CLAUDE.md@.claude claudeA
CLAUDE.md@.claude is agent-read markdown (claude) from hermes-labs-ai/rule-audit.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# CLAUDE.md — rule-audit ## What This Is Static analyzer for AI system prompts. Finds contradictions, gaps, and exploitable edge cases. Pure Python, no LLM dependency. Built at Hermes Labs Hackathon Round 8. ## Project Structure ``` rule_audit/ ├── __init__.py # audit(), audit_file(), AuditReport exports ├── parser.py # Rule extraction from raw text ├── analyzer.py # Core analysis: contradictions, gaps, priority, meta, absoluteness ├── edge_cases.py # EdgeCase generation from AnalysisResult ├── report.py # AuditReport class + Markdown renderer └── cli.py # CLI entry point (python -m rule_audit) tests/ ├── test_parser.py # Parser unit tests └── test_analyzer.py # Analyzer unit tests (includes hackathon prompt integration test) ``` ## Run Tests ```bash cd /path/to/rule-audit pip install -e ".[dev]" pytest pytest --cov=rule_audit --cov-report=term-missing ``` ## Key Design Decisions - **No LLM dependency**: All analysis is regex + heuristics. Fast, deterministic, offline. - **Rule objects are immutable dataclasses**: Parser produces them, analyzer consumes them, nothing mutates. …
Read the whole file at its exact version.
How to install
mdr add hermes-labs-ai/rule-audit/.claude/CLAUDE.md@git:20260913.d6aea49mdr add hermes-labs-ai/rule-audit/.claude/CLAUDE.md@sha256:c833a1ff5d0fe392Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_z5rin5fcqtbjyqav)
1 badge views in 30 days
Versions
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (2782 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
hermes-labs-ai/rule-audit · 3 stars · license MIT · pushed 2026-09-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_z5rin5fcqtbjyqav GET https://markdownregistry.com/api/v1/resolve?ref=hermes-labs-ai/rule-audit/.claude/CLAUDE.md GET https://markdownregistry.com/api/v1/blob/c833a1ff5d0fe392d31bf0dfac54907d1d0f1627df6dd9cfb0a9348738367cc4
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
More from hermes-labs-ai/rule-audit
Every file in hermes-labs-ai/rule-audit