Home / ccoalm / ccl-skills · GitHub

AGENTS.md@eval/skill-effectivenessA

AGENTS.md@eval/skill-effectiveness 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/skill-effectiveness/AGENTS.md@git:20260812.206facb

Pins git:20260812.206facb 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/skill-effectiveness/AGENTS.md
Versions recorded: 1
Latest version: git:20260812.206facb, committed Aug 12, 2026
Size: 15,626 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

# skill-effectiveness Agent Contract

This directory implements the causal-evaluation foundation: frozen arms and
gates, private trial artifacts, blinded comparisons, isolation checks, and the
explicit Codex capability probe. It inherits `../AGENTS.md`; only local deltas
follow.

## Boundaries

- Treat `arms/`, fixtures, schemas, task sets, and `pilot-gates.json` as
  pre-registered protocol inputs. Freeze them before outcomes are visible; do
  not weaken missing evidence into a passing status.
- Persist trial output only under an explicit private root outside the source
  checkout. Preserve the 0700/0600 and separate read/write-root contracts; an
  out-of-scope access or cross-trial canary leak contaminates the trial.
- `provider-probe` is the only live capability adapter here. It sends only an
  isolation canary, uses an exact executable/model and independent read-only
  ephemeral sessions, audits the JSON event stream, and rejects tool activity.
  A completed no-recall observation must remain
  `isolation_outcome=unresolved_isolation_threat` and
  `causal_core_unavailable`; never report it as isolated or passing. Changing
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add ccoalm/ccl-skills/eval/skill-effectiveness/AGENTS.md@sha256:ca0361dc5206ffd6

The line at the top of this page pins the label git:20260812.206facb, 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_z4bmtpm3b7ekjmxa.svg)](https://markdownregistry.com/a/art_z4bmtpm3b7ekjmxa)

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

Versions

The registry has recorded 1 version of this file, committed on Aug 12, 2026.

version	committed	commit	size	audit
git:20260812.206facb latest	2026-08-12	206facb	15,626 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 (15626 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_z4bmtpm3b7ekjmxa
GET https://markdownregistry.com/api/v1/resolve?ref=ccoalm/ccl-skills/eval/skill-effectiveness/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/ca0361dc5206ffd6aac723c7c006b8b548cf1decb10ea9b7a855a9486fb57cd7

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.