agentleFS
inclusionAIinclusionAI/Choruz/.agents/skills/choruz-archive-agent-notes/SKILL.md

choruz-archive-agent-notes

Skill1.1k starsChanged 18 days agoApache-2.0View on GitHub

Use when adding, auditing, pruning, archiving, restoring, or reviewing Agent Notes in this repository; checks every new note for superseded active records, classifies implemented notes by future decision value, deletes rejected notes that no longer prevent a tempting mistake, and applies the frozen archived/{class} rules.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the Agent Note rules, the archive instructions and the implemented-folder instructions before classifying.

    line 12
  2. Very specific:

    Proposed, never archive: keep a live proposal active.

    line 22
  3. Distinctive:

    Rejected, delete: delete the note when the rejected idea is obsolete, superseded, or unlikely to prevent re-litigation.

    line 24
  4. Distinctive:

    Do not archive toward a quota.

    line 26
  5. Very specific:

    Search for inbound links from active prose (git grep -n "<filename>").

    line 36
  6. Distinctive:

    After the move, never edit, move, or delete the note.

    line 39
  7. Very specific:

    Run python3 scripts/verify_agent_notes.py, python3 -m unittest discover scripts/tests, and git diff --check.

    line 43

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Archive Choruz Agent Notes

Reduce the active decision corpus without erasing history that can still guide work. Judge every note semantically; word count and age are discovery aids, never archive criteria.

Read the contracts

Read the Agent Note rules, the archive instructions and the implemented-folder instructions before classifying. Use current code, migrations, configuration, docs/, newer notes and inbound links to establish whether a rationale still owns or constrains anything.

Check supersession when adding a note

Every new Agent Note triggers a scoped audit of active notes covering the same decision, mechanism, or rejected alternative. Classify each full or partial supersession while writing the new note: archive qualifying implemented notes in the same PR, retain and cross-link partial supersessions or independently useful rationale, reject obsolete proposals, and delete rejected notes that no longer prevent a plausible mistake. Apply the consolidation rule in the README when the new owner absorbs every unique proposition; do not defer a known match to a later corpus audit.

Classify by future value

  • Implemented, keep active: retain a note when its rationale, alternatives, negative guarantees, wire or database semantics, ownership boundary, security rule, or reintroduction condition is likely to guide a future change. Length does not matter.
  • Implemented, archive: archive a note when the shipped decision is complete and its body is unlikely to guide future work: one-off UI chrome, a narrow adapter, a minor closed bug, superseded implementation detail, or process history whose current behaviour is obvious elsewhere.
  • Proposed, never archive: keep a live proposal active; if it is no longer worth pursuing, reject it with an honest reason on the Status: line.
  • Rejected, keep only as a guardrail: retain a rejection only when the losing proposal remains a tempting, meaningful mistake and the note explains why it loses.
  • Rejected, delete: delete the note when the rejected idea is obsolete, superseded, or unlikely to prevent re-litigation. Repair or delete inbound links.

Do not archive toward a quota. Inspect every note in scope, classify analogous groups under one principle, use best judgement for close cases, and record genuinely borderline decisions in the PR.

Calibrated examples

Archive implemented notes such as a closed sidebar-chrome tweak, a one-driver adapter detail whose current code is authoritative, or a completed migration checklist. Keep implemented notes such as workspace-scoped isolation (an ownership and security boundary) or per-turn roster injection (it states the negative guarantee that no team file exists). The four RFCs under archived/feature/ are the reference for what archival looks like: header block added, body untouched.

Archive one implemented note

  1. git mv the file from implemented/<class>/ to archived/<class>/; implemented is deliberately absent from the archive path.
  2. Insert only Archived: YYYY-MM-DD immediately below Status: implemented. Make no other body edit: do not reformat, update facts, or repair links inside the note.
  3. Search for inbound links from active prose (git grep -n "<filename>"). Redirect them to the current authority, retarget them to the archived path only when the historical snapshot is intentionally cited, or delete them.
  4. Run python3 scripts/verify_agent_notes.py.

After the move, never edit, move, or delete the note. Archived notes remain valid link targets but are historical snapshots, not authority for current behaviour.

Validate and report

Run python3 scripts/verify_agent_notes.py, python3 -m unittest discover scripts/tests, and git diff --check; select any additional evidence through choruz-pre-push-checks.

Report active implemented notes kept, implemented notes archived, rejected notes kept or deleted, proposed notes rejected if any, and every genuinely borderline case with its chosen outcome.

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.