl install file:../my-source --global) failing to resolve; they now resolve against your current working directory as expected.

  • Fixed a single unsupported entry in a plugin's .mcp.json failing the whole file at publish and install time; unsupported entries are now skipped and the rest of the plugin installs.

0.88.2

Bug Fixes

  • npm package - fixup README.md file

0.88.1

Bug Fixes

  • Global plugin MCP servers - tessl install --global now writes a plugin's MCP server config to each agent's real user-level config.

0.88.0

New Features

  • Plugin MCP Servers - Plugins can now declare MCP servers in a bundled .mcp.json at the package root.

  • Publish Through Symlinks - tessl skill publish and tessl plugin publish accept an opt-in --resolve-symlinks flag that copies a symlink target's bytes into the published tarball (within a safe boundary), so authors can reuse files from elsewhere in the repo.

Improvements

  • Workspace Scoping for Reviews - tessl review view and tessl review retry now accept --workspace / -w, and --last resolves the most recent run within that workspace.

  • Publish OIDC Warning - When publishing from GitHub Actions without an OIDC token permission, the CLI now warns instead of failing opaquely.

Bug Fixes

  • Fixed tessl skill review --threshold 0 incorrectly emitting a "Skill validation failed" error.

0.87.0

Breaking Changes

  • Skill review now requires a Tessl account. Both tessl review and the older tessl skill review now require authentication: sign in with tessl login, or set a TESSL_TOKEN API key in the environment for CI. Reviews run on Tessl's servers, so anonymous review runs are no longer supported.

Deprecations

  • tessl skill review is deprecated - use tessl review instead. tessl review (alias tessl review run) is the replacement: an async, server-side review with companion view, list, retry, and fix commands. The old command still runs for now but prints a deprecation warning on every run and will be removed in a future release. Replace tessl skill review <path> with tessl review <path>.

New Features

  • tessl review is now fully launched as an end-to-end workflow - review runs are first-class in the CLI with run as the default subcommand, and companion commands to view, retry, and fix reviews directly from the terminal.

  • Flexible reviewer selection - you can target a specific reviewer with --review-plugin or use your workspace's default reviewer configuration.

Improvements

  • Richer review output for debugging and automation - tessl review view now renders dynamic judges per run, and review JSON includes reviewer/plugin identity metadata.

  • Clearer tessl eval view output - run labels are shown and scenarios are sorted for easier reading.

  • More informative tessl eval run start output - pre-run context details are surfaced before execution.

Bug Fixes

  • Review command reliability fixes - tessl review list, view, and retry now resolve workspace names correctly, and --json without --workspace now returns a clear error.

  • Fixed completed scenario counts in multi-solution eval runs.

  • Fixed evaluator failures caused by repeated plugin installation arguments.

0.86.0

New Features

  • Customise the eval-scenarios run when publishing - added --eval-scenarios <scenario-search-path> to tessl plugin publish / tessl skill publish. The default is ./evals in the directory of the plugin being published.

Improvements

  • Default eval model is now DeepSeek v4 Flash.

  • tessl eval list --context-type - filter eval runs by the type of context injected into scenarios for the "with context" variant.

  • Richer tessl eval view - clearer variant labels, an injected-context block, scenario paths, and repo/plugin provenance.

  • tessl eval run echoes the scenario search directory and count before starting.

  • Commit-fixture uploads are grouped and deduped to remove some cases where redundant context was uploaded.

  • Install source policy: git-source allowlist, with denial messages that name the offending source.

  • You're prompted to accept pending invites before a personal org is created.

0.85.0

Breaking Changes

  • tessl eval run --agent is now single-valued - Previously --agent was repeatable and each value created a separate eval run. It now accepts a single agent; run the command once per agent to compare.

  • Removed legacy eval-run context flags - --variant, --context-ref, and --context-pattern have been removed from tessl eval run in favour of the new --context selection (see below).

New Features

  • Skill Inventory - Skill Inventory gives you a living map of every skill in your GitHub org - what exists, where it's used, and where you're duplicating effort. Run the initial import with tessl inventory import and it scans your repos, collects your skills and manifests, and gives you a snapshot of your whole inventory. Run it again any time - each scan is diffed, so you get a living view of what's new, unchanged, and removed over time.

  • Context Selection for tessl eval run - A single --context <path> front door now picks the context under test, with --context-commit to source it from a commit and --skill (repeatable) to narrow a local plugin to specific skills.

  • Control Baseline by Default - tessl eval run now always runs a control variant to compare against, with --skip-baseline to opt out.

  • Secrets injection for plugin evals — tessl eval run now accepts --env-file <path>. Variables in the file are encrypted client-side and delivered into the eval sandbox, where they are available to setup.sh scripts and the agent. See Passing secrets to your eval.

  • --child Flag for Nested Projects - tessl project create now requires --child to create a project nested inside an existing one, and blocks with a clear explanation when a parent project is detected in an ancestor directory.

  • tessl version - Bump a plugin's version locally without publishing, like npm version. Pass patch, minor, or major to increment the current version following semver, or an explicit version (e.g. tessl version 2.1.0) to set it directly. Updates the plugin manifest in place; an optional path argument targets a directory other than the current one.

Improvements

  • Clearer Install Output - tessl install now shows only the dependencies you explicitly requested on the success line; incidental re-installs are summarised as a dim Synced: N count.

  • tessl scenario generate workspace resolution - Workspace is now resolved from your linked Tessl project (tessl.json), the --workspace flag, or an interactive prompt — instead of being derived from the tile manifest name, which caused confusing 403 errors when the manifest used the local/ prefix. The --workspace flag is now accepted for tile-based generation.

0.84.0

New Features

  • Bootstrap Project Create - tessl project create now works in directories that don't yet have a tessl.json, bootstrapping it as part of the create flow.

  • Personal GitHub Account in Skill Inventory Import - tessl skill inventory import can now authenticate with a personal GitHub account, not just org-level credentials.

  • Plugin Marketplace Discovery - Tessl now classifies .claude-plugin/marketplace.json as a first-party manifest, picking up plugins from that location.

Improvements

  • Warning for Large-Scale Eval Runs - tessl eval run now prompts a confirmation before launching large eval batches.

  • Plan-Entitlement-Gated Model and Agent Selection - model and agent selection respects plan entitlements with clearer messages when a selection isn't available.

  • Age-Gated Registry Sources Fallback - registry sources blocked by release-age policy can now resolve to an older fallback source rather than hard-blocking.

Bug Fixes

  • Fixed tessl install to fast-fail on private or missing git repositories instead of silently succeeding with a hidden failure.

  • Fixed the judge-results display to show the correct score denominator in both CLI and frontend.

