agentleFS
Sign inStart free
CG-5228CG-5228/ClaudeCodeImpactLab_hackathon/skills/status/SKILL.md

status

Skill1 starsChanged 13 days agoMITView on GitHub

Show the StopCode mission, verification evidence, deferred work, elapsed time and boundary state for this project, concisely. Use when the user runs /stopcode:status or asks where the mission stands.

177 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use off, list and 7 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • StakeholderSenseiSkill

    off

    Disable polygraph for this repo (user-only escape hatch; all hooks no-op)

    Also in 4 projects that use this

  • SuShuhengSkill

    list

    Use when checking obshare-cli upload history, finding document tokens, or reviewing previous upload URLs and permission snapshots.

    Also in 8 projects that use this

  • codebycoreySkill

    new

    Start a new change with a proposal. Use when starting a feature, creating a proposal, or beginning planned work.

    Also in 7 projects that use this

  • michaelenglandSkill

    import

    This skill should be used when the user wants to import an existing .pptx file into deckwright, bring in a PowerPoint that was created outside this tool, reverse-engineer a presentation for editing, or invoke /deckwright:import. Converts a .pptx into a PptxGenJS generation script so it can be edited and regenerated through the deckwright pipeline.

    Also in 5 projects that use this

  • stotihvSkill

    knowledge

    Extracts knowledge from Amp threads and updates project docs. Use when asked to document recent work, sync docs after an epic, summarize what changed, or update AGENTS.md from thread history.

    Also in 4 projects that use this

  • VercelSkill

    next

    Next.js renderer for json-render that turns JSON specs into full Next.js applications with routes, layouts, SSR, and metadata. Use when working with @json-render/next, building Next.js apps from JSON specs, or creating AI-generated multi-page applications.

    Also in 9 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 146 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run exactly this command on its own (no cd, &&, ;, pipes or redirection.

    line 14
  2. Very specific:

    If the output says there is no StopCode project here, say so and point to /stopcode:start <goal>.

    line 21
  3. Very specific:

    Only use --outcome pass when the output you saw shows the check passed.

    line 27
  4. Very specific:

    When the user states a criterion is done without a check: criterion confirm <id> records a user confirmation, which StopCode labels …

    line 28
  5. Distinctive:

    Never present elapsed time as focused time, and never claim the user rested because no activity was observed.

    line 33

“Common” is measured: kept by at least 6 in 10 of the 146 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/stopcode:status

Optional focus from the user: $ARGUMENTS

Steps

  1. Run exactly this command on its own (no cd, &&, ;, pipes or redirection; during quiet hours only the bare StopCode command passes the hook):

    node "${CLAUDE_PLUGIN_ROOT}/bin/stopcode.js" status
  2. Relay the output faithfully and concisely (no more than ~15 lines): mission and its status headline, each criterion with its state and evidence, the next step, elapsed time labelled as elapsed wall-clock time, breaks (say "unknown" when none is recorded), quiet-hours and monitoring state, parked ideas and accepted additions, and the integration line.
  3. If the output says there is no StopCode project here, say so and point to /stopcode:start <goal>.

Recording progress (only when the user asks, or when you just ran a check in this session)

  • A check you actually ran this session can be recorded as evidence: node "${CLAUDE_PLUGIN_ROOT}/bin/stopcode.js" evidence add --kind test_run|build|command|manual_check --outcome pass|fail|unknown --summary "<command and parsed result>" --criterion <id or number> Only use --outcome pass when the output you saw shows the check passed. Unknown results are unknown, never pass.
  • When the user states a criterion is done without a check: criterion confirm <id> records a user confirmation, which StopCode labels separately from verification.
  • Classify new requests conservatively as in scope, necessary dependency, optional improvement, scope expansion, unrelated, or uncertain. Running the relevant tests for the goal is in scope; fixing a dependency the goal needs is usually in scope; "also reject empty passwords" during a login-validation fix is not automatically an expansion; adding a mobile app is. Record decisions with scope accept "<text>" (accepted addition) or idea add "<text>" (deferred); do not block work over scope and do not re-raise additions the user already accepted.

Rules

  • Never present elapsed time as focused time, and never claim the user rested because no activity was observed.
  • "Your original goal is complete" is only true when the status output says so; otherwise report the actual state (for example "Verification pending").

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free