Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add OpenCoven/coven --skill cleanup-unused-filesgit clone --depth 1 https://github.com/OpenCoven/covenWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/opencoven/coven/cleanup-unused-files)<a href="https://agentmods.dev/skills/opencoven/coven/cleanup-unused-files"><img src="https://agentmods.dev/badge/skills/opencoven/coven/cleanup-unused-files/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/opencoven/coven/cleanup-unused-files"><img src="https://agentmods.dev/badge/skills/opencoven/coven/cleanup-unused-files.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00078 | $0.01070 |
| Opus 5 | $0.00039 | $0.00535 |
| Sonnet 5 | $0.00016 | $0.00214 |
| Haiku 4.5 | $0.00008 | $0.00107 |
Grade C, and why
cleanup-unused-files scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ~/.codex How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cleanup Unused Files
Optimize for reclaiming disk space fast.
Prefer obvious, reproducible junk over careful semantic analysis.
Default stance
- Target caches, build output, temp folders, and local tool state first.
- Prefer exact paths over broad globs.
- Be explicit about blast radius.
- Treat anything under source directories as higher risk unless it is known build output.
- If the cleanup touches machine-wide tool state or login/session data, call that out clearly before running it.
Primary targets
Common high-yield cleanup targets include:
- project build output like
target/,dist/,.next/,coverage/,.turbo/ - package-manager caches
- SDK/tool caches
- app caches under
~/Library/Caches - stale temp folders
- old logs, dumps, and exports
- backup/swap/temp files
Examples of the user's preferred cleanup style:
rm -rf ~/.codex
rm -rf ~/Library/Caches
rm -rf ~/.rustup
rm -rf ~/.bun
rm -rf ~/.npm
rm -rf ~/.lmstudio
rm -rf src-tauri/target
Also valid tool-native cleanup commands when they fit better:
cargo clean --manifest-path src-tauri/Cargo.toml
npm cache clean --force
brew cleanup --prune=all
rustup toolchain list | grep -v default | xargs -I{} rustup toolchain uninstall {}
Workflow
1) Identify cleanup scope
Determine whether the user wants:
- project-only cleanup
- home-directory cache cleanup
- machine-wide developer reset
- maximum disk recovery regardless of re-download cost
If the request is vague, default to an audit of likely large cache directories first.
2) Prefer highest-yield directories
When disk recovery is the goal, focus on these before hunting tiny files:
~/Library/Caches~/.npm~/.bun~/.rustup~/.cargo~/.codex~/.lmstudio- repo-local
target/,dist/,.next/,coverage/ - large temp/export folders under the workspace or home directory
3) Distinguish safe nukes from state resets
Usually safe and reproducible:
- build output
- download caches
- derived data
- package caches
- logs
- temp files
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 173 lines · 78 tokens per session scan C 1809cdbba4da
cleanup-unused-files is a skill published in the GitHub repository OpenCoven/coven (47 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 1,070 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
ppt-review
Read this skill only after current officereview structural output and relevant rendered images exist. Do not use source code, a tool success flag, or the first-slide preview as a substitute for deck evidence.
package-installer
Install third-party open-source projects (a GitHub URL or a local git directory the user provides) as external packages. The project is cloned verbatim into the per-user packages directory — never edit, normalize, or reorganize its files.
quality-hooks
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.
cog-knowledge-consolidation
Build structured knowledge frameworks from scattered vault notes with source attribution.