Skip to content
Agentmart
Submit a tool

entropy-clean

Post-wave entropy cleanup — remove debug artifacts, enforce style, ensure git hygiene

Skill by zxdxjtu

IndexedMIT★ 8
Write a review

Chalk Labs

Need help deploying entropy-clean?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/zxdxjtu-entropy-clean

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Post-wave entropy cleanup — remove debug artifacts, enforce style, ensure git hygiene

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/entropy-clean

What's inside

Skill name
entropy-clean
Description
Post-wave entropy cleanup — remove debug artifacts, enforce style, ensure git hygiene
License
MIT
Instructions
136 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Entropy Clean — Repository Hygiene

You are an **entropy cleanup agent**. After each wave of development, you clean up the repository to prevent accumulation of debug artifacts, style violations, and orphan files.

**Parameter**: $ARGUMENTS — feature ID and optional wave number

## Step 1: Read Project Config

```bash
cat .harness/config.json
```

Extract `lint_command`, `build_command`, and any style conventions.

## Step 2: Detect Debug Artifacts

Scan changed files (from the latest wave) for common debug artifacts:

### JavaScript/TypeScript
- `console.log(` / `console.debug(` / `console.warn(` (unless in a logging module)
- `debugger;`
- `// TODO` / `// FIXME` / `// HACK` (that were added in this wave, not pre-existing)
- `alert(` / `window.confirm(`

### Python
- `print(` (unless in CLI/logging module)
- `breakpoint()` / `pdb.set_trace()`
- `import pdb`

### General
- Commented-out code blocks (>3 lines)
- `XXX` / `TEMP` / `DELETE ME` markers
- Hardcoded localhost URLs or test credentials

Report each finding with file path and line number.

## Step 3: Orphan File Detection

Check for files created during this wave that are not:
- Imported/required by any other file
- Referenced in configuration
- Test files
- Documentation

These may be abandoned experiments from failed task attempts.

## Step 4: Style Enforcement

If `lint_command` is configured:
```bash
{lint_command} 2>&1 | head -50
```

Report lint errors introduced in this wave (compare with pre-wave state).

If no lint command but common patterns detected:
- Check naming consistency (camelCase vs snake_case mixing)
- Check import ordering
- Check trailing whitespace / missing newlines

## Step 5: Git Hygiene

1. Check for uncommitted changes:
```bash
git status --short
```

2. Check commit messages from this wave follow convention:
```bash
git log --oneline -10
```

3. Check for accidentally committed files:
   - `.env` files
   - `node_modules/` entries
   - Build artifacts
   - Large binary files

## Step 6: Auto-Fix (Safe Only)

For **safe, non-destructive** fixes only:

1. Run formatter if available (prettier, black, gofmt):
```bash
{format_command} 2>&1
```

2. Remove obvious debug statements that were added in this wave (not pre-existing)

3. If auto-fixes were made, commit:
```bash
git add -A && git commit -m "chore(entropy): wave {N} cleanup — remove debug artifacts, fix style"
```

## Step 7: Generate Cleanup Report

Write to `.harness/evidence/{FXXX}/entropy-cleanup-wave-{N}.md`:

```markdown
# Entropy Cleanup — Wave {N}

## Summary
- Date: {ISO timestamp}
- Files scanned: {count}
- Issues found: {count}
- Auto-fixed: {count}
- Manual review needed: {count}

## Debug Artifacts
| File | Line | Type | Status |
|------|------|------|--------|
| {path} | {line} | console.log | auto-removed |
| {path} | {line} | TODO comment | needs review |

## Orphan Files
| File | Created By | Referenced By | Recommendation |
|------|-----------|--------------|----------------|
| {path} | {task} | none | delete |

From zxdxjtu/harness, MIT.

More from zxdxjtu/harness

Signals

Stars
8
Forks
3
Open issues
1
Last commit (this folder)
Mar 28, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from zxdxjtu

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get entropy-clean running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying entropy-clean?

CallGet help
Cite this page

entropy-clean skill. Agent Mart. https://agentmart.dev/skills/zxdxjtu-entropy-clean (last updated 2026-10-24)