agentleFS
Sign inStart free
reganomikareganomika/Bullpen/skills/refresh-rules/SKILL.md

refresh-rules

Skill1 starsChanged 4 months agoMITView on GitHub

Re-read the current ~/.claude/CLAUDE.md, this project's own CLAUDE.md (if any), and the model-routing skill right in this chat, no new chat needed. Use when the routing rules changed after this session started, and the chat is still running on the old version.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read right now, in full:

    line 6

≈ “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

Read right now, in full:

  1. ~/.claude/CLAUDE.md
  2. CLAUDE.md at the root of the current project, if it exists
  3. ${CLAUDE_SKILL_DIR}/../model-routing/SKILL.md (the model-routing skill that ships next to this one; on a plugin install that resolves inside the installed plugin's copy, which is the version actually loaded, and rule edits reach it only when the plugin updates. On a manual copy it is ~/.claude/skills/model-routing/SKILL.md. If the placeholder above was not substituted and still reads literally, use those two paths directly.)

Whatever they currently say applies for the rest of this session in place of what was in the system prompt at session start: the same rules, just re-read fresh, since these files can change after a session has already loaded and the system prompt doesn't hot-reload.

Apply this from now until the end of the session.

Don't try to judge whether anything changed compared to how you'd been behaving before: that's unreliable self-assessment, you have no accurate record of your own old system prompt to honestly compare against, and on a large accumulated context that guess easily comes out confident and wrong. Instead, always, regardless of any belief about what changed, produce a concrete checkable artifact right now, not a claim: the current iron rule for agent routing in one line (the required model parameter, route-gate if installed).

The user looks at what you produced and sees for themselves whether it matches what they expect right now, instead of trusting your claim.

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