artifact-hygiene skillA
artifact-hygiene is agent-read markdown (skill) from flurdy/agent-skills: Run a local-only, read-only advisory audit of publishable working-tree files and unpublished branch history with redaction-safe findings..
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
# Artifact Hygiene Run the local-only proof of concept that checks whether repository content is safe to publish. The helper is the only component allowed to read candidate content. The active model receives normalized, redacted findings and coverage—not raw candidate content. Claude Code uses the Sonnet alias for this bounded interpretation; Pi continues to route by `model-tier`. This skill is advisory and read-only. It never fetches, follows links, calls remote services, validates credentials, installs hooks, blocks CI, edits files, changes Git state, rewrites history, or creates tracker or remote state. ## Placement and enforcement The helper and skill remain together under `~/.agents/skills/` as the portable, client-neutral audit discovered by Pi, Claude Code, and Codex. The model can render its redacted advisory report; a hook cannot. Enforcement therefore stays in thin client-specific hooks that call the helper and map its result to allow or deny, such as the [Claude Code push gate in ai-tools](https://github.com/flurdy/ai-tools/tree/main/claude/artifact-hygiene-gate), without copying detectors or report logic. ## Scope The proof of concept scans: …
Read the whole file at its exact version.
How to install
mdr add flurdy/agent-skills/artifact-hygiene@v0.6.1mdr add flurdy/agent-skills/artifact-hygiene@sha256:611638dec53cf68ePin 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_v34wpkyehrb2rifb)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.6.1 latest | 2026-09-15 | 88f6036 | 14,504 B | A | view · diff |
| v0.6.0 | 2026-09-13 | 56f01ae | 14,364 B | A | view · diff |
| v0.5.2 | 2026-09-13 | bc3694e | 10,673 B | A | view · diff |
| v0.5.1 | 2026-09-12 | b46c6b8 | 10,212 B | A | view · diff |
| v0.5.0 | 2026-09-12 | 13a1558 | 9,907 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 (14504 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
flurdy/agent-skills · 9 stars · license MIT · pushed 2026-09-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_v34wpkyehrb2rifb GET https://markdownregistry.com/api/v1/resolve?ref=flurdy/agent-skills/artifact-hygiene GET https://markdownregistry.com/api/v1/blob/611638dec53cf68e3b2aa87e89da8f5eb255f40c694724693c3e4e89ba13de84
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.