Windows installer (new distribution channel)

Signed Windows installers are now available for direct download. The Inno installer wraps a signed tessl.exe bundled with TESSL_DISABLE_UPDATE (winget will manage updates):

  • https://install.tessl.io/installers-windows/0.84.0/TesslSetup-0.84.0-x64.exe

  • https://install.tessl.io/installers-windows/0.84.0/TesslSetup-0.84.0-arm64.exe

The signed package will be installable directly via winget install tessl.tessl as soon as it will be approved by Microsoft

0.83.0

New Features

  • **Jujutsu Repo Support - tessl project repair now detects and handles jj-managed repositories alongside Git.

  • Finer Eval Run Controls - tessl eval run adds two independent opt-outs: --skip-forced-context-activation and --skip-scoring. Use them on their own or together to control whether the run forces context activation and whether the rubric scorer fires.

Improvements

  • Solver and Scorer Flag Deprecation - The --solver and --scorer flags on tessl eval run are now hidden but still functional, with a one-line deprecation warning; prefer the new --skip-* flags.

Bug Fixes

  • **Removed a vendor-native plugin-manifest ingestion path that could pick up stale manifests outside the expected resolution flow.

0.82.0

Improvements

  • Install Policy Enforcement - tessl install now honors org-configured release-age and commit-age policies. For registry sources, the CLI automatically falls back to an older version that satisfies the policy (with a clear reason in the install output) or hard-blocks if no version qualifies. For git sources, it resolves to the most recent commit old enough to satisfy the minimum commit-age policy instead of installing HEAD.

  • Policy-Aware tessl outdated - Versions blocked by a release-age policy are now annotated as [release age policy] in the update table, and git sources show the latest age-compliant commit as the recommended update so you can see what will (and won't) be installed before running tessl update.

0.81.3

Improvements

  • Eval Failure Reasons - eval run and eval view now display the reason when a run fails (e.g. quota exceeded), instead of a bare failure marker

  • Eval Default Model Notice - A one-time notice informs you that the default eval model is now GLM 5.1, with guidance on selecting a different model

  • Resilient Eval Polling - eval run now rides out transient server errors and network blips while polling, instead of reporting a completed run as failed

  • Clearer Validation Errors - Manifest schema errors are now rendered in a readable format instead of a raw JSON dump

  • MCP Tool Updates - The new_tile MCP tool is renamed to new_plugin, and the outdated tool now accepts a projectDir parameter to check a specific directory

Bug Fixes

  • Fixed plugin pack failing with a missing tile.json error for plugins created with plugin new; migrated plugins also no longer pack from the stale legacy manifest

  • Fixed eval run evaluating the stale legacy tile.json instead of .tessl-plugin/plugin.json when both manifests are present

  • Publishing a migrated plugin now errors if tile.json declares private: true but plugin.json omits it, preventing a private plugin from accidentally going public

  • Fixed broken documentation links shown after plugin new and skill new

  • Removed misleading advice pointing at tile.json from the "no content" validation error

0.81.2

Bug Fixes

  • scenario generate: Clearer Error When No Manifest Found — Running tessl scenario generate in a directory with no manifest previously crashed with a confusing ENOENT: tile.json error. It now shows a clear message pointing you to add a .tessl-plugin/plugin.json.

0.81.1

Bug Fixes

  • Fixed skill publish incorrectly triggering the import wizard when plugin.json already exists

  • Fixed skill publish --bump not writing the bumped version to plugin.json, causing the old version to be published

  • Fixed skill publish pre-publish version checks reading from tile.json instead of plugin.json

0.81.0

New Features

  • Tiles are now Plugins - This release completes the switch from Tiles to Plugins. The CLI now uses "plugin" across every command, help listing, flag description, and message. For more information on how to migrate from Tiles to Plugins, there is a guide in the documentation.

  • Full moderation status in plugin info - plugin info now shows the complete moderation state for a published version (pass, pending, skipped, fail, or error).

Improvements

  • ls shortcut - tessl ls now works as a shortcut for tessl list, mirroring the existing i → install shortcut.

  • Workspace-scoped uploads - Eval-related uploads (scenario tarballs, plugin archives, repo archives) are now scoped to the active workspace, so teammates in the same workspace can access uploads created by other members.

Bug Fixes

  • Eval run links now point directly to workspace-scoped URLs, skipping the redirect members previously hit when clicking through.

  • scenario generate now works in plugin-only directories (a .tessl-plugin/plugin.json with no tile.json), which previously failed with a "tile.json not found" error.

  • The CLI no longer fails to start when its log file can't be written (e.g. in sandboxed or read-only environments) — file logging is now best-effort.

0.80.0

New Features

  • Eval Enablement Checks - tessl scenario generate, tessl tile publish, and tessl skill publish now pre-flight check whether the target workspace has evals enabled. Scenario generation fails fast with a clear message; publish still succeeds but cleanly skips the eval upload with a single info line.

Improvements

  • Cleaner Publish Output - tessl tile publish no longer prints validation warnings twice (once from pre-publish validate, once from pack).

  • Clearer Forbidden Errors - When creating a project fails because the workspace doesn't exist or you lack permission, the CLI now shows an actionable message instead of a generic 403 Forbidden.

  • Skill Install Paths - Skills are no longer written under .gemini/skills; installation routes through .agents/skills, and any legacy tessl:* / tessl__* entries left in .gemini/skills are cleaned up automatically.

Bug Fixes

  • tessl tile new now preserves the rule description you provide instead of overwriting it with a TODO placeholder.

  • Generated RULES.md now ends with a trailing newline.

0.79.1

Improvements

  • Clearer Guidance for Missing Project Links - When a linked Tessl project can't be found or isn't accessible, the CLI now surfaces actionable next steps with specific tessl project create and tessl project repair commands instead of a raw 404. The tessl eval run help text now also explains that eval runs are saved to a Tessl project.

0.79.0

New Features

  • OpenHands agent support (alpha) — tessl init, tessl install, and tessl run now recognise OpenHands. Auto-detection follows the standard project → home → PATH ladder; OpenHands is excluded from the interactive picker while in alpha but can be selected explicitly via --agents openhands.

  • tessl search --global — install search results into ~/.tessl/ without requiring a project to be initialised. Short form g available.

  • tessl eval run --list-agents — print the supported <agent>:<model> catalogue (with the default marked) without running an eval. Supports --json for scripting.

  • tessl project - Tessl now supports workspace-backed projects in the CLI, giving your local work a persistent project identity for evals and other project-based workflows. Use tessl project create to create a project, tessl project link to connect an existing one, and tessl project repair to fix broken project links.

  • tessl eval run --scorer-agent — override the agent and model used for the score step (as agent:model), while the solver agent stays unchanged. tessl eval view shows the override under a Scored by: line.

