caro.prune SKILL.md skillA
caro.prune from wildcard/caro is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add wildcard/caro/caro.prune@git:20260517.2609016Pins git:20260517.2609016 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- wildcard/caro
- Path
.claude/skills/caro.prune/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260517.2609016, committed May 17, 2026
- Size
- 8,823 bytes
- Repository stars
- 40
- License
- AGPL-3.0
Safely reclaim disk space in the caro project. Cleans Rust build cache, stale git worktrees (both .claude/worktrees/ and .worktrees/), empty stubs, and node_modules using a tiered audit that preserves any worktree with uncommitted changes, missing remotes, or a lock file. Use when du shows the project > 30 GB or disk free is low.
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
# caro.prune Skill **Purpose:** Reclaim disk space without losing any work. Caro's worktree-heavy workflow + Rust build caches grow the repo to 100 GB+ within weeks of active development. This skill turns that back into ~5–15 GB while preserving every worktree that has dirty files, an unpushed branch, or a `locked` flag. **Codified from:** the 2026-05-16 cleanup pass that reduced the project from **101 GB → 18 GB** in ~5 min by removing 53 stale worktrees + the entire `target/` cache. --- ## When to Use - `du -sh .` shows the project > 30 GB - `df -h .` shows < 100 GB free on the volume - Before a long session where the repo will be growing (releases, big refactors) - After finishing a multi-week sprint with many merged PRs (their worktrees linger) - Periodic hygiene — once a month is a good cadence ## When NOT to Use - Mid-build (`cargo build` running) — Tier 1 will wipe the cache out from under it - Right before a benchmark run — you want the warm cache - If `git worktree list` shows < 10 worktrees — not enough fat to be worth the audit - On a worktree branch that isn't `main` and isn't your own — leave the parent alone --- ## Safety Invariants …
Read the whole file at its exact version.
How to install
mdr add wildcard/caro/caro.prune@sha256:2218214aa743bdc4The line at the top of this page pins the label git:20260517.2609016, 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_me7n4cxvgyfmb63n)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on May 17, 2026.
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 (8823 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
wildcard/caro · 40 stars · license AGPL-3.0 · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_me7n4cxvgyfmb63n GET https://markdownregistry.com/api/v1/resolve?ref=wildcard/caro/caro.prune GET https://markdownregistry.com/api/v1/blob/2218214aa743bdc4c5a4af1837687f813e75d009a0934193f6fa2ff9a4c22be5
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.