capability-audit skillA
capability-audit is agent-read markdown (skill) from rtur2003/claude-code-promts-skills: Use when evaluating, comparing, installing, or recommending a Claude Code plugin, Agent Skill, MCP server, agent toolkit, or GitHub-hosted AI extension, especially when popularity is weak evidence or the candidate requests shell, network, filesystem, or credential access..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Capability Audit
## Purpose
Collect comparable evidence about GitHub-hosted agent capabilities before installation. The bundled script uses the GitHub API without cloning a repository. It reports maintenance metadata, license, distribution files, executable surfaces, test signals, and high-risk text patterns. It does not install, authenticate, or declare a project safe.
## Workflow
1. Convert each candidate to `owner/repo` or a GitHub repository URL.
2. Run the script for all credible candidates, not only the popularity leader:
```bash
python ${CLAUDE_SKILL_DIR}/scripts/audit.py owner/repo another/repo
```
3. Read the exact pinned commit or package that would be installed. The script inspects the current default branch only; say so explicitly.
4. Open every discovered plugin manifest, `SKILL.md` frontmatter, hook, MCP configuration, and executable script before recommending installation.
5. Compare candidates using task fit, blast radius, runtime proof, maintenance, interoperability, rollback, documentation, and adoption. Cap adoption at 5% of the decision.
…Read the whole file at its exact version.
How to install
mdr add rtur2003/claude-code-promts-skills/capability-audit@git:20260922.3340a16mdr add rtur2003/claude-code-promts-skills/capability-audit@sha256:44793501fbe158c0Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_iphz3xtkdx2zxqwt)
1 badge views in 30 days
Versions
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 (2761 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
rtur2003/claude-code-promts-skills · 53 stars · license MIT · pushed 2026-09-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_iphz3xtkdx2zxqwt GET https://markdownregistry.com/api/v1/resolve?ref=rtur2003/claude-code-promts-skills/capability-audit GET https://markdownregistry.com/api/v1/blob/44793501fbe158c0e81212da426e70d44e0c1f15dea3d9192b3842d7847156bc
Your agent 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.
More from rtur2003/claude-code-promts-skills
Every file in rtur2003/claude-code-promts-skills