  • tessl eval run --quality-check — opt-in flag that asks the backend's LLM judge to filter out misleading scenarios (low feasibility, rubric leakage, low value) before solve and score. Excluded scenarios show up under a red ✗ Excluded by quality check line in tessl eval view. tessl tile publish --with-scenario-quality-check enables the same filter for the eval that runs as part of publishing.

Improvements

  • Simpler tessl skill import / skill new — no longer prompts for workspace or visibility; defaults to local workspace and private visibility. Pass flags explicitly to override.

  • Scenario config (scenario.json) — declarative working-directory setup for evals. Declare fixtures to install (commit or directory), include paths to copy in verbatim, and setup scripts to run after install. Conventional defaults (resources/ auto-included, setup.sh auto-run) mean most scenarios need no scenario.json at all. tessl scenario generate now produces a scenario.json for every generated scenario, plus any supporting input state (e.g. resources/) when the source commit needs it. Setup scripts are off by default per workspace — contact Tessl to enable.

  • Cleaner install error messages — local paths missing the file: prefix now surface a clear validation error instead of a generic parse failure.

  • Softer security-review copy — surfaces showing a per-skill security status now display "No security review available." instead of "Security review has not been run yet."

  • tessl skill review includes referenced skill content — skill reviews now include all referenced content and scripts for logged-in users.

Bug Fixes

  • Install exits non-zero on failure — tessl install and tessl install --global now reliably propagate tile install failures as command failures (non-zero exit code).

  • tessl scenario generate <relative-path> — relative paths like tiles/foo are now correctly routed to the tile flow when the directory exists locally, instead of misrouting to the repo flow and erroring on missing -commits/-prs.

  • tessl tile lint — @decorator tokens in markdown headings and YAML frontmatter are no longer treated as hard-link references and no longer produce false-positive lint warnings.

  • MCP install bootstrap message — the "Initialising new tessl project at …" message no longer prints during bulk sync installs that don't actually write tessl.json.

  • Experimental agent detection — explicit project-level usage of experimental agents (e.g. OpenClaw workspace markers) is now respected ahead of the experimental gate, and the default install flow no longer force-enables experimental agents.

0.78.0

New Features

  • Activation Solver for Evals - tessl eval run --solver=activation measures which skills activate for each scenario, and tessl eval view renders the results in a per-scenario activation table

  • Set Project Name on Init - tessl init accepts a new --name flag to set the project name in tessl.json at creation time

  • Target Org on Workspace Create - tessl workspace create now accepts a --org-id flag to associate a workspace with a specific organization

  • List Organizations - New tessl org list command displays the organizations you belong to

  • Scenario Quality Checks for Evals - tessl eval run --quality-check will filter out scenarios that would give misleading results, based on a quality assessment that looks for things like “criteria leaking into the task” or “task duplicating information from the skill it is meant to exercise”

Improvements

  • Clearer Eval Run Status - Pending and in-progress eval and generation runs render as yellow "In Progress" with elapsed time, instead of an ambiguous "Pending"

  • Better Invalid Manifest Errors - tessl eval run against a directory with a malformed tile.json now reports the manifest error directly with a hint to fix it, instead of falling through to the scenarios flow

  • Removed Eval Compare - tessl eval compare has been removed. Use tessl eval view and tessl eval list instead

  • Global Install from Search - tessl search now supports --global so selecting a result installs it to ~/.tessl/ instead of the current project

Bug Fixes

  • Fixed tile rule creation to safely handle prompts containing / so they no longer create unintended nested paths in the generated rule files

0.77.0

New Features

  • Experimental Windows Support - The Tessl CLI is now available on Windows as an experimental release. Install it with PowerShell:

  • Eval Setup Scripts - Eval scenarios support a new setup field in scenario.json — an ordered array of script paths that run after fixtures and includes are installed, before the solver agent starts.

Improvements

  • Cleaner Top-Level Help - Simplified top-level CLI help.

0.76.0

New Features

  • Eval Progress Bars — eval run and eval view now show real-time per-scenario progress bars with colour-coded status (complete, active, queued)

  • Directory Fixtures in Evals — Scenarios can now declare include paths for directory-based fixtures, alongside existing commit-based fixtures.

  • "latest" Dependency Version — Use "latest" as a dependency version in tessl.json to always resolve the most recent published version

  • Uninstall Individual Skills — tessl uninstall --skill <name> removes specific skills from a dependency instead of removing the entire tile

  • Verifiers in Tile Packing — The verifiers/ directory is now included when packing tiles (when evals are enabled)

  • Failed Security Review Visibility — Security reviews that failed to run are now shown as "failed" instead of appearing as "pending"

Improvements

  • Project Name from Directory — tessl init now derives the project name from the directory basename instead of using a generic default

  • Archive Without Version — tessl archive now works without a version suffix, allowing you to archive all versions of a tile at once

  • Eval Agent/Model Display — eval view now shows the agent and model for all eval run types

  • Workspace Commands — -user flag renamed to -username , -user still works with a deprecation warning

  • Help Text Corrections — Improved descriptions for install --skip-init, tile pack, skill import, and config set

Bug Fixes

  • Fixed eval scenario path resolution when base directory is "."

  • Fixed eval git diff ignoring user's custom diff tool configuration

  • Fixed object metadata serialization in eval debug output

Breaking Changes

  • Removed --project-dependencies — The --project-dependencies flag has been removed from tessl install and tessl init. Dependency scanning and automatic tile matching are no longer part of the install flow. Use tessl search to find relevant tiles instead.

0.75.0

New Features

  • API Key Management — New api-key command group with create, list, and delete subcommands for managing workspace-scoped API keys. Supports both interactive and non-interactive (scripting) modes

  • Auto-Select Single Workspace — When you're a member of only one workspace, the CLI now skips the workspace selection prompt and selects it automatically

Breaking Changes

  • auth token Removed — The auth token command has been removed. Use the new api-key create, api-key list, and api-key delete commands instead for workspace-scoped API key management

0.74.0

New Features

  • Machine-Readable Search: tessl search --json flag outputs results in JSON format for scripting and automation

  • Skill Review Threshold: tessl skill review now supports a --threshold option: when the score is below this threshold, the command will fail - helpful for CI use cases

  • Scores in Search & Info: Search results and tessl tile info now display quality scores and security review details

Improvements

  • Piped Token Output: tessl auth token now suppresses the spinner and hints when output is piped, making it easier to use in scripts

  • Better Error Display: Failed operations now render a red cross indicator for clearer error visibility

  • Search Column Alignment: Interactive search results now have properly aligned columns

  • Remove Steering to Use query_library_docs MCP tool: It was getting in the way of skill activation from some users. You can manually opt-in to install the rules yourself with tessl install tessl/cli-setup

