AGENTS.md@evalA

AGENTS.md@eval from ccoalm/ccl-skills is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned

mdr add ccoalm/ccl-skills/eval/AGENTS.md@git:20261004.932325c

Pins git:20261004.932325c in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 14 of 14 checks passed
Kind: AGENTS.md file
Repository: ccoalm/ccl-skills
Path: eval/AGENTS.md
Versions recorded: 2
Latest version: git:20261004.932325c, committed Oct 4, 2026
First version recorded: Aug 12, 2026
Size: 5,806 bytes
Repository stars: 6
License: Apache-2.0

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

# eval Agent Contract

Measurement surfaces for agent behavior: fixtures consumed by the behavior-eval
harness, plus standing audits that read real host transcripts. Nothing here
enforces repository changes. These produce machine-readable advisory evidence
and next actions that an agent learning loop can consume; human reading or
intervention is optional.

Rules:

- **Advisory by construction.** Nothing in this directory may become a merge
  gate. An automated eval controller may continue, repair, reject or roll back
  an isolated candidate, but it cannot authorize merge, push, release or deploy.
  These tools classify free-text briefs and prompts with heuristics, and
  heuristics over open semantics do not converge reliably.
  Standing measurement tools exit non-zero only when the scan itself broke,
  never because the measured population looked bad. The causal synthetic smoke
  is the explicit exception: contract-complete but provider-unevaluated exits
  `3` so automation cannot promote it as a green gate.
- **`frozen_at_sha` is an ancestry/batch marker, not a "validated at" stamp.**
  Use `root` for fixtures that belong to the initial public snapshot. An
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add ccoalm/ccl-skills/eval/AGENTS.md@sha256:2301c274b669d023

The line at the top of this page pins the label git:20261004.932325c, 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.

Badge

[![mdr](https://markdownregistry.com/badge/art_a7c24hnp23ys26a4.svg)](https://markdownregistry.com/a/art_a7c24hnp23ys26a4)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Aug 12, 2026 and Oct 4, 2026, about one every 54 days.

version	committed	commit	size	audit
git:20261004.932325c latest	2026-10-04	932325c	5,806 B	A	view · diff
git:20260812.206facb	2026-08-12	206facb	5,346 B	A	view

Audit of the latest version

A 14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Size between 200 bytes and 200 KB (5806 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

GitHub

ccoalm/ccl-skills · 6 stars · license Apache-2.0 · pushed 2026-10-09 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_a7c24hnp23ys26a4
GET https://markdownregistry.com/api/v1/resolve?ref=ccoalm/ccl-skills/eval/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/2301c274b669d023d0f73e125c1d249fdb2b6447202d03c35001bca56caae584

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.