entropy-clean
Post-wave entropy cleanup — remove debug artifacts, enforce style, ensure git hygiene
Skill by zxdxjtu
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.
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.
About
Reviews
Write a reviewNo 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
- 0.466score
tdd-align
zxdxjtu
Generate three-layer tests from spec — tests are the alignment contract
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
eval-fix
zxdxjtu
Adversarial fix loop: read eval report → fix gaps → re-evaluate → repeat until convergence
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
evaluate
zxdxjtu
Adversarial evaluation: compare dev product against reference baseline using Playwright MCP
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
harness-init
zxdxjtu
Initialize Harness for your project — learn repo, team norms, generate customized framework
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
harness-status
zxdxjtu
Restore state, health check, determine current phase, suggest next step
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
proposal
zxdxjtu
Start a new feature proposal — guided spec + design generation
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
sdd-init
zxdxjtu
Initialize SDD harness for a project — scan codebase, generate config, full-spec, full-design
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
spec-review
zxdxjtu
Multi-person spec review with line-by-line comments and resolution tracking
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
steward
zxdxjtu
Module stewardship guardian — check code changes against AGENT.md boundaries and contracts
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
archive
zxdxjtu
Phase 3: merge spec/design deltas, code review, atomic commits, push, and trigger self-evolution
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
baseline
zxdxjtu
Capture baseline of a reference product using Playwright MCP for clone/replicate scenarios
SkillDFreshness: D★ 8Claude Code +9 - 0.463score
help
zxdxjtu
Explain Harness plugin and available commands
SkillDFreshness: D★ 8Claude Code +9
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
- Repository
- github.com/zxdxjtu/harness
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from zxdxjtu
- 0.466score
evaluate
zxdxjtu
Adversarial evaluation: compare dev product against reference baseline using Playwright MCP
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
harness-init
zxdxjtu
Initialize Harness for your project — learn repo, team norms, generate customized framework
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
baseline
zxdxjtu
Capture baseline of a reference product using Playwright MCP for clone/replicate scenarios
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
eval-fix
zxdxjtu
Adversarial fix loop: read eval report → fix gaps → re-evaluate → repeat until convergence
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
archive
zxdxjtu
Phase 3: merge spec/design deltas, code review, atomic commits, push, and trigger self-evolution
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
harness-status
zxdxjtu
Restore state, health check, determine current phase, suggest next step
SkillDFreshness: D★ 8Claude Code +9
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.
Cite this page
entropy-clean skill. Agent Mart. https://agentmart.dev/skills/zxdxjtu-entropy-clean (last updated 2026-10-24)