A cleanup command for removing or organising files left behind during Claude development sessions. It can handle reports, misplaced root files, test files, work records, or all categories together.

Use it to preview or perform cleanup, consolidate reports, move tests into tests/, organise work records, and archive original files.

It reduces project clutter and helps move useful documentation into the README or the appropriate project folders.

cleanup — Command by stefan-jansen

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/stefan-jansen/claude-code-toolkit/cleanup

Clone the repo

git clone --depth 1 https://github.com/stefan-jansen/claude-code-toolkit

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 519 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.

Model	Per session	Once invoked
Fable 5	$0.00008	$0.00519
Opus 5	$0.00004	$0.00260
Sonnet 5	$0.00002	$0.00104
Haiku 4.5	$0.00001	$0.00052

Measured 3d ago against content hash 95633c0c16b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cleanup 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 3d 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.

plugins/system/commands/cleanup.md · 71 lines

What it actually says

Smart Project Cleanup

Clean up clutter from Claude development sessions.

Arguments: $ARGUMENTS

Modes

Mode	Description
`reports`	Consolidate .md reports into README/work units
`reports --auto`	Auto-consolidate without prompts
`root`	Clean misplaced files from root directory
`tests`	Move test files to tests/
`work`	Clean .claude/work directory
`all`	Full cleanup (default)
`--dry-run`	Preview without changes

What Gets Cleaned

Root clutter: Random .md files, one-off scripts, misplaced configs Test files outside tests/: test_*.py, debug_*.py, temp_*.py Report proliferation: *_REPORT.md, *_ANALYSIS.md, *_PLAN.md Work directory: Completed work >7 days, abandoned units

Consolidation Logic

Reports classified by content and filename:

Work-related (analysis, findings) → .claude/work/current/
Architecture docs (design, pattern) → .claude/reference/
General insights → Append to README.md

Process

Scan for clutter by category
Show preview with suggested action
Interactive (default) or auto mode
Archive originals to .archive/cleanup_TIMESTAMP/
Report changes made

Target Structure

project/
├── README.md              # Main docs
├── CLAUDE.md              # AI context
├── .claude/
│   ├── work/              # All work units
│   ├── reference/         # Permanent docs
│   └── memory/            # Memory files
├── tests/                 # ALL test files
├── scripts/               # Utility scripts
└── src/                   # Source code

Preserved

Core docs, source code, formal tests, structured work units

Removed/Archived

Debug scripts, one-off tests, duplicate docs, misplaced files

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.

3d ago First seen · 71 lines · 8 tokens per session scan A 95633c0c16b9

Subscribe to this mod's changes

cleanup is a command published in the GitHub repository stefan-jansen/claude-code-toolkit (85 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 519 once invoked, about $0.0000 per session on Opus 5. 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 2026-08-30.

Writing and docs agents anthropic claude-code coding-agents framework plugins

cleanup

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Smart Project Cleanup

Modes

What Gets Cleaned

Consolidation Logic

Process

Target Structure

Preserved

Removed/Archived

What this file has done since we first saw it

Other commands, from other repositories

ctx

enrich

reportloop

a11y

components

docs