Home / flurdy / agent-skills · skills/artifact-hygiene/SKILL.md · GitHub

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(skill) from flurdy/agent-skills: Run a local-only, read-only advisory audit of publishable working-tree files and unpublished branch history with redaction-safe findings..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

Latest version
mdr add flurdy/agent-skills/artifact-hygiene@v0.6.1
Exact content
mdr add flurdy/agent-skills/artifact-hygiene@sha256:611638dec53cf68e

Pin 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_v34wpkyehrb2rifb.svg)](https://markdownregistry.com/a/art_v34wpkyehrb2rifb)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
v0.6.1 latest2026-09-15 88f6036 14,504 BA view · diff
v0.6.02026-09-13 56f01ae 14,364 BA view · diff
v0.5.22026-09-13 bc3694e 10,673 BA view · diff
v0.5.12026-09-12 b46c6b8 10,212 BA view · diff
v0.5.02026-09-12 13a1558 9,907 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • 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

GitHub

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.

More from flurdy/agent-skills

AGENTS.md agents
flurdy/agent-skills · AGENTS.md
git:20260630.7b39634 · audit B · 9 stars
CLAUDE.md claude
flurdy/agent-skills · CLAUDE.md
git:20260907.23d6b60 · audit A · 9 stars
architect skill
flurdy/agent-skills · skills/architect/SKILL.md · Architecture and implementation planning gate for complex or high-blast-radius work. Produces evidence-backed…
v2.0.1 · audit A · 9 stars
backlog-groom skill
flurdy/agent-skills · skills/backlog-groom/SKILL.md · Per-bead backlog quality audit — flags thin descriptions, label drift, stale YAGNIs, mis-prioritised nice-to-haves…
v0.1.2 · audit A · 9 stars
beads-check-dolt-migration skill
flurdy/agent-skills · skills/beads-check-dolt-migration/SKILL.md · Detect whether a beads repository needs classic-to-Dolt migration or an in-place Dolt schema upgrade.
v1.1.0 · audit A · 9 stars
beads-migrate-to-dolt skill
flurdy/agent-skills · skills/beads-migrate-to-dolt/SKILL.md · Safely migrate classic Beads data or upgrade a Dolt schema, preserving backups and remote history. Repository aftercare…
v2.0.1 · audit A · 9 stars
beads-setup skill
flurdy/agent-skills · skills/beads-setup/SKILL.md · Preview and separately confirm a fresh repository Beads store with a dedicated private GitHub Dolt remote. Refuses…
v0.1.0 · audit A · 9 stars
beads skill
flurdy/agent-skills · skills/beads/SKILL.md · Shared Beads workflow baseline. Use whenever an agent uses `bd`, manages durable tasks, blockers, or handoffs, resolves…
v0.6.0 · audit A · 9 stars
browser-screenshot skill
flurdy/agent-skills · skills/browser-screenshot/SKILL.md · Take a screenshot of the running web application for visual verification of UI/CSS changes. Use when iterating on…
v1.1.0 · audit A · 9 stars
circleci-status skill
flurdy/agent-skills · skills/circleci-status/SKILL.md · Check CircleCI build status and failed job logs for the current GitHub repository. Use when asked whether CircleCI is…
v1.0.1 · audit A · 9 stars
clean-code skill
flurdy/agent-skills · skills/clean-code/SKILL.md · Format, lint, and fix all warnings across the entire codebase — including test files and pre-existing issues.
v1.1.0 · audit A · 9 stars
complete-task skill
flurdy/agent-skills · skills/complete-task/SKILL.md · Complete an in-progress task by running clean-code, staging, and committing. Close the bead on trunk, leave it open for…
v2.0.0 · audit A · 9 stars

Every file in flurdy/agent-skills

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