Bug Fixes

  • Fixed skill review API calls failing due to stale authentication tokens

  • Fixed eval commands resolving git repo root incorrectly when run from subdirectories

0.73.0

New Features

  • Security Reviews on Install - tessl install and tessl update now show security review results before installation. CRITICAL/RISKY findings require confirmation to proceed, ADVISORY findings show an advisory after install, and unscanned items display a warning. Use -dangerously-ignore-security to bypass prompts in CI/scripted contexts

  • Commit-Pinned Installs - tessl install now accepts github:<repo>@<sha> and full GitHub commit URLs, allowing you to install a skill at a specific commit. A post-install hint directs to tessl update for future updates

  • Publish --bump Flag - tessl tile publish and tessl skill publish now accept --bump patch|minor|major to auto-increment the version when the current version already exists in the registry

  • .agents/skills Directory Support - Install skills in .agents/skills alongside other requested agents since that’s the folder many tools are aligning with

Improvements

  • Grouped Search Results - tessl search now groups results by type (Tiles / Skills) with section headers when both types are present

Bug Fixes

  • Fixed tessl skill new showing interactive prompts even when all required flags (-name, -description, -workspace) are provided

  • Fixed MCP server processes becoming orphaned when the parent process disconnects (stdin closes)

0.72.0

New Features

  • Pre-Publish Validation & Dry Run - Tile and skill publish commands now validate permissions, workspace, and version availability before publishing, with clear pass/fail output. Use --dry-run to check without actually publishing.

  • Security Scores in Search - Search results now display security assessment levels (Passed, Caution, Risky, Critical) alongside tile scores

Improvements

  • Smarter Eval Scenario Generation - Existing scenarios are now considered when generating new ones, avoiding duplicates

  • Large File Exclusion in Eval Archives - Files over 10MB are automatically excluded from repo archives during eval runs

  • Eval Commit Ref Validation - Commit refs are validated before archive creation, with clear error messages for missing refs

0.71.0

New Features

  • Support for Copilot in VSCode — Skills, rules, and our MCP server can be automatically set-up for vscode

  • Eval Run Labels — New --label / -l flag on tessl eval run lets you attach a short description to a run. Labels appear in tessl eval list and the Tessl web UI, making it easier to identify what you were testing across multiple runs.

  • Eval Variant Selection — New --variant flag on tessl eval run lets you run only a specific variant. Pass --variant without-context to run the baseline only (useful for iterating on scenario quality without affecting the with-context comparison), or --variant with-context to skip the baseline.

  • Local Repo Eval Runs — Project evals can now run against local git repos without SCM integration; the CLI archives and uploads the repo automatically

  • Smarter Scenario Generation — tessl eval generate now avoids duplicating existing scenarios when generating new ones; --count specifies how many new scenarios to add

Bug Fixes

  • Allow installation of skills from unknown dot folders in GitHub repositories (e.g., .agent-skills/)

0.70.1

Improvements

  • Non-Interactive Mode for Evals & Scenarios — tessl eval run and tessl scenario generate now print the run/generation ID and URL immediately when running non-interactively, instead of polling for completion

  • Clearer Help Text — tessl eval run and tessl scenario generate now show which flags are mode-specific, and invalid flag combinations are rejected with helpful messages

Bug Fixes

  • Fixed install --watch-local exiting prematurely — the process now stays alive until Ctrl+C and updated output to show relative paths rather than absolute ones

  • Fixed installation from file: source to exclude .git directories - It now installs the same files that would be captured by tessl tile pack or tessl tile publish

0.70.0

New Features

  • Local Tile Watching — New --watch-local flag on tessl install watches local file-source tiles for changes and automatically reinstalls tiles, streamlining the tile development workflow

  • Search Score Display — tessl search results now show aggregate quality and impact scores with color-coded badges

  • Scenario Generation from PRs — New --prs flag on tessl scenario generate accepts PR numbers as an alternative to --commits

  • Multiple Scenario Downloads — tessl scenario download now accepts multiple space-separated IDs (e.g., tessl scenario download id1 id2)

  • Eval Run Repeats — New --runs / -n flag on tessl eval run to repeat each agent configuration multiple times

  • Eval Polling for Tile Evals — Tile evals now poll for completion instead of returning immediately, with Ctrl+C to detach gracefully

  • Eval JSON Output for Tile Evals — --json flag on tessl eval run now works for tile evals, outputting run ID, tile name, and scenario count

  • Eval Agent Flag — New --agent flag (format: agent:model) replaces --model for tile evals, aligning with project eval conventions

  • Eval Cost Metadata — tessl eval view now displays cost, runtime, turns, and token usage below each solution

  • Eval Agent/Model Display — tessl eval view stats now show the agent and model used for each solution

  • --last for Eval Debug & Retry — tessl eval debug and tessl eval retry now support --last for quick access to the most recent eval run

  • Repository Metadata in tile.json — Tiles now support an optional repository URL field in their manifest

Improvements

  • Tile Cache Protection — Tile authoring commands now warn when operating on paths inside .tessl/tiles/, preventing accidental edits that would be overwritten on the next install

  • Cleaner Help Text — Removed meaningless --no-{flag} negated boolean flags from all commands, improved flag capitalization, and reordered commands for logical grouping

  • Consistent Scenario Terminology — "Generation run" renamed to "generation" throughout the CLI for simpler, more natural language

  • Scenario Generate Table Output — tessl scenario generate results now render as a formatted table with Scenario ID and Commit ID columns

  • Smarter Binary Install — Skips re-downloading binaries that already exist and pass validation; corrupt binaries are automatically cleaned up

Fixes

  • Fixed CLI crashes when output streams disconnect unexpectedly (EPIPE handling)

  • Fixed unpublish help text to reflect the correct 2-day timeframe (was showing 2 hours)

0.69.0

New Features

  • Scenario Generation Commands - New tessl scenario command suite for generating and managing test scenarios. Generate scenarios from tiles or repository commits (tessl scenario generate), download them to disk (tessl scenario download), and track generation runs (tessl scenario list, tessl scenario view)

  • Global Tile Installation - Install tiles globally with tessl install --global to make documentation and skills available across all your projects.

