clean

A cleanup command for archiving finished epics and finding old or abandoned project files.

In plain words
What is it for?
Use it to preview or confirm archiving epics, removing stale files, deleting empty directories, and creating archive summaries.
Why use it?
It identifies completed work older than 30 days, leftover progress files, orphaned files, and empty folders before cleanup.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/kamiazya/scopes/clean
Clone the repo
git clone --depth 1 https://github.com/kamiazya/scopes

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 496 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00496
Opus 5 $0.00000 $0.00248
Sonnet 5 $0.00000 $0.00099
Haiku 4.5 $0.00000 $0.00050

Measured 2d ago against content hash fd25c66b5006, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clean scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/pm/clean.md · 103 lines

What it actually says

Clean

Clean up completed work and archive old epics.

Usage

/pm:clean [--dry-run]

Options:

  • --dry-run - Show what would be cleaned without doing it

Instructions

1. Identify Completed Epics

Find epics with:

  • status: completed in frontmatter
  • All tasks closed
  • Last update > 30 days ago

2. Identify Stale Work

Find:

  • Progress files for closed issues
  • Update directories for completed work
  • Orphaned task files (epic deleted)
  • Empty directories

3. Show Cleanup Plan

🧹 Cleanup Plan

Completed Epics to Archive:
  {epic_name} - Completed {days} days ago
  {epic_name} - Completed {days} days ago
  
Stale Progress to Remove:
  {count} progress files for closed issues
  
Empty Directories:
  {list_of_empty_dirs}
  
Space to Recover: ~{size}KB

{If --dry-run}: This is a dry run. No changes made.
{Otherwise}: Proceed with cleanup? (yes/no)

4. Execute Cleanup

If user confirms:

Archive Epics:

mkdir -p .claude/epics/.archived
mv .claude/epics/{completed_epic} .claude/epics/.archived/

Remove Stale Files:

  • Delete progress files for closed issues > 30 days
  • Remove empty update directories
  • Clean up orphaned files

Create Archive Log: Create .claude/epics/.archived/archive-log.md:

# Archive Log

## {current_date}
- Archived: {epic_name} (completed {date})
- Removed: {count} stale progress files
- Cleaned: {count} empty directories

5. Output

✅ Cleanup Complete

Archived:
  {count} completed epics
  
Removed:
  {count} stale files
  {count} empty directories
  
Space recovered: {size}KB

System is clean and organized.

Important Notes

Always offer --dry-run to preview changes. Never delete PRDs or incomplete work. Keep archive log for history.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 103 lines · 0 tokens per session scan A fd25c66b5006

Subscribe to this mod's changes

clean is a command published in the GitHub repository kamiazya/scopes (2 stars, last pushed 9mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 496 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.