- Home
- Skills
- Code Quality & Review
- 🧹 Code Comment Cleaner
More screenshots
Works with the AI Agents you already use
🧹 Code Comment Cleaner
It treats uncertain matches as review candidates, not proof of dead code.
$5
🧹 Code Comment Cleaner
Example session with this skill installed
Preview code-like comments in src/ and tests/ for .js, .ts, and .py files. Do not edit anything. Show file paths, line ranges, detection reasons, and preservation reasons.
- Read your context and instructions
- Compiled the code comment cleaner
Mode: preview
Files scanned: 24
Candidate removals: 2
- src/auth.ts L42-L45 — multi-line block contains
ifandreturn - tests/helpers.py L18-L22 — 3 adjacent
#lines each contain a code indicator
Preserved: 2 - src/config.ts L5 — contains TODO
- src/license.js L1-L12 — contains copyright
No files changed. Review the candidates before requesting clean mode.
Connects securely to your tools. The creator never sees your data.
About this skill
Review commented-out code before deleting it
Use Code Comment Cleaner to build a file-and-line preview of comment blocks that look like abandoned implementation across supported source files. It treats uncertain matches as review candidates, not proof of dead code.
Apply explicit preservation rules first
The workflow keeps blocks that match TODO, FIXME, NOTE, or XXX markers; license or copyright terms; and disabled-test patterns. It also preserves a narrow natural-language sentence pattern. Project-specific directives, docstrings, examples, generated sections, and unusual prose still need human review.
Require confirmation before a write
Preview mode changes nothing. Clean mode repeats the preview, asks for confirmation, creates a .bak beside each changed file, rechecks the proposed ranges, and removes only the reviewed blocks from bottom to top.
Cover eight language families
Rules are defined for JavaScript and TypeScript, Python, Java, Go, Rust, HTML, and CSS comment styles. Unknown file types require a decision before scanning.
Know the limitation
This is a procedural SKILL.md workflow with reference patterns, not a bundled parser or deterministic executable. Results depend on the agent's scanner implementation and can produce false positives or false negatives; review the diff and run the repository's normal checks afterward.
- Procedural workflow only; no bundled executable scanner or parser.
- Heuristics can produce false positives and false negatives, especially in docstrings, directives, templates, and unusual syntax.
- Single-line detection requires runs of at least 3 adjacent code-like comment lines; shorter runs are not candidates under the published rule.
- Preservation rules are narrow and cannot recognize every project-specific note, example, directive, or intentionally disabled block.
- Preview and confirmation are required; after cleanup, review the diff and run tests, lint, and build.
- Unknown file types require an explicit decision.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
1 use
Times used to date
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 5 months ago
Permissions
File Scopes
Code Comment Cleaner needs terminal access to run find commands for scanning multiple files and to create backup copies. File read access scans source files for commented code patterns. File write access only occurs after user explicitly confirms "yes" to cleaning; it then creates a .bak backup and writes the cleaned version. No browser, network, or environment access required.