  • Eval Variant Comparison - tessl eval run now supports running evaluations with multiple agent variants and context patterns, with automatic detection of tile vs. project scenario sources

Improvements

  • Project Directory Hints - tessl init and tessl install now display a helpful hint when the target project directory differs from your current working directory

Bug Fixes

  • Fixed a crash when piping CLI output to another command (e.g., tessl list | head) by gracefully handling broken pipe signals

  • Fixed markdown link validation incorrectly parsing non-markdown files during tile linting

0.68.0

New Features

  • GitHub Copilot CLI Support — Tessl now recognizes GitHub Copilot CLI as an agent, with automatic detection, rules wiring via AGENTS.md, skill installation, and MCP configuration

  • Search Type Filtering — tessl search now accepts a --type flag to filter results by content type (skills, docs, or rules)

  • Skill Review Auto-Accept — tessl skill review --optimize now supports a --yes / -y flag to skip the confirmation prompt and auto-apply improvements

Improvements

  • Automatic Binary Cleanup — Old CLI binary versions are now automatically cleaned up after updates, keeping only the current version and one rollback

  • Short SHAs for Git Tiles — tessl list and tessl doctor now display short SHAs for git-sourced tiles instead of full commit hashes

  • Command Detection Timeout — Command lookups now have a 1-second timeout to prevent indefinite hangs during agent detection

Breaking Changes

  • tessl skill search Removed — Use tessl search --type skills instead

Bug Fixes

  • Fixed tessl skill review --optimize failing with a raw 401 error when not authenticated — now shows a clear login prompt

  • Fixed unpublish help text to reflect the correct 2-day window (was incorrectly showing 2 hours)

0.67.0

New Features

  • Skill Optimization - tessl skill review --optimize now applies feedback from the review to generate an updated SKILL.md file

  • Evaluation Type Support - tessl eval list now displays all evaluation types (tile, repo, skill) with a new "Type" column and --type flag to filter by evaluation type

  • Filter Evaluations by Status - tessl eval list now supports a --status flag to filter runs by status (pending, in_progress, completed, failed)

Bug Fixes

  • Fixed tessl skill review returning exit code 0 on validation failure — it now correctly returns a non-zero exit code, enabling proper CI/CD integration

  • Fixed tessl api --input - sending incorrect Content-Type when piping JSON via stdin

0.66.0

New Features

  • outdated command — Check installed tiles for newer versions, showing current, safe update, and latest version info

  • update command — Update tiles to newer versions. Use --yes for all, and --force to include breaking updates

0.65.0

Bug Fixes

  • Windows Compatibility for Generated Files - Fixes generated file and directory names containing colons (:) which are invalid in Windows file paths. Tile files committed to git repositories can now be cloned on Windows without errors. Existing installations are migrated automatically

0.64.0

New Features

  • Local Tile Evaluation - Run evals against your tiles directly from the CLI with tessl eval run and get a fast feedback loop for improving your tiles

  • Eval Results in Terminal - View eval results with per-scenario breakdowns, variant comparisons, and scoring summaries using tessl eval view

  • Eval Run History - List recent eval runs filtered by workspace, tile, or author with tessl eval list

  • Eval Retry - Re-run failed evals with tessl eval retry

0.63.4

Improvements

  • Internal - Stability improvements

0.63.3

New Features

  • Local Path Support for Tile Info - tessl tile info now accepts a local directory path as an argument and defaults to the current directory when no argument is provided, making it consistent with other tile commands like publish and lint

Improvements

  • Better Publish Messages - After publishing tiles or skills, the CLI now displays the published resource URL and a note about moderation timelines

Bug Fixes

  • Fixed MCP configuration failures when using npx tessl by ensuring the tessl binary is accessible via the PATH during init

0.63.2

Bug Fixes

  • Fixed circular reference issues when CLAUDE.md and AGENTS.md are symlinked

0.63.0

Improvements

  • The CLI is now distributed as a native binary instead of a bundled Node.js package

0.62.2

New Features

  • Optional Authentication - You can now use tessl init, tessl install, and tessl search without logging in. Public tiles are accessible to everyone, while private tiles will show helpful hints to log in when needed

Bug Fixes

  • Fixed --skill flag not working correctly when installing a single skill from a local tile with multiple skills

0.62.1

Improvements

  • Internal - Stability improvements

0.62.0

New Features

  • Unified Search — tessl search now returns both tiles and skills in a single view, with visual badges showing content types ([docs], [skills], [rules]) and skill provenance

  • Tile Evaluations — New tessl eval command group for evaluating tiles:

    • tessl eval run [path] — Run evaluations on local tiles

      • --force flag to re-run all evaluations including previously solved cases

    • tessl eval list — View recent eval runs with status

    • tessl eval view-results <id> — View detailed results with color-coded scores and assessment tables

      • --last flag to quickly view most recent eval results

    • Git metadata (branch, commit, dirty state) automatically attached to eval runs

  • Tile Info — New tessl tile info <name> command to view tile metadata, verification status, and moderation status

  • Skills in MCP Context — The query_library_docs MCP tool now includes installed skills when building knowledge context

Improvements

  • Redesigned Help for tessl -h — Commands are now grouped by category with improved formatting and readability

  • Publish Workspace Context — Publishing now shows the target workspace name before uploading

Bug Fixes

  • Fixed --skill flag being ignored when installing skills from registry tiles

  • Fixed re-installing tiles not updating the manifest with new skill selections

  • Fixed tile lint incorrectly flagging files as orphaned when linked via @path.md includes

0.61.4

Improvements

  • Install --yes Flag Behavior - The --yes flag now auto-selects all skills when installing from GitHub, even in interactive mode. Previously it only worked in non-interactive environments.

  • Non-Interactive tile new - The tessl tile new command can now run fully non-interactively when all required flags are provided, making it easier for scripts and agents to use.

Fixes

  • GitHub Skill Installation Bugfixes - Address various edge cases that prevented some skills being installed from GitHub

  • GitHub Skill Installation Respects Pinned Version - Fixed an issue that meant we always installed a skill from a repository's trunk rather than the commit sha in tessl.json when doing tessl install

0.61.3

Improvements

  • Faster git installs - Git dependencies are no longer re-downloaded on every install when already at the correct version

0.61.2

Improvements

  • Windows Platform Detection - The CLI now detects Windows and provides a clear error message directing users to use WSL instead

  • Lenient GitHub Skill Installation - Skills from GitHub with missing referenced files or minor schema issues now install with warnings instead of failing completely

  • Better Warning Display - Installation warnings are now grouped by tile name with count summaries (e.g., "3 content warnings in github:user/repo")

  • Verbose Install Output - Added --verbose (-v) flag to tessl install and tessl skill search commands to display detailed warning messages during installation

Bug Fixes

  • Fixed skill validation warnings showing absolute temp directory paths instead of relative paths

  • Fixed installation failures when GitHub skills have invalid optional frontmatter fields (e.g., allowed-tools as array instead of string)

0.61.1

New Features

  • Skill Commands - Added a complete set of dedicated skill management commands: tessl skill new, tessl skill import, tessl skill lint, tessl skill publish, tessl skill review, and tessl skill search. Skills are now first-class citizens with their own command group for easier discovery and management.

  • GitHub Installation Support - Install tiles and skills directly from GitHub repositories using tessl install github:user/repo or full URLs. Supports branch selection, subdirectories, and interactive skill selection. Git sources are pinned to commit SHAs for version stability.

