agentleFS
ImtylerrrrrrImtylerrrrrr/second-brain/skills/end-session/SKILL.md

end-session

Skill1 starsChanged 5 months agoMITView on GitHub

Checkpoint the session into the second-brain — records what actually happened (git-anchored) and what is next, updates the dashboard, syncs git facts. Use before ending a working session or before /clear.

12 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

second-brain: end-session

Git-anchored write. Follow the discipline below EXACTLY — Part 1 governs this skill.

!cat "${CLAUDE_PLUGIN_ROOT}/references/discipline.md"

Steps

  1. Locate the vault (cwd or ancestors containing Projects/Dashboard.md; else registered vaults in ~/.claude/second-brain/vaults, ask if several; none → "run /second-brain:setup first").
  2. Which repo(s) were touched this session? Evidence: this conversation's work + git -C <repo> status -sb + git -C <repo> log --oneline -10. Cannot tell → ASK the user; never guess.
  3. For each touched repo, update Projects/<repo>.md per Part 1:
    • ## ▶ Thread → Last: cited facts — ALL commits since that note's last_handoff_commit (hash+subject via git log <last_handoff_commit>..HEAD --oneline, or the full log if last_handoff_commit: none), not just commits made in this conversation turn; plus files changed, tests run, user decisions; Next: the user's stated intent (ask if unstated).
    • frontmatter → last_handoff_commit: $(git -C <repo> rev-parse --short HEAD), branch, last_updated: today.
    • ## 🕑 Session log → prepend one dated line.
    • Milestone candidates → append - [ ] confirm milestone "<name>" → /second-brain:analyze <repo> to ## ✅ TODO. Do NOT touch milestone boxes.
  4. Update the Dashboard row for this repo only (Last session · Next · Updated). Row missing → add it.
  5. Sync L1: bash "${CLAUDE_PLUGIN_ROOT}/scripts/sync.sh"
  6. Git hygiene: uncommitted/untracked changes in touched repos → flag them ("commit before you forget?"). Never commit for the user unless asked.
  7. Confirm in one line per repo: what was recorded + the anchor hash.

Rules

  • Facts cited, intent labeled, unknown → ask. NEVER check milestone boxes (that is /second-brain:analyze's job). No transcript summaries.

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.