AI4Math-Lean-Agents
CLAUDE.md9 starsChanged 4 months agoMITView on GitHub
For Lean setup-only work in this repository, read and follow: For Lean formalization or proof work in this repository, read and follow the shared Skill layer: Shared helper scripts, references, prompts, schemas, examples, and tests live in: Use Claude Code as the primary Lean coding agent. Backend integration is adapter-first: Numina and Archon are recommended adapter candidates, not defaults or hard requirements. Preserve the built-in official Numina adapter recipe, and connect other Lean-specialist backends only through the backend adapter checklist…
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/lean-formalization.mdcCursor rule
- lean-formalizationSkill
- lean-formalizationSkill
- lean-setupSkill
The file
We split this CLAUDE.md into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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
- Distinctive: line 26
Do not treat a language switch as a task reset.
- Distinctive: line 27
When no target is provided, run or propose a safe local smoke/readiness check before asking for more input.
- Distinctive: line 28
Use the bundled smoke test when no user target is available.
- Distinctive: line 31
Do not require API keys for the default coding-agent path.
≈ “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.
Files
Claude Code Instructions
For Lean setup-only work in this repository, read and follow:
skills/lean-setup/SKILL.mdFor Lean formalization or proof work in this repository, read and follow the shared Skill layer:
skills/lean-formalization/SKILL.mdShared helper scripts, references, prompts, schemas, examples, and tests live in:
skills/lean-runtime/Use Claude Code as the primary Lean coding agent. Backend integration is adapter-first: Numina and Archon are recommended adapter candidates, not defaults or hard requirements. Preserve the built-in official Numina adapter recipe, and connect other Lean-specialist backends only through the backend adapter checklist after setup, call, credential, mutation, validation, and failure contracts are documented. Setup-only mode should create or verify the Lean/mathlib workspace without asking for a theorem target.
Match the user's language by default. If the user's language is ambiguous, default to Chinese. Lead the interaction: inspect context, summarize what is ready, recommend the next useful step, and ask at most one blocking question. Do not treat a language switch as a task reset; keep the current diagnosis and continue leading in the new language. When no target is provided, run or propose a safe local smoke/readiness check before asking for more input. Use the bundled smoke test when no user target is available. Formalization/proof readiness should inspect local Lean readiness first; inspect Numina/backend readiness only when the user asks for an optional Lean-specialist backend. Setup-only readiness should focus on local Lean/mathlib state, and should mention or inspect a backend only when the user asks for an optional backend adapter. Do not require API keys for the default coding-agent path. Shared workspace is the default Lean project context; Numina may target it instead of upstream examples.
Deploy or call a backend adapter only after explanation and approval. Keep secrets in environment variables or ignored local files.
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
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.

