agentleFS
moazessam376-devmoazessam376-dev/sparring/CLAUDE.md

sparring

CLAUDE.md0 starsChanged 2 months agoMITView on GitHub

Sparring is an agent skill: a hard technical interviewer and visual tutor for codebases the user built. SKILL.md and references/ are authoritative; docs/ holds dated design records; scripts/drill.mjs owns all state.

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:

    Every behavior rule in the skill traces to evidence in docs/research/.

    line 16

≈ “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.md — sparring

Sparring is an agent skill: a hard technical interviewer and visual tutor for codebases the user built. SKILL.md and references/ are authoritative; docs/ holds dated design records; scripts/drill.mjs owns all state.

Rule

  • Opus models only: if the model powering this session is any Claude Opus version (the system prompt names it), invoke the opus-as-fable skill (.claude/skills/opus-as-fable/SKILL.md) as your first action of the session and follow it for the whole session. Fable and Mythos sessions must not load it; they already behave that way.

Commands

  • node scripts/drill.mjs <command> — the state CLI. See the cheat sheet in SKILL.md.
  • node --test scripts/drill.test.mjs — the test suite. Must be green before any commit that touches the script.

Rules of the repo

  • Every behavior rule in the skill traces to evidence in docs/research/. A new rule needs a source or it does not ship.
  • State lives at $SPARRING_HOME or ~/.sparring/<project>/. Never write it by hand; go through the script.
  • The skill is read by Claude Code, Codex, and Cursor. Keep SKILL.md portable: no harness-specific tool names in it.
  • No emoji.

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.