AGENTS.md@specs/156-stop-recheck-escape-terms/evidenceA

AGENTS.md@specs/156-stop-recheck-escape-terms/evidence 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/specs/156-stop-recheck-escape-terms/evidence/AGENTS.md@git:20261003.7faeb8b

Pins git:20261003.7faeb8b in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
ccoalm/ccl-skills
Path
specs/156-stop-recheck-escape-terms/evidence/AGENTS.md
Versions recorded
1
Latest version
git:20261003.7faeb8b, committed Oct 3, 2026
Size
1,223 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

# evidence Agent Contract

Frozen measurement artifacts for round 156: the validation record and the
replay runner that produced its firing-point numbers.

Rules:

- **Frozen after landing.** Do not edit, regrade or regenerate these files to
  improve a later conclusion. Overturn a reading with a new measurement in a new
  round's evidence directory and cite it from that round's register row.
- **`recheck_replay.py` is an evidence tool, not a repository gate.** It calls a
  live model, is non-deterministic, and must never be wired into `make test` or
  any blocking check. A run proves only what one model produced on one prompt.
- **Read the runner before citing a number.** It reads `DECISION_RECHECK` from
  each checkout given on the command line, disables tools and hooks, runs in an
  empty directory, and counts a run as `none` when neither verdict line appears;
  a `none` is a grading miss, never a pass for either arm.
- **No credentials, host paths or third-party content.** Scenario text is
  synthetic and uses a neutral domain.

Validation:

- `python3 -m py_compile specs/156-stop-recheck-escape-terms/evidence/recheck_replay.py`
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add ccoalm/ccl-skills/specs/156-stop-recheck-escape-terms/evidence/AGENTS.md@sha256:ac500049dcc27b5e

The line at the top of this page pins the label git:20261003.7faeb8b, 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 badge

[![mdr](https://markdownregistry.com/badge/art_ft2hob25zvkmcfhr.svg)](https://markdownregistry.com/a/art_ft2hob25zvkmcfhr)

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

Versions

The registry has recorded 1 version of this file, committed on Oct 3, 2026.

versioncommittedcommitsizeaudit
git:20261003.7faeb8b latest2026-10-03 7faeb8b 1,223 BA 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 (1223 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 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ft2hob25zvkmcfhr
GET https://markdownregistry.com/api/v1/resolve?ref=ccoalm/ccl-skills/specs/156-stop-recheck-escape-terms/evidence/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/ac500049dcc27b5edc0e133e8225b6315071a9ff515c867cc77c485fe5c55341

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.

More from ccoalm/ccl-skills

AGENTS.md AGENTS.md file
ccoalm/ccl-skills · AGENTS.md
git:20261003.5ac538d · audit A · 6 stars
AGENTS.md@eval AGENTS.md file
ccoalm/ccl-skills · eval/AGENTS.md
git:20261004.932325c · audit A · 6 stars
AGENTS.md@eval/evidence/placement-face-2026-08-28 AGENTS.md file
ccoalm/ccl-skills · eval/evidence/placement-face-2026-08-28/AGENTS.md
git:20260829.e0c8729 · audit A · 6 stars
AGENTS.md@eval/evidence/placement-face-2026-08-28/arms AGENTS.md file
ccoalm/ccl-skills · eval/evidence/placement-face-2026-08-28/arms/AGENTS.md
git:20260829.e0c8729 · audit A · 6 stars
AGENTS.md@eval/evidence/routing-bank-runner-round-2026-08-14 AGENTS.md file
ccoalm/ccl-skills · eval/evidence/routing-bank-runner-round-2026-08-14/AGENTS.md
git:20260815.594239a · audit A · 6 stars
AGENTS.md@eval/evidence/routing-new-tighten-vs-owner-2026-08-15 AGENTS.md file
ccoalm/ccl-skills · eval/evidence/routing-new-tighten-vs-owner-2026-08-15/AGENTS.md
git:20260815.14dfddf · audit A · 6 stars
AGENTS.md@eval/evidence/routing-p3-log-plus-test-2026-08-14 AGENTS.md file
ccoalm/ccl-skills · eval/evidence/routing-p3-log-plus-test-2026-08-14/AGENTS.md
git:20260814.f4c1164 · audit A · 6 stars
AGENTS.md@eval/evidence/zh-doc-borrow-2026-08-27 AGENTS.md file
ccoalm/ccl-skills · eval/evidence/zh-doc-borrow-2026-08-27/AGENTS.md
git:20260828.6e3ddd8 · audit A · 6 stars
AGENTS.md@eval/evidence/zh-doc-borrow-2026-08-27/arms AGENTS.md file
ccoalm/ccl-skills · eval/evidence/zh-doc-borrow-2026-08-27/arms/AGENTS.md
git:20260828.6e3ddd8 · audit A · 6 stars
AGENTS.md@eval/skill-effectiveness AGENTS.md file
ccoalm/ccl-skills · eval/skill-effectiveness/AGENTS.md
git:20260812.206facb · audit A · 6 stars
AGENTS.md@hooks AGENTS.md file
ccoalm/ccl-skills · hooks/AGENTS.md
git:20260812.206facb · audit A · 6 stars
AGENTS.md@packages AGENTS.md file
ccoalm/ccl-skills · packages/AGENTS.md
git:20260815.1f122f5 · audit A · 6 stars

Every file in ccoalm/ccl-skills

Browse by kind, by grade A, or by owner.