agentleFS
Sign inStart free
enckequityenckequity/samebrain/skills/rule-mine/SKILL.md

rule-mine

Skill0 starsChanged 5 months agoMITView on GitHub

Turn repeated, evidenced user corrections into a minimal guardrail pull request when /rule-mine is invoked.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Never edit guardrails directly.

    line 10
  2. Very specific:

    Gather signals: Look for corrections the user had to make more than once: facts in {{REPO}}/memory/MEMORY.md and memory/topics/*.md …

    line 14
  3. Distinctive:

    Stop: Never merge your own rule-mine PR.

    line 31
  4. Distinctive:

    If no cluster qualifies, say so and propose nothing.

    line 32

≈ “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

rule-mine

Rules should evolve from evidence. This skill turns repeated corrections into a proposed edit to {{REPO}}/global/guardrails.md — agent-proposed, human-merged. Never edit guardrails directly; the PR is the safety gate.

Procedure

  1. Gather signals. Look for corrections the user had to make more than once: facts in {{REPO}}/memory/MEMORY.md and memory/topics/*.md recording "stop doing X" / "always do Y" moments, and your own recollection of this machine's recent sessions. Telemetry ({{REPO}}/telemetry/) shows which agents and machines were active where — use it to judge whether a pattern is one machine's quirk or fleet-wide.
  2. Cluster. Group signals describing the same underlying behavior. A cluster qualifies only if it shows up 3+ times or caused real damage once (reverted work, broken protected surface).
  3. Draft minimally. For each qualifying cluster, draft the smallest guardrail edit that would have prevented it — one line where possible, matching the existing style of guardrails.md. No speculative rules.
  4. Propose as a PR. Branch under your agent namespace, commit only the global/guardrails.md edit (message feat: guardrail — <summary>), open a PR whose body quotes the evidence: each correction, where it happened, and the memory/telemetry pointer. Follow the claim protocol in global/coordination.md first.
  5. Stop. Never merge your own rule-mine PR; never edit rendered files. If no cluster qualifies, say so and propose nothing.

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