agentleFS
matthewdonsemail-labmatthewdonsemail-lab/log/skills/captureRule/SKILL.md

captureRule

Skill63 starsChanged yesterdayMITView on GitHub

Maintain concise current instructions in AGENTS.md, preserving stable rule ids and archiving superseded context when Matt authorizes pruning.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the current task and current rules.

    line 14
  2. Very specific:

    Add or update a concise dated rule in Matt's meaning.

    line 15
  3. Distinctive:

    If Matt authorized removal or consolidation, preserve the prior text in the private workspace rule archive, outside this repository.

    line 16
  4. Distinctive:

    Keep the native ownership/scope rules authoritative.

    line 17
  5. Distinctive:

    Update the affected skill/spec and generated MCP guidance when applicable.

    line 18
  6. Distinctive:

    Check document links, parser-compatible rule formatting and citations.

    line 19
  7. Distinctive:

    When committing, include the rule, related source/docs and required AST-backed commit log entry together.

    line 20

≈ “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

Capture and maintain a rule

Current instructions first

AGENTS.md is the active implementation contract. Record durable constraints, scope and ownership there. Keep anecdotes, completed migrations, one-off messages and obsolete defaults in history or the relevant domain document.

Procedure

  1. Read the current task and current rules. Existing authorization is sufficient; do not ask again to prune rules Matt explicitly asked to prune.
  2. Add or update a concise dated rule in Matt's meaning. Preserve stable active rule ids and the ## Hard rules (from matt) heading because the knowledge/MCP collectors parse them.
  3. If Matt authorized removal or consolidation, preserve the prior text in the private workspace rule archive, outside this repository. Record old-to-current citations in the MCP generator's consolidated mapping. Never silently renumber a historical id to unrelated behavior.
  4. Keep the native ownership/scope rules authoritative. A platform procedure or old generated field inventory cannot reintroduce a superseded architecture.
  5. Update the affected skill/spec and generated MCP guidance when applicable. Generated guides are rebuilt from their sources. Do not load the full historical snapshot into active client instructions.
  6. Check document links, parser-compatible rule formatting and citations. Do not add or run application tests unless Matt asks. Do not perform paid semantic review as routine rule maintenance.
  7. When committing, include the rule, related source/docs and required AST-backed commit log entry together. Never bypass hooks. Report only checks actually performed.

Scope

Without explicit instruction to prune or supersede, preserve the existing durable constraint and resolve a genuine unanswered conflict. Do not manufacture a confirmation requirement when the current task already resolves it.

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.