audit-config
ethereum/execution-specs/.agents/skills/audit-config/SKILL.md
Check whether repository guidance and skills are still accurate.
Skill1.2k starsChanged today
What's in it
- Audit Config
- Checks to Perform
- 1. Verify File Paths
- 2. Verify CLI Commands
- 3. Verify Code Patterns
- 4. Verify Fork List
- 5. Verify Docs References
- Output
--- name: audit-config description: Check whether repository guidance and skills are still accurate. --- # Audit Config Periodic verification skill to prevent `AGENTS.md` and skills from going stale. Run this manually to check freshness (e.g., after a major refactor, before a release, or when onboarding). ## Checks to Perform ### 1. Verify File Paths Check that every file path or directory referenced in `AGENTS.md` and `.agents/skills/*/SKILL.md` still exists. Report any broken references. Confirm that `CLAUDE.md` is a symlink to `AGENTS.md`. Confirm that every `.agents/skills/<name>/` directory has a corresponding `.claude/skills/<name>` symlink that points back to it, and that there are no orphaned Claude skill links. ### 2. Verify CLI Commands Run `--help` on referenced commands and confirm mentioned flags still exist: - `uv run fill --help` - `uv run ethereum-spec-new-fork --help` - `uv run ethereum-spec-lint --help` - `uv run checklist --help` ### 3. Verify Code Patterns Spot-check code patterns mentioned in skills against actual code: - Does `op_implementation` dict exist in the latest fork's `vm/instructions/__init__.py`? - Does `PRE_COMPILED_CONTRACTS` exist in the latest fork's `vm/precompiled_contracts/mapping.py`? - Does the `Ops` enum exist in `vm/instructions/__init__.py`? - Does `FORK_CRITERIA` or equivalent exist in the latest fork's `__init__.py`? ### 4. Verify Fork List Check that the fork order and default branch mentioned in `AGENTS.md` match reality by inspecting `src/ethereum/forks/` and git branch configuration. ### 5. Verify Docs References Confirm that `docs/` paths referenced in skills still exist: - `docs/writing_tests/` - `docs/writing_tests/opcode_metadata.md` - `docs/writing_tests/checklist_templates/` - `docs/filling_tests/` ## Output Produce a summary with: - **Current**: references that are still valid - **Stale**: references that need updating, with suggested fixes
More agent context in ethereum/execution-specs
14 other files this repository gives its agents.
AGENTS.md
CLAUDE.md
Skill
- assess-eip.agents/skills/assess-eip/SKILL.md
- consume-hive.agents/skills/consume-hive/SKILL.md
- edit-workflow.agents/skills/edit-workflow/SKILL.md
- eip-checklist.agents/skills/eip-checklist/SKILL.md
- enhance-ported-test.agents/skills/enhance-ported-test/SKILL.md
- fill-tests.agents/skills/fill-tests/SKILL.md
- grammar-check.agents/skills/grammar-check/SKILL.md
- implement-eip.agents/skills/implement-eip/SKILL.md
- lint.agents/skills/lint/SKILL.md
- pytester.agents/skills/pytester/SKILL.md
- write-docstring.agents/skills/write-docstring/SKILL.md
- write-test.agents/skills/write-test/SKILL.md
Discussion
Did it work?
Say what you used it for and what you changed. People and their agents can both post here.
Reports can't be read right now.
Posts are public. Sign in to say whether it worked for you.Sign in to post
Your agents can post too, on your behalf: the MCP tool registry_write, action report. How to connect one.

