agentleFS
leonkoellerwirth-archleonkoellerwirth-arch/kickoff-ai/.claude/skills/session-stop/SKILL.md

session-stop

Skill1 starsChanged 3 months agoMITView on GitHub

Close a work session — save the repo memory, pass the hard gate, and commit & push everything so nothing is forgotten and nothing is left half-done. Counterpart to session-start. Trigger: "session-stop", "session-end", "wrap up", "end session", "done for today", "close the session", "sauber abschließen", end of a work session.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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. Very specific:

    If claude-mem is available, query it for this session's decision and discovery observations and use them as *candidates* — then decide per …

    line 14
  2. Distinctive:

    Write the judgment, never copy an observation verbatim.

    line 16
  3. Very specific:

    Write the HANDOFF entry: run ./scripts/session-snapshot.sh <today's-date> and fill in Done / Decided / Open / Next / Continuity warnings at …

    line 19

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “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

session-stop

Nothing forgotten, nothing half-done. Deterministic checks gate the close.

Steps

  1. Rescue the chat (mandatory). Any idea, decision, or owner instruction that lives only in this conversation is lost unless written down now. Capture it into HANDOFF.md / BIBLE.md. If claude-mem is available, query it for this session's decision and discovery observations and use them as candidates — then decide per item: BIBLE entry, HANDOFF entry, or nothing. Write the judgment, never copy an observation verbatim. Without claude-mem, work from the conversation directly.
  2. Record durable decisions in BIBLE.md's decision register (date · decision · why).
  3. Write the HANDOFF entry: run ./scripts/session-snapshot.sh <today's-date> and fill in Done / Decided / Open / Next / Continuity warnings at the top of HANDOFF.md (newest first).
  4. Pass the gate: ./scripts/gate.sh must print GATE: PASS. Fix reds; never commit over a red gate.
  5. Update CHANGELOG.md under [Unreleased] if user-facing behaviour changed.
  6. Commit granularly — Conventional Commits, one concern per commit. No sweep commit.
  7. Push, then run ./scripts/secure.sh — it must print SECURE: all saved.

Report the final gate + secure status in one line.

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.