  • Skill Search - Discover available skills across the Tessl ecosystem with the new interactive tessl skill search command. Search returns both external skills from GitHub and tiles containing skills, with interactive selection and installation.

  • Skill Review - Evaluate skill quality with tessl skill review, which validates SKILL.md files and provides LLM-based scoring across multiple dimensions with actionable suggestions for improvement. Supports both local paths and GitHub URLs.

  • Non-Interactive Mode - Commands now auto-detect TTY availability and work in CI/CD pipelines and with AI agents. When required flags are missing in non-interactive environments, commands provide clear error messages pointing to available options.

  • Selective Skill Installation - Choose specific skills when installing tiles using the new include.skills manifest field in tessl.json. Reduces clutter in agent directories by only activating the skills you need.

  • Codex Support - Full support for Codex as a core agent alongside Claude Code, Cursor, and Gemini. Includes project detection, MCP configuration, steering, and skills synchronization.

  • Gemini Production Ready - Gemini agent is no longer experimental and fully supported in production workflows.

Improvements

  • Simplified Skill Naming - Skill directories now use cleaner names (tessl:<skill> instead of tessl:<workspace>:<tile>:<skill>) and are symlinked rather than copied for better performance and consistency.

  • Automatic Eval Publishing - Evals are now published by default when running tessl tile publish or tessl skill publish. Use -skip-evals to opt out. Published evals automatically trigger evaluation runs.

  • Better Skill Discovery - Improved skill detection uses a three-step process (root check, priority directories, full scan) with optimizations that reduce scan time and exclude build/cache directories.

  • Streamlined Publishing - The tessl skill publish command no longer asks redundant "will you share this?" prompts since publishing inherently means sharing.

  • Improved Help Text - Updated tessl init --agent to list all supported agents (claude-code, codex, cursor, gemini) and clarified that tessl install accepts both registry tiles and GitHub URLs. Added tessl i as a shortcut alias.

  • Relative Paths in Manifest - When creating tiles with --install, the CLI now stores relative paths in tessl.json instead of absolute paths, making projects portable across machines and directories.

  • Smarter CLI Setup - The tessl/cli-setup tile is now only installed when your tiles have documentation, reducing overhead for steering-only projects.

  • Flexible Tile Content - Tiles can now contain any file type, not just markdown files, allowing for configuration files, code examples, and other documentation formats.

Bug Fixes

  • Fixed skill review score display showing /4 instead of the correct /3 scale

  • Fixed status command handling of non-semver versions for git-based and file-based tiles

  • Fixed orphaned file detection for tiles with root-level skills - README.md and other root files are no longer incorrectly flagged as orphaned

  • Fixed skill publish command to accept SKILL.md file paths directly instead of only directory paths

  • Fixed file source tiles being incorrectly deleted as orphaned on repeated installs when dependency key differed from tile name

  • Fixed skill frontmatter validation warnings during installation from external sources like GitHub

  • Fixed tessl skill new output messages to reference correct tile directory paths

  • Fixed skill selection in GitHub repos to require explicit choices, preventing accidental installation of all skills from large repositories

0.60.0

New Features

  • Project Mode (Managed vs Vendored) - Choose how tile content is managed in your project:

    • Managed mode - Tile contents are gitignored like node_modules (default for existing projects)

    • Vendored mode - Tile contents are committed to your repository (default for new projects)

    • Switch modes anytime by setting "mode": "managed" or "mode": "vendored" in tessl.json

Improvements

  • Simplified Local Tile Dependencies - Local tiles (using file: or link: sources) no longer require a version field in tessl.json. The CLI automatically reads versions from installed tile.json files. Existing manifests with both version and source are automatically migrated to the new format.

0.59.0

New Features

  • .tileignore Support - Exclude files from tile validation and packaging using gitignore-style patterns.

0.58.1

Improvements

  • Tile Commands Auto-Detect - tessl tile pack, tessl tile lint, and tessl tile publish can now be run directly from your tile directory without explicitly specifying the path

Bug Fixes

  • Squashed some bugs that were hiding in the codebase. They know what they did.

0.58.0

New Features

  • Context Cost Analysis (Experimental) - The tessl doctor and tessl tile lint commands now display estimated token costs for tile content loaded into agent context windows. This helps you understand which tiles contribute most to context usage and identify oversized content before publishing.

  • HTTP Proxy Support - The CLI now works in proxied network environments by automatically detecting and using HTTP/HTTPS proxy settings from environment variables (http_proxy, https_proxy, HTTP_PROXY, HTTPS_PROXY). The CLI respects no_proxy/NO_PROXY bypass rules.

Improvements

  • Enhanced Python Dependency Scanning - Improved Python dependency detection with support for extras notation (e.g., openai[aiohttp]>=1.52.2) across requirements.txt, pyproject.toml, and uv tree output. The scanner now also automatically falls back to pip3 when pip is not available, improving compatibility with macOS and Linux distributions.

Bug Fixes

  • Fixed Go package PURL validation to require the v prefix in version strings (e.g., v1.9.3 instead of 1.9.3), ensuring pkg.go.dev documentation links work correctly.

  • Fixed false "broken link" warnings during tessl tile lint when markdown files contain URI schemes like mailto:, tel:, ftp:, or data:.

0.57.0

New Features

  • Monorepo Subfolder Support - The tessl install --project-dependencies command now scans dependencies from your current working directory, enabling you to run it from monorepo subfolders in an initialized project (e.g., tessl init && cd backend && tessl install --project-dependencies)

Improvements

  • Smarter Documentation Tree - The context tool now only includes files that are transitively linked from a tile's documentation entrypoint, filtering out orphaned files and making documentation discovery more focused

Bug Fixes

  • Fixed markdown link validation to properly handle anchors (e.g., ./guide.md#section). The validator now validates both file existence and anchor validity, with clearer error messages for broken links

0.56.2

Improvements

  • Internal - Stability improvements

0.56.1

Improvements

  • Observability Enhancements - Improved telemetry infrastructure for better diagnostics and system monitoring

0.56.0

Breaking Changes

  • Node.js 18 No Longer Supported - The CLI now requires Node.js 20 or later. Node.js 18 reached end-of-life in April 2025 and is no longer supported. The CLI will now fail with a clear error message if you attempt to run it on Node.js 18.

Improvements

  • Only Auto-Init Outside Existing Projects - The install and search commands no longer automatically initialize a project when run in a subdirectory of a Tessl project directory. This prevents accidentally creating unwanted projects when running commands after changing directories. To initialize a project, explicitly run tessl init first.

Bug Fixes

  • Fixed an issue where the init command's failed to identify and install relevant tiles.

