agentleFS
mediajunkiemediajunkie/piper-morgan-product/.claude/skills/update-current-state/SKILL.md

update-current-state

Skill8 starsChanged 11 days agoApache-2.0View on GitHub

Update BRIEFING-CURRENT-STATE.md when work changes project status. Any agent

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Replace the stale line; don't add one under it: Keep the line's shape: - Item *(Role, YYYY-MM-DD [time], how you know)*: the fact.

    line 32
  2. Very specific:

    Run python3 scripts/check-current-state.py before committing.

    line 37
  3. Distinctive:

    Commit and push from your own worktree with the unit of work it describes.

    line 40
  4. Distinctive:

    Update the lines your evidence covers and leave the rest.

    line 44

≈ “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

update-current-state

docs/briefing/BRIEFING-CURRENT-STATE.md is a short "Now" page (v2.0, 2026-10-08, R6 step 3, PM-approved 2026-10-04). It says where the project stands today, one dated line per item. It is no longer a progress log: the old 169 KB file, Recent Progress included, is verbatim in docs/internal/architecture/decisions/briefing-current-state-history.log, and day-by-day progress lives in the omnibus logs.

When to use

  • Your work changed something the Now page states: the live alpha version, the latest tag, the MVP count, engineering focus, a usage or mail change, the R6 status, or a milestone position.
  • The session-start hook says BRIEFING: STALE, or a line you can attest to is visibly wrong (PM's standing request, 2026-04-22: any agent refreshes it; a partial update beats none).

How

  1. Get the fact from its source this turn, not from memory: curl https://piper-morgan.fly.dev/health, git tag, python3 scripts/sprint-truth.py, the rollup, your own session log.
  2. Replace the stale line; don't add one under it. Keep the line's shape: - **Item** *(Role, YYYY-MM-DD [time], how you know)*: the fact.
  3. Bump front-matter last_updated (and last_verified) to the newest date on the page.
  4. Narrative goes elsewhere: what happened belongs in your session log (the omnibus picks it up); superseded context worth keeping goes to the history log, appended, never into this page.
  5. Run python3 scripts/check-current-state.py before committing. CI runs it too (Code Quality): it fails if the page exceeds its size_cap_bytes (12,000) or if last_updated is older than the newest attested line.
  6. Commit and push from your own worktree with the unit of work it describes.

Only attest what you can

Update the lines your evidence covers and leave the rest. If you notice a line is wrong but can't verify the right value, say so in the line ("stale per X; owner to correct") rather than guessing.

Anti-patterns

Don'tInstead
Append an "UPDATE <dates>" paragraphOverwrite the line with today's fact and source
Copy PM's open-asks list onto the pageLink the attention rollup
Paste sprint listsPoint to sprint-truth.py
Leave last_updated behind the newest lineBump it; CI enforces this

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.