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

finish

Skill1 starsChanged 13 days agoMITView on GitHub

Save an accurate StopCode handoff and logically end the tracked session, even if the work is incomplete, optionally starting quiet hours the user chose. Use when the user runs /stopcode:finish, says they want to stop or clock out for the day.

22 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use bootstrap, debug and 8 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.
  • OpenAISkill

    bootstrap

    Project bootstrapping orchestrator for repos that depend on Vercel-linked resources (databases, auth, and managed integrations). Use when setting up or repairing a repository so linking, environment provisioning, env pulls, and first-run db/dev commands happen in the correct safe order.

    Also in 3 projects that use this

  • AnthropicSkill

    debug

    Structured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack trace, "this works in staging but not prod", "something broke after the deploy", or when behavior diverges from expected and the cause isn't obvious.

    Also in 5 projects that use this

  • Hugging FaceSkill

    implement

    Make tests pass. Invoke after /write-tests produces failing tests.

    Also in 6 projects that use this

  • dillonluiSkill

    design-review

    Review a view or flow for UX and UI issues. Provides severity-ranked, actionable findings grounded in established design heuristics. Use when the user asks for design feedback, UX review, or UI critique.

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 8 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not start or continue implementation work.

    line 17
  2. Very specific:

    Run exactly one command, built from the choices, on its own (no cd, &&, ;, pipes or redirection):

    line 24
  3. Very specific:

    Do not propose new tasks or a backlog.

    line 35

“Common” is measured: kept by at least 6 in 10 of the 18 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:finish

Arguments from the user: $ARGUMENTS

Stopping must never require the mission to be complete. Your job is to park the work honestly, not to finish it.

Steps

  1. Do not start or continue implementation work. If a command you launched earlier is still running, leave it alone and mention it.
  2. Interpret the arguments:
    • a duration (30m, 2h) or until HH:MM / tomorrow = the quiet interval the user wants;
    • --protect = block new coding actions in this project during the interval (StopCode's PreToolUse hook denies new tool calls; it does not close Claude Code, cancel running commands, or affect other projects);
    • --complete = the user states the original goal is done (recorded as a user confirmation, separate from verification);
    • any other words = a one-line note for the handoff.
  3. If the arguments do not say whether to protect the time, ask one question with AskUserQuestion: "How do you want to stop?" with options "Just park my work (no blocking)", "Park and block new coding here for 30 minutes", "Park and block new coding here until my next working block". Keep it short; accept the answer and move on.

  4. Run exactly one command, built from the choices, on its own (no cd, &&, ;, pipes or redirection):

    node "${CLAUDE_PLUGIN_ROOT}/bin/stopcode.js" finish [--quiet <duration>] [--until <HH:MM|tomorrow>] [--protect] [--complete] [--note "<one line>"]
  5. Report exactly what the command reported, line by line: handoff saved (with its path) or failed; tracked session ended; mission parked or completed; quiet hours active until a time (blocking or advisory) or not requested or failed. If one part failed, say so plainly; do not summarise two results as one success.
  6. Close with "Your work is parked." only if the handoff saved. Never claim Claude Code exited or that the user has rested.

After finishing

Do not propose new tasks or a backlog. If the user keeps chatting, be brief. Their next action is written in the handoff; /stopcode:resume restores it later.

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