agentleFS
edxleonedxleon/runspector/.claude/skills/session-end/SKILL.md

session-end

Skill9 starsChanged 11 days agoMITView on GitHub

Close a working session on runspector - state of the tree, branches and pull requests, the last workflow runs, and the project memory brought up to date so the next session starts where this one stopped. Use when the maintainer says "session end" or asks for a handoff.

28 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use session-start and ship.

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.
  • bitwize-music-studioSkill

    session-start

    Runs the session startup procedure - verifies setup, loads config and state, checks skill models, and reports project status. Use at the beginning of a fresh session.

    Also in 11 projects that use this

  • AWSSkill

    ship

    Finalize dev work on an issue branch — update docs, push, and open a PR.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 21 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Learned: only what a future session would otherwise get wrong and cannot find in the code, AGENTS.md or the commits - a measurement, a …

    line 39
  2. Distinctive:

    If this session found a new "when you change X, also do Y", add the row.

    line 49

“Common” is measured: kept by at least 6 in 10 of the 21 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

Session end

The repository is public, so the session's story does not go into a file in it. It goes into commits and pull requests (what changed and why) and into the project's auto memory (what the next session needs and cannot read from the repository). This skill makes sure nothing of the session is left only in the conversation.

1. Facts

Run, in parallel:

git status --short
git branch --no-merged origin/main          # local work that never reached main
git log --oneline origin/main..HEAD
gh pr list --state open
gh run list --limit 15
  • Uncommitted or unpushed work of this session: commit it on a branch and open a pull request, or name it as an open thread below. Never leave it unmentioned.
  • A red or cancelled run of evals, sweep, mutation or scorecard: read its summary now and say what it was.

2. The project memory

The memory index (MEMORY.md) loads at every session start; the status memory of the project holds the state. Update it - or create it, if there is none - with:

  • Shipped: version, date, what changed for the runner, in one line per release.
  • Open: each item with owner (maintainer or session) and the date it was added; remove what this session finished.
  • Learned: only what a future session would otherwise get wrong and cannot find in the code, AGENTS.md or the commits - a measurement, a pitfall, a decision with its reason. Not a diary.

A rule that can be checked mechanically belongs in a test or hook instead of the memory (AGENTS.md lists the existing gates); say so as an open item if it is more than a few lines.

3. AGENTS.md

If this session found a new "when you change X, also do Y", add the row.

4. Handoff

## Session end
Done:
- ...
Next session starts with: <the most concrete next step>
Open threads: <only when there are any>

Push, merge and release stay the maintainer's word.

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.