0.55.1

Improvements

  • Faster Auto-Updates - The CLI now checks for updates every 3 hours (down from 24 hours), ensuring you get critical fixes and improvements more quickly. You can still adjust the interval with TESSL_AUTO_UPDATE_INTERVAL_MINUTES or disable it by setting it to 0.

0.55.0

New Features

  • Updated Workspace Roles - Workspace member roles have been updated to: member, publisher, manager, and owner (the viewer role has been removed)

Bug Fixes

  • Fixed authentication issue where API token authentication (TESSL_TOKEN) would fail after token refresh attempts, causing authenticated API calls to fail

0.54.0

New Features

  • Tile Manifest Validation - The describes field in tile manifests is now validated to ensure it contains a valid PURL (Package URL) format. Invalid PURLs or unsupported package types will show helpful warnings during tessl tile lint, tessl tile pack, and tessl tile publish operations

Improvements

  • Project Directory Detection - Improved project directory discovery logic allows the CLI to better locate your tessl.json even when running commands from subdirectories within your project

Bug Fixes

  • Fixed missing newline after tessl list output for better terminal formatting

0.53.0

New Features

  • Go Modules Support - Dependency scanner now detects Go projects and extracts dependencies from go.mod files

  • Auto-Init on Search - When selecting a tile from search results, the CLI now automatically initializes the project if needed (creates tessl.json)

  • Dynamic Terminal Sizing - Interactive prompts now adapt to your terminal height for better readability

  • Escape Key Cancellation - Press Escape to cancel select/checkbox prompts

Improvements

  • Smarter Context Tool - When no documentation is found, the tool now suggests running a search to find relevant tiles

  • CI Environment Detection - Auto-update and version checks are now automatically disabled in CI environments

Bug Fixes

  • Fixed tile installation failures when system temp directory is on a different filesystem (handles cross-device moves)

0.52.2

No changes in this release

0.52.1

Improvements

  • Homebrew installation now available for stable releases

  • MCP server stability improvements

0.52.0

New Features

  • Added tessl tile lint command to validate tiles before publishing

Bug Fixes

  • Tile upgrades now properly clean up old files when installing new versions

  • Fixed markdown link validation to skip code blocks in tile documentation

0.51.0

  • MCP Tool Improvements

    • Renamed get_library_context tool to query_library_docs and updated descriptions for better clarity

    • Updated cli-setup steering tile version to reflect tool rename and improve adoption

  • Tile Management

    • Added tessl list command to display installed tiles

  • CLI UX

    • Improved CLI message spacing and copy for better readability

0.50.6

  • Added the ability to archive and unarchive workspaces

    • Archiving a workspace allows you to non-destructively remove workspaces you no longer wish to use or see. Archiving a workspace also archives all tiles in that workspace. This means that users can still install those tiles if defined in their manifest, but will not otherwise see them in search etc.

    • Unarchiving, as you’d expect, shows a workspace once again. However, it does not unarchive tiles within the workspace, to avoid potentially unarchiving content that was previously archived before the workspace was.

  • Fixed a bug when authenticating in multiple machines that would result in our MCP tool get_library_context only working on the last machine you authenticated.

0.50.5

We added a new tessl tile pack command which validates and builds a tarball for a tile. It can be useful to validate things before doing tessl tile publish.

Also fixed a bug where the CLI would fail to run when who signed up without a first or last name.

0.50.4

Fix tessl tile publish requiring an absolute path

0.50.3

This release marks a significant shift in focus. We've rebuilt the CLI from the ground up as an Agent Enablement Platform, pausing work on the Tessl Framework to concentrate on our registry functionality and agent integration.

We really appreciate all the feedback we have received so far. Please, keep it coming.

What's Changed

Getting Started is Now Simpler

When you run tessl init in your project, it now automatically detects your dependencies and pulls relevant tiles from the registry. For teams already using tessl, new developers only need to install the CLI and grant MCP server permissions—everything else happens automatically when the MCP starts up.

Smarter Agent Integration

Instead of agents searching through generated documentation, they now use our new get_library_context MCP tool to query tiles directly. This requires logging in to tessl, but makes context retrieval much more efficient. The MCP tools also include login (for in-session authentication) and status (for checking project state).

Note: KNOWLEDGE.md is no longer generated since agents now pull context on-demand.

Command Reorganization

We've streamlined the command structure. Changes to existing commands:

  • tessl registry install|search → tessl install|search

  • tessl registry sync → tessl install --project-dependencies

  • tessl registry publish|unpublish|archive → tessl tile publish|unpublish|archive

  • tessl version → tessl --version

Release Channels & Auto-Updates

You can now choose between latest (default, stable) and beta (early access) channels. The CLI checks for updates hourly and auto-updates transparently (max once per 24 hours). Configure the interval with $TESSL_AUTO_UPDATE_INTERVAL_MINUTES or set it to 0 to disable.

New Commands

  • tessl doctor - diagnose authentication, manifest status, detected agents, and dependencies (add -json for full dependency details)

  • tessl uninstall - remove tiles from your project

What's Removed

The Framework functionality is no longer included. If you need the full framework features, v0.28.0 remains available (though development is paused).

Currently, automatic setup only supports Claude Code and Cursor. We'll add other agents based on requests—in the meantime, you can manually configure the MCP with any agent.

Note: This is a major rewrite (v0.30.0 → v0.50.2). Existing workflows will need adjustment.

(Updated Nov 27, 2025)

0.28.0

New Features

  • Invoking setup agent via npx will now configure mcp to use tessl via npx, ensuring smoother setup for users without a global install.

  • Added integration with Cursor IDE for automatic generation and application of steering rules from tiles.

  • Added tessl registry uninstall to easily uninstall tiles.

Improvements

  • Improved error messages for the add-member command to enhance clarity.

  • Improved tessl status output to better reflect post-generation changes.

  • Aligned arguments for tessl registry unpublish and tessl registry archive.

Bug Fixes

  • Fixed detection of direct dependencies in the pip detector.

  • Resolved issue where unsupported package managers showed unnecessary user-facing messages.

  • Extended display name support to include PyPI and Maven packages.

  • Removed outdated compatibility code for specs.json.

0.27.0

New Features

  • New tessl setup project-info Command: CLI-only users can use this command to add details that Tessl tools require to AGENTS.md.

  • Framework Initialization: you can choose “full-framework” (closed beta, login required) or “registry only” when running init.

  • Steering Rules: Tiles can now define agent behavior rules via a new steering section in their manifests. These rules are automatically aggregated into a RULES.md file.

  • Local Usage Spec Installation: Added support for installing tiles from local directories via a new source field in tessl.json.

Improvements

  • Simplified usage spec installation paths by removing version info from the directory structure.

Bug Fixes

  • Fixed config list to return empty results instead of throwing errors when no config file is present.

