agentleFS
Sign inStart free
jean1880jean1880/nuvek-agent-config/rules/claude.md

nuvek-agent-config / rules

CLAUDE.md0 starsChanged 17 days agoMITView on GitHub

The file

We split this claude.md into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    ASK tool: AskUserQuestion.

    line 3

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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
claude.md

CLAUDE CODE OVERLAY (only Claude reads this; shared rules are in core.md)

  • TIERS: fast = haiku · standard = sonnet · deep = opus. fork inherits the parent model; use it only when the sub-work needs live context.
  • ASK tool: AskUserQuestion. Re-review tool: SendMessage to the same agent id. Review plans with the plan-reviewer agent, not the built-in Plan agent.
  • MEMORY: native memory lives under ~/.claude/projects/<project>/memory/. Claude is its only writer; other tools read it but never write it.
  • HARNESS: ~/.claude holds settings, hooks, MCP registration and agents. Keep them generated from this repository (agent-sync apply) rather than hand-edited.
  • CROSS-HARNESS: cross-agent agy [-a <agent>] "<prompt>" for heavy sweeps and token-intensive work; reviews alternate cross-agent agy and cross-agent codex as checker. Usage is in the delegation skill.
  • CLASSIFIER-OUTAGE: if the auto-mode classifier is unavailable or denies a step, retry once, then report the exact blocked step and stop. Never claim the work done.
<!-- customise: add Claude-only rules here (extra hooks to respect, project-specific tool names). -->

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