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 wyattjoh/skills --skill clean-storagegit clone --depth 1 https://github.com/wyattjoh/skillsWrote 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/wyattjoh/skills/clean-storage)<a href="https://agentmods.dev/skills/wyattjoh/skills/clean-storage"><img src="https://agentmods.dev/badge/skills/wyattjoh/skills/clean-storage/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/wyattjoh/skills/clean-storage"><img src="https://agentmods.dev/badge/skills/wyattjoh/skills/clean-storage.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 | $0.00088 | $0.01449 |
| Opus 5 | $0.00044 | $0.00724 |
| Sonnet 5 | $0.00018 | $0.00290 |
| Haiku 4.5 | $0.00009 | $0.00145 |
Grade C, and why
clean-storage 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 10d 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.
- The user's environment may block `rm -rf` from the agent. The script deletes through How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean storage
Finds regenerable build artifacts and caches, verifies each one is genuinely
disposable, reports them, and cleans only after the user agrees. Cargo projects are
cleaned through cargo clean; other verified artifacts are deleted directly.
Do not add context: fork. This workflow depends on AskUserQuestion for the
deletion checkpoint and on the user reading the full path list, and a forked
subagent cannot prompt the user. It must run inline.
Workflow
1. Scan (read-only, run without asking)
bun $SKILL_DIR/scripts/scan.ts --root ~/Code --root ~/Projects
Default root is the home directory. Scanning a whole home directory takes a while,
so prefer explicit --root flags when the user named a location.
Useful flags:
| Flag | Effect |
|---|---|
--root <path> |
Root to walk, repeatable. Default ~ |
--min-size <MB> |
Hide candidates below this size. Default 10 |
--max-depth <n> |
Walk depth. Default 8 |
--caches |
Add global caches to a root-scoped scan |
--json |
Machine-readable output |
--apply |
Delete the verified candidates |
Global caches (Xcode DerivedData, DeviceSupport, go-build, Playwright, and the
package manager stores) live outside any scanned root. They are included only in a
home-wide scan, or when --caches is passed. This keeps a scoped request like
"clean up my Rust project" from proposing deletions across the whole machine.
2. Report every path and action
Print the complete list of artifacts that would be cleaned, one per line, before
asking for anything. Include the scanner's action for every path: Cargo targets
show the project directory where cargo clean will run; other artifacts show
delete. The user is authorizing specific paths and actions, not a number. A
category summary alone is not enough to consent to a deletion, and neither is "the
largest few entries".
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 140 lines · 88 tokens per session scan C 74742b4bb027
clean-storage is a skill published in the GitHub repository wyattjoh/skills (2 stars, last pushed yesterday), licensed MIT. It adds 88 tokens to every session and 1,449 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…