Borrowing it
Nothing to install: this file belongs to VoTruongDanh/Skills-Agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/VoTruongDanh/Skills-Agent/main/.agents/skills/clean/SKILL.mdgit clone --depth 1 https://github.com/VoTruongDanh/Skills-AgentWrote 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/votruongdanh/skills-agent/clean)<a href="https://agentmods.dev/skills/votruongdanh/skills-agent/clean"><img src="https://agentmods.dev/badge/skills/votruongdanh/skills-agent/clean/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/votruongdanh/skills-agent/clean"><img src="https://agentmods.dev/badge/skills/votruongdanh/skills-agent/clean.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 | $0.00058 | $0.01020 |
| Opus 5 | $0.00029 | $0.00510 |
| Sonnet 5 | $0.00012 | $0.00204 |
| Haiku 4.5 | $0.00006 | $0.00102 |
Grade A, and why
clean scanned grade A with 0 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 5d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Protocol
START: Read .ai-memory.md from project root. Check for known junk patterns, previous cleanup history, and project-specific ignore rules.
END: Update .ai-memory.md using Memory Compaction Rules with: what was cleaned, space recovered, ignore rules added, and recurring patterns.
Goal
Identify and remove unnecessary files generated by AI, build processes, or development tools without affecting the working codebase.
Agent Routing
- If cleanup involves build artifacts/CI → read
.kiro/skills/agents/agents/devops-engineer.mdand apply its knowledge - If cleanup involves security-sensitive files → read
.kiro/skills/agents/agents/security-auditor.mdand apply its knowledge
Socratic Gate
Before cleaning, verify:
- Is the project under version control? (safety check)
- Are there uncommitted changes that could be lost?
- Any specific directories/patterns to preserve? If uncertain, ASK before proceeding.
Workflow
- Read Memory — Load
.ai-memory.mdfor project context and past cleanup history. - Scan the project for common junk file patterns.
- Identify AI-generated files that may be redundant or outdated.
- Present a clear list of files to be removed with sizes and reasons.
- Ask for confirmation before deletion.
- Remove approved files and report space saved.
- Suggest .gitignore updates if needed.
- Update Memory — Save cleanup results and new patterns to
.ai-memory.md.
Common Junk Patterns
- Temporary files:
*.tmp,*.temp,*.bak,*.swp,*~ - Log files:
*.log,*.log.*,debug.log,error.log - Cache directories:
.cache/,__pycache__/,.pytest_cache/,.mypy_cache/ - Build artifacts:
dist/,build/,*.pyc,*.pyo,*.class,*.o - Node modules:
node_modules/(if not needed) - IDE files:
.vscode/,.idea/(if not in .gitignore) - OS files:
.DS_Store,Thumbs.db,desktop.ini - AI artifacts: Duplicate markdown files, unused generated code, test outputs
Safety Rules
- Never delete files in version control (check git status first).
- Never delete configuration files (.env, config.json, etc.) unless explicitly requested.
- Never delete source code without explicit confirmation.
- Always show what will be deleted before proceeding.
- Preserve .gitignore and other dot files unless they're clearly junk.
- Ask before removing entire directories.
- NEVER delete
.ai-memory.md— it is a persistent project memory file.
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.
- 5d ago Changed · +3 lines 3a3ffab274ad
- 10d ago First seen · 95 lines · 58 tokens per session scan A 52e7a5402b11
clean is a skill published in the GitHub repository VoTruongDanh/Skills-Agent (2 stars, last pushed 6d ago), licensed MIT. It adds 58 tokens to every session and 1,020 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. 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…