clean

clean is a cursor rule for Cursor from VoTruongDanh/Skills-Agent. It costs 56 tokens per session (1,016 once invoked), scanned A, original, MIT.

Rules for finding and removing unnecessary files such as temporary files, build output, AI-created leftovers, and caches from a code project.

In plain words
What is it for?
Use it to scan for junk, remove safe-to-delete files, update .gitignore, and record what was cleaned in the project's memory file.
Why use it?
It helps reduce repository clutter while checking for uncommitted work and project-specific files that must be kept.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/votruongdanh/skills-agent/clean
Clone the repo
git clone --depth 1 https://github.com/VoTruongDanh/Skills-Agent

Made for: Cursor.

Wrote 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.

agentmods badge for clean

README.md
[![agentmods](https://agentmods.dev/badge/rules/votruongdanh/skills-agent/clean.svg)](https://agentmods.dev/rules/votruongdanh/skills-agent/clean)
Your own site
<a href="https://agentmods.dev/rules/votruongdanh/skills-agent/clean"><img src="https://agentmods.dev/badge/rules/votruongdanh/skills-agent/clean.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,016 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00056 $0.01016
Opus 5 $0.00028 $0.00508
Sonnet 5 $0.00011 $0.00203
Haiku 4.5 $0.00006 $0.00102

Measured today against content hash 76b598200b83, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 today.

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.

.cursor/rules/clean.mdc · 98 lines

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.md and apply its knowledge
  • If cleanup involves security-sensitive files → read .kiro/skills/agents/agents/security-auditor.md and apply its knowledge

Socratic Gate

Before cleaning, verify:

  1. Is the project under version control? (safety check)
  2. Are there uncommitted changes that could be lost?
  3. Any specific directories/patterns to preserve? If uncertain, ASK before proceeding.

Workflow

  1. Read Memory — Load .ai-memory.md for project context and past cleanup history.
  2. Scan the project for common junk file patterns.
  3. Identify AI-generated files that may be redundant or outdated.
  4. Present a clear list of files to be removed with sizes and reasons.
  5. Ask for confirmation before deletion.
  6. Remove approved files and report space saved.
  7. Suggest .gitignore updates if needed.
  8. 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.

Read the full file on GitHub · 98 lines

Changes

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.

  1. today Changed · +3 lines 76b598200b83
  2. 5d ago First seen · 95 lines · 56 tokens per session scan A ee89fa2f76ed

Subscribe to this mod's changes

clean is a cursor rule published in the GitHub repository VoTruongDanh/Skills-Agent (2 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 1,016 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.