Claudemd audit
A claude code skill that classifies CLAUDE.md rules by enforcement type
npx -y skills add blacksundev/claudemd-auditAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Analyse a CLAUDE.md against an instruction budget. Classifies each instruction line as deterministic-eligible (could be enforced by a hook), probabilistic-only (requires LLM judgment), vague (no actionable signal), or redundant (duplicates another rule). Outputs a budget report. Use when reviewing CLAUDE.md size, identifying rules that should move to hooks, shrinking an oversized instruction file, or planning an instruction migration. Triggers on phrases like "audit my CLAUDE.md", "is my CLAUDE.md too long", "what rules can I move to hooks", "instruction budget", or when the user is reviewing a CLAUDE.md file.
SKILL.md
2.4 KB, 424 tokens by cl100k_base, as published. Nobody here has run it
claudemd-audit
Audits a CLAUDE.md file against an instruction budget.
When to invoke
When the user asks any of:
- "audit my CLAUDE.md"
- "is my CLAUDE.md too long"
- "what rules can I move to hooks"
- "what's wasting my instruction budget"
- "classify the rules in my CLAUDE.md"
Also when refactoring or shrinking a CLAUDE.md.
How to use
The skill ships with audit.py. Run it against the user's CLAUDE.md:
python audit.py /path/to/CLAUDE.md
For JSON output:
python audit.py /path/to/CLAUDE.md --json
Then summarise the findings, focusing on:
- total instruction line count vs total file line count
- ratio of deterministic-eligible to probabilistic-only — high deterministic ratio means a lot of rules could move to hooks
- specific vague lines that can be deleted with no loss
- specific redundant lines that should be consolidated
- the three biggest deterministic-eligible candidates worth moving to hooks first
Classifications
- deterministic-eligible — rule that could be enforced by a hook (e.g. "never edit migrations", "always run lint before commit")
- probabilistic-only — requires LLM judgment (e.g. "match the existing code style")
- vague — no actionable signal (e.g. "be helpful", "write good code")
- redundant — near-duplicate of another rule
Limitations
The classification heuristics are intentionally simple. They catch common signal patterns and miss subtler ones. Misclassifications are expected. Treat the output as a starting point for human review.
If a heuristic misfires noticeably on a given input, file the case as a TODO comment in audit.py rather than fixing the heuristic in place. The goal is repeatable signal, not perfect classification.
What ships with it: 4 files
26.7 KB alongside SKILL.md, 1 of them executable