AGENTS.md@snippets/evidenceA
AGENTS.md@snippets/evidence from parcha-ai/parcha-skills is an AGENTS.md file: the standing instructions coding agents read in that repo.
mdr add parcha-ai/parcha-skills/snippets/evidence/AGENTS.md@git:20260725.7c99829Pins git:20260725.7c99829 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- AGENTS.md file
- Repository
- parcha-ai/parcha-skills
- Path
snippets/evidence/AGENTS.md- Versions recorded
- 1
- Latest version
- git:20260725.7c99829, committed Jul 25, 2026
- Size
- 1,094 bytes
- Repository stars
- 65
- License
- MIT
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
<!-- evidence:start --> ## Evidence - Claim only what you witnessed. Name the command, exit code, file, count, or log line that supports it; "should work" is not a result. - Test the capability you claim. A read does not prove write access, and a unit test does not prove a deploy (SLSA/in-toto provenance and attestation: identify what produced the result and from which inputs). - For a high-stakes claim, prefer two independent checks over repeating one check (SLSA "verified reproducible"). - Report skips, failures, and partial runs as such, with their evidence; never call them complete. - Judge the code you find on its merits. Do not label it "pre-existing" or someone else's to avoid assessing it. - Before publishing evidence, classify it. Publish only tests, schemas, aggregates, timings, synthetic or redacted summaries, non-reversible hashes, or pointers to private evidence. - Keep raw transcripts, prompts, traces, customer data, credentials, and identifying paths out of public repos. If publication status is uncertain, stop before committing. <!-- evidence:end -->
Read the whole file at its exact version.
How to install
mdr add parcha-ai/parcha-skills/snippets/evidence/AGENTS.md@sha256:cb69a4505370a2c4The line at the top of this page pins the label git:20260725.7c99829, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_lzrotvaeto54oixp)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Jul 25, 2026.
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (1094 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
parcha-ai/parcha-skills · 65 stars · license MIT · pushed 2026-10-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_lzrotvaeto54oixp GET https://markdownregistry.com/api/v1/resolve?ref=parcha-ai/parcha-skills/snippets/evidence/AGENTS.md GET https://markdownregistry.com/api/v1/blob/cb69a4505370a2c4c51f2b2d5267b5bc638fd3e11a6e528b88d8cab4e9cf932a
Your AI assistant 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.
Guides: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.