codebase-pruner SKILL.md skillA
codebase-pruner from afu-it/safe-code is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add afu-it/safe-code/codebase-pruner@git:20261004.9138475Pins git:20261004.9138475 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- afu-it/safe-code
- Path
skills/codebase-pruner/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261004.9138475, committed Oct 4, 2026
- First version recorded
- May 9, 2026
- Size
- 12,122 bytes
- Repository stars
- 4
- License
- MIT
Scan an entire codebase to detect and safely remove dead code such as unused functions, orphaned modules, unreferenced exports, stale configs, dead routes, and leftover workflow artifacts. Use when asked to clean up dead code, remove unused code, prune stale files, find orphaned modules, audit codebase bloat, or delete code left behind after a workflow or architecture change.
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
# Codebase Pruner Audit a repo for dead code, estimate deletion risk, and remove only high-confidence candidates in small verified slices. Reason from real entrypoints, config references, and runtime wiring instead of guessing from filenames. ## Core Rules - Treat dead code as code with no live path from any entrypoint, config reference, or runtime hook. - Map references before deleting anything. One missed reference invalidates the deletion. - Prefer `Audit` first. Use `Execute` only after the dead-code inventory is clear enough to act safely. - If a candidate has dynamic dispatch risk, reflection risk, or external integration risk, flag it instead of deleting it automatically. - Never delete generated files. Update the generator or generated output flow instead. - Never mix pruning with unrelated feature work or refactors. - Prefer narrow, reversible slices with verification after each slice. - Use the codegraph index when available. Treat graph output as evidence, not permission to delete. ## Graph-Aware Audit Path Use this path before manual scanning when a codegraph index is available: 1. `codegraph sync` (or `$build-graph` when no index exists) …
Read the whole file at its exact version.
How to install
claude plugin marketplace add https://markdownregistry.com/mp/a/art_tlplxi54xrdh6ube/45909992280a8768c00fb63e4330727a55473c9e88e0b9ed97dd20cf67b2a348.json
Then /plugin install codebase-pruner@markdownregistry-tlplxi54xrdh6ube in Claude Code. It installs git:20261004.9138475, the one graded A here, pinned to the commit it was graded at, and leaves it there.
mdr add afu-it/safe-code/codebase-pruner@sha256:45909992280a8768The line at the top of this page pins the label git:20261004.9138475, 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_tlplxi54xrdh6ube)
1 badge image fetches in 30 days. What the badge shows.
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it: what changed in afu-it/safe-code/codebase-pruner since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.
Got a copy of codebase-pruner from somewhere else? Ask it: where did my codebase-pruner come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.
Versions
The registry has recorded 5 versions of this file, between May 9, 2026 and Oct 4, 2026, about one every 37 days.
Watch this file (sign in, one email per new version)
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261004.9138475 latest | 2026-10-04 | 9138475 | 12,122 B | A | view · diff |
| git:20260715.9c4747a | 2026-07-15 | 9c4747a | 11,211 B | A | view · diff |
| git:20260609.41300db | 2026-06-09 | 41300db | 10,934 B | A | view · diff |
| git:20260601.75250b6 | 2026-06-01 | 75250b6 | 10,907 B | A | view · diff |
| git:20260509.8cf57a9 | 2026-05-09 | 8cf57a9 | 11,085 B | A | view |
Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.
It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.
Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.
mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml
It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.
Installed this file, say at .claude/skills/codebase-pruner/SKILL.md? Drop it here to learn which saved version you have and what changed since. Your browser works out its SHA-256 fingerprint and sends only that; the file itself never leaves your computer.
Or paste its contents
Your agent can run this same check on the agent markdown files you have installed, up to 50 in one ask. Add the registry once:
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it to check the files you have installed. No key and no account.
From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies
In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies
No sha256sum on your machine? shasum -a 256 prints the same lines.
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 (12122 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
afu-it/safe-code · 4 stars · license MIT · pushed 2026-11-17 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_tlplxi54xrdh6ube GET https://markdownregistry.com/api/v1/resolve?ref=afu-it/safe-code/codebase-pruner GET https://markdownregistry.com/api/v1/blob/45909992280a8768c00fb63e4330727a55473c9e88e0b9ed97dd20cf67b2a348
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.