llms.txt llmstxtA
llms.txt is agent-read markdown (llmstxt) 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
# Owner: Hermes Labs - https://hermes-labs.ai # rule-audit > Static analyzer for LLM system prompts. Parses a prompt into normative rules and reports logical contradictions, coverage gaps, priority ambiguities, meta-rule paradoxes, and absolute-rule edge cases. Pure Python, zero LLM dependency, deterministic. Part of the Hermes Labs reliability stack. rule-audit is, roughly, a linter for AI system prompts. Given a raw prompt string, it extracts normative rules, classifies their modality (MUST / MUST_NOT / SHOULD / MAY), scores absoluteness, and finds pairs that conflict. For each finding it renders a concrete example scenario with a suggested attack vector and mitigation — illustrative starting points for testing, not verified exploits. No API keys, no network, no LLM calls. Install: `pip install rule-audit`. Python 3.9+. MIT licensed. ## Docs - [README](README.md): Install, quickstart, CLI and Python API usage, architecture overview. - [SPEC](SPEC.md): Full technical spec — parsing algorithm, contradiction detection methodology, severity calibration, data model, performance characteristics, known limitations. …
Read the whole file at its exact version.
How to install
mdr add hermes-labs-ai/rule-audit/llms.txt@git:20260923.3cc5946mdr add hermes-labs-ai/rule-audit/llms.txt@sha256:fe4d68fcad6d998bPin 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_dn2nazlzdnyclftg)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260923.3cc5946 latest | 2026-09-23 | 3cc5946 | 3,408 B | A | view · diff |
| git:20260921.36432d5 | 2026-09-21 | 36432d5 | 3,505 B | A | view · diff |
| git:20260913.d6aea49 | 2026-09-13 | d6aea49 | 3,431 B | A | view · diff |
| git:20260907.eebbd82 | 2026-09-07 | eebbd82 | 3,423 B | A | view · diff |
| git:20260606.7277088 | 2026-06-06 | 7277088 | 3,418 B | A | view · diff |
| git:20260531.1058560 | 2026-05-31 | 1058560 | 3,125 B | A | view · diff |
| git:20260430.5884160 | 2026-04-30 | 5884160 | 7,036 B | A | view |
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (3408 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_dn2nazlzdnyclftg GET https://markdownregistry.com/api/v1/resolve?ref=hermes-labs-ai/rule-audit/llms.txt GET https://markdownregistry.com/api/v1/blob/fe4d68fcad6d998bac08b22e19a333536c86053c7533b69a33c34384a8a20c25
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