agentleFS
The-Artificer-of-Ciphers-LLCThe-Artificer-of-Ciphers-LLC/skills-from-the-artificer/work-journal/SKILL.md

work-journal

Skill6 starsChanged 33 days agoMITView on GitHub

Record and recall per-branch session decisions across sessions and agent worktrees using an append-only local markdown journal. Use at the end of each short work cycle, after a build or test result, before handing work to another agent, or when resuming a branch.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

work-journal

Convention: per-branch, append-only, local markdown at $(git rev-parse --git-common-dir)/work-journal/<branch>.md. Every worktree of the repository shares the same git common dir, so all agents read and write the same folder; nothing is committed. (Slashes in branch names are replaced with -.)

The bundled script scripts/journal.sh implements it. Optional wiring you can add yourself: a session-start hook that prints journal.sh tail 2, and a Stop hook that asks for an entry when HEAD has no journal entry. Neither is required.

Durable, curated lessons belong in your project's own notes; when a journal entry produces a lesson, copy the one-line lesson there.

Entry shape (under 15 lines)

**Change:** <what changed, one sentence>
**Decision:** <what was decided and why, if the code does not say it>
**Evidence:** <file:line, test names, telemetry, build number>
**Verified:** <build, tests run and result>
**Next:** <the next highest-leverage step, or blocker>

Commands

J="<path-to-this-skill>/scripts/journal.sh"
"$J" add <<'MD'
**Change:** ...
MD
"$J" tail 5

The header (date, branch, short HEAD sha) is added for you. Journal after committing.

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.