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 katalalab/katala-os --skill skill-cleanergit clone --depth 1 https://github.com/katalalab/katala-osWrote 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/katalalab/katala-os/skill-cleaner)<a href="https://agentmods.dev/skills/katalalab/katala-os/skill-cleaner"><img src="https://agentmods.dev/badge/skills/katalalab/katala-os/skill-cleaner/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/katalalab/katala-os/skill-cleaner"><img src="https://agentmods.dev/badge/skills/katalalab/katala-os/skill-cleaner.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 | $0.00054 | $0.00534 |
| Opus 5 | $0.00027 | $0.00267 |
| Sonnet 5 | $0.00011 | $0.00107 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade B, and why
skill-cleaner scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Enumerates other installed skillslowAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls ~/.claude/skills/ | wc -l Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
find ~/.claude/skills/ -maxdepth 1 -name "*.bak-*" -type d -mtime +7 -exec rm -rf {} + Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
What it actually says
skill-cleaner — ~/.claude/skills/ maintenance
Audits the skill directory and reports what to clean. Never deletes without operator confirmation.
When to use
- "スキルディレクトリを整理して"
- "壊れたスキルリンクがある、確認して"
- "skills の .bak ディレクトリが溜まってる"
- After skill migrations or repo moves
Do not use for:
- Deleting active, working skills
- Modifying skill content (use the skill's own update process)
Audit steps
# 1. Count total skills and symlinks
ls ~/.claude/skills/ | wc -l
# 2. Detect broken symlinks
find ~/.claude/skills/ -maxdepth 1 -type l | while read l; do
[ ! -e "$l" ] && echo "BROKEN: $l -> $(readlink $l)"
done
# 3. List .bak directories (stale backups)
ls -d ~/.claude/skills/*.bak-* 2>/dev/null | wc -l
ls -d ~/.claude/skills/*.bak-* 2>/dev/null | head -10
# 4. Detect duplicate skills (symlinks pointing to same target)
find ~/.claude/skills/ -maxdepth 1 -type l -exec readlink {} \; | sort | uniq -d
Cleanup (operator confirms each step)
# Remove broken symlinks
# !! Requires operator explicit confirmation for each batch !!
find ~/.claude/skills/ -maxdepth 1 -type l ! -follow | xargs rm
# Remove stale .bak directories (>7 days)
find ~/.claude/skills/ -maxdepth 1 -name "*.bak-*" -type d -mtime +7 -exec rm -rf {} +
Hard-rule reminders
- Always audit first (read-only pass), then report findings before any deletion.
- Auto mode blocks self-modification of
~/.claude/skills/— the operator must run cleanup commands directly or add explicit Bash permissions. - Deletions are irreversible for non-git directories. Confirm targets before proceeding.
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.
- 9d ago First seen · 56 lines · 54 tokens per session scan B 49771d9ebc9b
skill-cleaner is a skill published in the GitHub repository katalalab/katala-os (2 stars, last pushed 10d ago), licensed MIT. It adds 54 tokens to every session and 534 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (enumerates other installed skills, 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…