agentleFS
Sign inStart free
foxrun-aifoxrun-ai/foxrun/skills/log/SKILL.md

log

Skill6 starsChanged 17 days agoMITView on GitHub

Write one receipt to the owning workspace's history at a material moment: a decision, a direction change, shipped work, a material source, or a blocker. Use mid-session or at the end of a session when the person says log this, land the receipt, note that decision, or record what shipped.

18 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 0 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 16 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read workspace_settings.<workspace>.database in ~/.foxrun/config/person.json.

    line 24
  2. Very specific:

    If it is absent, use ~/.foxrun/data.db.

    line 25
  3. Very specific:

    Read back the new comment in the show output.

    line 33
  4. Very specific:

    Follow ~/.foxrun/config/gates.md before any gated action.

    line 46
  5. Very specific:

    No deletes, rewrites, cleanup, backfill, or edits to prior receipts, ever.

    line 48

“Common” is measured: kept by at least 6 in 10 of the 16 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

log

History only grows. One receipt per material moment, written once, never edited.

Trigger phrases

log this · land the receipt · note that decision · record what shipped

Run

  1. Resolve the workspace that owns the changed work; never route by the current directory alone.
  2. Confirm the moment is material: a decision, a direction change, a shipped result, a material source, or a blocker. Skip routine narration and duplicates.
  3. Choose one type: progress, decision, source, blocked, or done.
  4. Select <workspace>, its confirmed <tracker>, and the existing task that owns this moment. Read workspace_settings.<workspace>.database in ~/.foxrun/config/person.json. If it is absent, use ~/.foxrun/data.db. Pass the workspace and tracker to the installed command. Record one event with the installed command:
python3 ~/.foxrun/events/log.py add comment --workspace <workspace> --db <tracker> --receipt-root ~/foxrun/<workspace> --by <agent> <task id> "<type>: <title>; <body>; refs: <ids or paths>"
python3 ~/.foxrun/events/log.py show --db <tracker> --subject-type task --subject-id <task id>
  1. Read back the new comment in the show output. Confirm its comment ID, workspace, and type in one line. Events live in the selected tracker. Keeper builds <workspace>/history/LOG.md from events. A missing task waits for placement through program-control; do not create a separate log file.

Failure modes

  • Owning workspace ambiguous: ask one routing question before writing.
  • Tracker or task absent: stop and name the missing owner. Do not invent another history.
  • Receipt already exists: report it and do not duplicate it.
  • Uncertain command result: read back before any retry.

Boundaries

  • Follow ~/.foxrun/config/gates.md before any gated action.
  • Fires by hand, mid-session or at the end of a session. No schedule.
  • No deletes, rewrites, cleanup, backfill, or edits to prior receipts, ever. Moving a workspace from log.md to log.jsonl is a separate, approved step done with ~/.foxrun/events/log_switch.py.

log_switch.py stages legacy history for review. It does not write new event receipts or authorize promotion.

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