Skip to content
Agentmart
Submit a tool

cleanup

Cleans up old auto-captured files with configurable retention policy and archive support.

Skill by goffity

IndexedMIT
Write a review

Chalk Labs

Need help deploying cleanup?

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/goffity-cleanup

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

Cleans up old auto-captured files with configurable retention policy and archive support.

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/cleanup

What's inside

Skill name
cleanup
Description
Cleans up old auto-captured files with configurable retention policy and archive support.
License
MIT
Instructions
134 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Cleanup - Retention Policy Manager

จัดการไฟล์เก่าด้วย retention policy พร้อม archive และ dry-run mode

## Usage

```
/cleanup                    # Preview ด้วย default settings (30 days)
/cleanup [days]             # Preview with custom retention period
/cleanup [days] --execute   # Execute cleanup
/cleanup --archive          # Archive before delete
```

## Instructions

### Step 1: Parse Arguments and Show Current State

```bash
export TZ='Asia/Bangkok'

echo "=== Auto-captured Files ==="
find docs/auto-captured -type f -name "*.md" 2>/dev/null | wc -l | xargs echo "Total files:"

echo ""
echo "=== Learnings Files ==="
find kb/05-ai-reviewed/learnings -type f -name "*.md" 2>/dev/null | wc -l | xargs echo "Total files:"

echo ""
echo "=== Archives ==="
ls -la docs/archives/ 2>/dev/null || echo "No archives yet"
```

### Step 2: Determine Mode

| Argument | Mode |
|----------|------|
| (none) | Dry-run, 30 days retention |
| `[days]` | Dry-run with custom retention |
| `[days] --execute` | Execute cleanup |
| `--archive` | Enable archiving |
| `--all` | Clean all targets |

### Step 3: Run Cleanup Script

**Dry-run mode (default):**

```bash
cd "$PROJECT_ROOT"
./scripts/cleanup.sh --days [DAYS] --dry-run [--archive] [--all]
```

**Execute mode:**

```bash
cd "$PROJECT_ROOT"
./scripts/cleanup.sh --days [DAYS] [--archive] [--all]
```

### Step 4: Show Results

Display the script output showing:
- Files that would be / were deleted
- Total space freed
- Archives created (if enabled)

### Step 5: Confirm and Suggest Next Steps

```markdown
## Cleanup Summary

| Metric | Value |
|--------|-------|
| Retention Period | [days] days |
| Files Processed | [count] |
| Space Freed | [size] |
| Archives Created | [count] |

### Next Steps

1. Review remaining files in `docs/auto-captured/`
2. Run `/distill` to extract patterns from learnings
3. Schedule periodic cleanup (cron job recommendation)
```

## Examples

```bash
# Preview what would be deleted (30 days default)
/cleanup

# Preview with 7 days retention
/cleanup 7

# Execute cleanup with archiving
/cleanup 14 --archive --execute

# Clean all targets (auto-captured + draft learnings)
/cleanup --all --execute
```

## Retention Policy

| Target | Policy |
|--------|--------|
| `docs/auto-captured/` | Delete all files older than retention period |
| `kb/05-ai-reviewed/learnings/` | Delete only `status: draft` files older than retention period |
| `kb/05-ai-reviewed/retrospective/` | Never auto-delete (permanent records) |
| `kb/02-patterns/` | Never auto-delete (distilled knowledge) |

## Archive Format

When `--archive` is enabled:
- Archives stored in `docs/archives/`
- Format: `archive_[target]_YYYYMMDD_HHMMSS.tar.gz`
- Contains all files that will be deleted

## Scheduling Recommendation

Add to crontab for automatic cleanup:

From goffity/dev-km, MIT.

More from goffity/dev-km

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jun 19, 2026 (4 months ago)
Last release
Oct 12, 2026 (18 days ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from goffity

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 cleanup 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 cleanup?

CallGet help
Cite this page

cleanup skill. Agent Mart. https://agentmart.dev/skills/goffity-cleanup (last updated 2026-10-24)