pactkit-audit SKILL.md skillA
This file is byte-identical to the first copy the registry indexed, one of 3 indexed copies. Same content hash, so the same checks give both the same grade.
pactkit-audit from pactkit/claude-code-plugin is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add pactkit/claude-code-plugin/pactkit-audit@git:20260824.4329ca2Pins git:20260824.4329ca2 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- pactkit/claude-code-plugin
- Path
skills/pactkit-audit/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260824.4329ca2, committed Aug 24, 2026
- First version recorded
- May 6, 2026
- Size
- 2,830 bytes
- Repository stars
- 5
- License
- none declared
H1-H7 AI Readiness Assessment — harness audit scoring and hotspot analysis.
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
# PactKit Audit H1-H7 AI Coding Harness readiness assessment. Scans project structure against a 7-layer model, produces a Harness Score (0-100), and identifies code hotspots. ## When Invoked - **Done Phase 8** (Harness Audit Refresh): Auto-invoked via `pactkit audit --append`. - **Standalone**: Ad-hoc project health assessment. - **Headless / Frontend integration**: Called as `/pactkit-audit` via Claude Code headless mode. ## The 7 Layers | Layer | Name | What It Checks | |-------|------|----------------| | H1 | Prompt Engineering | CLAUDE.md, rules, agents, commands | | H2 | Context Engineering | Specs, test cases, architecture graphs | | H3 | Process Governance | Sprint board, PDCA workflow artifacts | | H4 | Tool Governance | Skills, CLI tools, MCP integration | | H5 | Safety & Guardrails | Pre-commit hooks, security rules, credential guards | | H6 | Observability | Logging, cost tracking, lessons, self-audit rules | | H7 | Evolution | Version management, changelog, CI/CD publish | ## Scoring - Each layer scores **L0-L3** (None → Basic → Structured → Advanced). - **Harness Score** = sum(all 7 levels) / 21 × 100. - **AI Ready** = min(all 7 levels) ≥ L1. ## Protocol …
Read the whole file at its exact version.
How to install
mdr add pactkit/claude-code-plugin/pactkit-audit@sha256:145fb1808b90822dThe line at the top of this page pins the label git:20260824.4329ca2, 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_jl5zdt5gq2e6jgmv)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between May 6, 2026 and Aug 24, 2026, about one every 110 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260824.4329ca2 latest | 2026-08-24 | 4329ca2 | 2,830 B | A | view · diff |
| git:20260506.b7a0e93 | 2026-05-06 | b7a0e93 | 2,816 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 (2830 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
pactkit/claude-code-plugin · 5 stars · license none declared · pushed 2026-09-17 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_jl5zdt5gq2e6jgmv GET https://markdownregistry.com/api/v1/resolve?ref=pactkit/claude-code-plugin/pactkit-audit GET https://markdownregistry.com/api/v1/blob/145fb1808b90822d7b93f83a6aa310ec3cf6893985ca031cbfd222c7fc0633a8
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.
More from pactkit/claude-code-plugin
Every file in pactkit/claude-code-plugin