Install
$ agentstack add skill-manastalukdar-ai-devstudio-cleanproject ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ● Environment & secrets Used
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Clean Project
I'll help clean up development artifacts while preserving your working code.
Strategic Thinking Process
Before cleaning, I need to carefully consider:
- Artifact Identification
- What patterns indicate temporary/debug files?
- Which files might look temporary but are actually important?
- Are there project-specific conventions for temp files?
- What about generated files that should be kept?
- Safety Analysis
- Which deletions are definitely safe?
- Which require more careful inspection?
- Are there active processes using these files?
- Could removing these break the development environment?
- Common Pitfalls
- .env files might look like artifacts but contain config
- .cache directories might be needed for performance
- Some .tmp files might be active session data
- Debug logs might contain important error information
- Cleanup Strategy
- Start with obvious artifacts (.log, .tmp, *~)
- Check file age - older files are usually safer to remove
- Verify with git status what's tracked vs untracked
- Group similar files for batch decision making
Based on this analysis, I'll create a git checkpoint for safety:
git add -A
git commit -m "Pre-cleanup checkpoint" || echo "No changes to commit"
Important: I will NEVER:
- Add "Co-authored-by" or any Claude signatures
- Include "Generated with Claude Code" or similar messages
- Modify git config or user credentials
- Add any AI/assistant attribution to the commit
- Use emojis in commits, PRs, or git-related content
I'll identify cleanup targets using native tools:
- Glob tool to find temporary and debug files
- Grep tool to detect debug statements in code
- Read tool to verify file contents before removal
Critical directories are automatically protected:
- .claude directory (commands and configurations)
- .git directory (version control)
- node_modules, vendor (dependency directories)
- Essential configuration files
When I find multiple items to clean, I'll create a todo list to process them systematically.
I'll show you what will be removed and why before taking action:
- Debug/log files and temporary artifacts
- Failed implementation attempts
- Development-only files
- Debug statements in code
After cleanup, I'll verify project integrity and report what was cleaned.
If any issues occur, I can restore from the git checkpoint created at the start.
This keeps only clean, working code while maintaining complete safety.
Token Optimization
Expected range: 50–100 tokens (already clean), 300–500 tokens (typical cleanup)
Caching: Caches cleanup patterns and protected path lists in .claude/cache/cleanproject/ for 7 days. Invalidated when .gitignore changes.
Early exit: Returns immediately if no artifacts match known cleanup patterns.
Patterns used: Bash-only operations, early exit, template-based pattern matching
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: manastalukdar
- Source: manastalukdar/ai-devstudio
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.