skill-comply SKILL.md skillA
skill-comply from shimo4228/claude-harness is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add shimo4228/claude-harness/skill-comply@git:20261010.b5821aaPins git:20261010.b5821aa in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- shimo4228/claude-harness
- Path
skills/skill-comply/SKILL.md- Versions recorded
- 8
- Latest version
- git:20261010.b5821aa, committed Oct 10, 2026
- First version recorded
- Aug 17, 2026
- Size
- 9,293 bytes
- Repository stars
- 3
- License
- MIT
Measure whether a skill, rule or agent definition is actually followed. Use when a rule's or skill's real adherence is in question, or right after adding one.
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-comply: Automated Compliance Measurement Measures whether coding agents actually follow skills, rules, or agent definitions by: 1. Auto-generating expected behavioral sequences (specs) from any .md file 2. Auto-generating scenarios with decreasing prompt strictness (supportive → neutral → competing), to show whether the target is followed even when the prompt does not support it 3. Running `claude -p` and capturing tool call traces via stream-json 4. Classifying tool calls against spec steps using LLM (not regex) 5. Checking temporal ordering deterministically 6. Generating self-contained reports with spec, prompts, and timelines It measures runtime adherence only. A static quality audit is skill `skill-stocktake` / `rules-stocktake`, a reference-integrity check is skill `skill-health`, and a with/without ablation of a skill's effect is skill `skill-creator` §5. ## Supported Targets - **Skills** (`skills/*/SKILL.md`): Workflow skills like search-first - **Rules** (`rules/common/*.md`): Mandatory rules like testing.md, security.md, debugging.md - **Agent definitions** (`agents/*.md`): accepted as a target, but invocation is **not observable** today — every child …
Read the whole file at its exact version.
How to install
mdr add shimo4228/claude-harness/skill-comply@sha256:b236eb90f9bc4ac4The line at the top of this page pins the label git:20261010.b5821aa, 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_rndvrb5ooh6pi6rb)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 8 versions of this file, between Aug 17, 2026 and Oct 10, 2026, about one every 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261010.b5821aa latest | 2026-10-10 | b5821aa | 9,293 B | A | view · diff |
| git:20261008.b63e5f1 | 2026-10-08 | b63e5f1 | 9,037 B | A | view · diff |
| git:20261007.d62d71a | 2026-10-07 | d62d71a | 9,296 B | A | view · diff |
| git:20260926.538565e | 2026-09-26 | 538565e | 13,496 B | A | view · diff |
| git:20260925.a3765d2 | 2026-09-25 | a3765d2 | 14,359 B | A | view · diff |
| git:20260919.f95d231 | 2026-09-19 | f95d231 | 14,372 B | A | view · diff |
| git:20260902.9b5c240 | 2026-09-02 | 9b5c240 | 14,584 B | A | view · diff |
| git:20260817.c3233a2 | 2026-08-17 | c3233a2 | 15,031 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (9293 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
shimo4228/claude-harness · 3 stars · license MIT · pushed 2026-10-18 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_rndvrb5ooh6pi6rb GET https://markdownregistry.com/api/v1/resolve?ref=shimo4228/claude-harness/skill-comply GET https://markdownregistry.com/api/v1/blob/b236eb90f9bc4ac40267e71e8949e081693b1f12ed941cdda640b889a21ef4d6
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: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.