0.26.0

New Features

  • Selecting Cursor during tessl init or via tessl setup agent will now automatically install rule files into .cursor/rules/tessl/framework as part of project setup, improving Framework adherence.

0.25.0

New Features

  • Improved Tile Installation UX: Tiles suggested during install/update are now selected by default, making the default path simpler for users.

  • Improved Help for tessl init: The -help output for tessl init now lists available agents, making it easier to discover options.

  • Non-Interactive Shell Support: CLI installation no longer blocks in non-interactive shell environments.

Improvements

  • Better Logging Behavior: In non-interactive mode, JSON logs are now correctly sent to stderr, preserving standard piping behavior.

  • Help Text Visibility: Tile help text remains visible even when tiles are deselected, improving clarity during installation.

Bug Fixes

  • Maven Dependency Detection: Fixed issues with the Maven dependency detector to ensure accurate detection.

  • Logging Flushing Reliability: Addressed a flakiness issue by ensuring that stdio is flushed on close, not exit.

  • Ink Render Handling: Corrected usage of Ink’s rendering logic to prevent hanging or exit-related issues.

  • Security: Updated pino logger to remove a transitive vulnerability.

0.24.0

New Features

  • tessl registry sync to synchronize tiles from the registry.

  • tessl setup framework to switch between the full Tessl framework and “registry-only” mode.

  • tessl stamp to manually sync spec/code hashes after intentional edits so tessl status stops flagging them.

  • tessl registry search now matches by full tile name (workspace/name), making it easier to find your own tiles.

  • tessl registry list added to browse available tiles.

  • tessl document adds tests to spec by default.

Improvements

  • tessl status surfaces an explicit error if bootstrap hasn’t been run.

  • Tool calls will fail if agent bootstrap process has not been run, with guidance to fix.

  • Added --print-project-cache flag for getting the path to the project cache.

  • Removed interactive tool picker removed to simplify workflows.

  • AGENTS.md now includes clearer “bootstrap” hints and wording tweaks to reduce confusion about when/why bootstrap should run.

Bug Fixes

  • MCP commands now authenticate correctly in all call sites.

  • Reduced noisy output during tessl registry sync.

Compatibility

  • Minimum Node.js version is now >= 22.0.0.

0.23.0

New Features

  • Added support for GitHub Copilot.

  • tessl edit now supports code files that have an associated @describe spec. Changes are made via the spec.

Improvements

  • tessl whoami command now includes your user ID.

  • Reduced the chances of "token expired" errors, by proactively refreshing tokens when commands are run.

  • Test commands will now time out if no output is received for a set period, preventing hangs.

  • Registry commands now prompt for initialization if the workspace isn’t already set up.

  • Unused .tessl/usage-specs directories are now removed during sync if the corresponding entries are removed from tessl.json.

  • Test generation is now controlled by a unified generateTests param, which always skips locked tests.

  • Improved list command usability, to make it easier for agents to select the right parameters.

  • tessl registry publish skips uploading irrelevant .md and .gitignored files.

Bug Fixes

  • tessl status no longer shows duplicated test paths.

  • Resolved issue where interactively selected tools weren’t able to run.

  • Fixed Goose setup, so that correct .gooserules configuration is used.

Deprecations

  • Removed deprecated annotations like @describes, @generates, and @satisfied-by.

⚠️ Be sure to check out the changes in 0.22.0 if you're coming from an older version

0.22.1

Bug Fixes

  • Fixed a project language detection issue that would occasionally cause errors across different commands.

0.22.0

⚠️ Upgrading for users who installed via npm

If you have already installed tessl via npm, you'll need to:

  • Run npm uninstall -g tessl-alpha (if you have a version earlier than v0.21.0)

  • Run npm i -g @tessl/cli to update to the latest version.

The update command will work as expected from v0.22.0 onwards.

Camel case flag support has been removed

Camel case flag support has now been fully phased out, all command flags should be provided in kebab case.

New Features

  • init now offers the option to set up an agent and MCP integration when initializing a project for the first time.

Improvements

  • Support information is now listed in help for logged-out users.

  • Tool parameters are now displayed before model parameters in tool-level help.

  • Links are now supported in kitty terminal.

Bug Fixes

  • Fixed the rules file targeting in Gemini CLI agent setup.

  • feedback is now gated to authenticated users, unauthenticated users can request support via email (support@tessl.io).

0.21.2

Bug Fixes

  • Fixed MCP server not allowing invocation of install or search tools when not logged in.

0.21.1

Improvements

  • Running tools with spec-registry-only context will now fail early and remind you to install the Tessl Framework before continuing.

  • Added ability to exit registry search with the Escape key.

  • Search results now link to the spec registry page instead of individual package registries.

Bug Fixes

  • Fixed Ctrl+C handling with the experimental observe command.

  • Fixed a deprecation warning on registry install.

0.21.0

⚠️ Upgrading for users who installed via npm

We have now published to public npm! This means that if you installed Tessl using npm, auto update with tessl update will not work for you for this version. To update, you’ll need to run:

⚠️ Re-initializing your projects

With this release, you’ll need to re-initialize any previously-created Tessl projects by running tessl init inside those directories.

Breaking Changes

  • Removed test generation from the build tool and introduced a new build-tests tool

  • The spec format has been updated to allow capabilities to contain requirements that don’t have [@test] links:

    • create and edit specs will only add [@test] links if explicitly asked to do so in the --prompt

New Features

  • Our spec format now supports distinguishing between three types of tests:

    • locked tests: capture functional requirements provided

      • Denoted by { .locked } next to the [@test] link or in a header containing [@test] links.

      • You can manually mark tests as locked or use tessl test to do it by passing --lock-tests.

    • impl tests: cover implementation details that are tested to identify changes in behaviour disconnected from a spec’s functional requirements.

      • Denoted by { .impl }.

      • They are generated by tessl document --include-impl-details .

    • draft tests: are untagged and could have been added manually or using edit or create

      • You can use tessl test --lock-tests to automatically lock all draft the tests from a spec when all tests pass.

  • Added flags to build-tests tool to select which kind of tests to generate --generate-draft-tests, --generate-locked-tests, and --generate-impl-tests.

New Commands & Tools

  • Added new registry install, registry search, and registry sync commands for working with Usage Specs.

  • Added a new test tool, to run all of the tests for a given spec.

  • Added generate-tests tool to add tests to a given spec.

  • Added experimental observe tool to observe MCP tool invocations.

Spec Registry

  • Unauthenticated users can now access a subset of Tessl’s features to add Usage Specs to their projects.

    • Running init while logged out will set up AGENTS.md and framework files relating to the Tessl Spec Registry.

Global Config

  • config commands now support the --global flag, for updating the global Tessl config.

  • The global config now supports a shareUsageData key to allow for analytics opt-out.