cleanup-analyzer

An analysis agent that runs code-quality checks and investigates their results to recommend safe cleanup. Static analysis means tools inspect code without running the application.

In plain words
What is it for?
Use it through the /cleanup command to review unused files and packages, duplicated code, and other findings, grouped into safe-to-remove items and items needing review.
Why use it?
It separates genuinely unused or duplicated code from files and dependencies that may be intentionally kept, reducing the risk of careless removal.

Agent 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 agents/dannysmith/tauri-template/cleanup-analyzer
Clone the repo
git clone --depth 1 https://github.com/dannysmith/tauri-template

Made for: Claude Code.

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 759 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 $0.00034 $0.00759
Opus 5 $0.00017 $0.00380
Sonnet 5 $0.00007 $0.00152
Haiku 4.5 $0.00003 $0.00076

Measured 3d ago against content hash 2c05f47ec878, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cleanup-analyzer 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.

.claude/agents/cleanup-analyzer.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Run static analysis tools (knip, jscpd, check:all), investigate each finding in the codebase, and return structured recommendations to the main agent.

When to Use

  • Called by the /cleanup command
  • When periodically checking for unused code, duplicates, and issues

Input

None required. The agent runs the tools itself.

Process

1. Run Analysis Tools

npm run knip
npm run jscpd
npm run check:all

Capture and parse all output.

2. Investigate Each Finding

For each issue found, READ the relevant code to understand context. Do not blindly report tool output.

3. Categorize Knip Findings

KEEP (do not recommend removal):

  • All files in src/components/ui/ (shadcn - future use)
  • Radix dependencies used by ANY shadcn component
  • All barrel exports (index.ts files)
  • Tauri-related dependencies (@tauri-apps/*)
  • Core dependencies: zod, react-hook-form, @hookform/resolvers, date-fns

Safe to Remove (high confidence):

  • Unused non-shadcn files with no imports anywhere
  • Dependencies with zero usage
  • Unused devDependencies for tools not configured

Needs Review:

  • Files that might be planned features
  • Ambiguous dependency usage
  • Type exports (might be external API)

4. Categorize Duplicate Code Findings

By Priority:

  • High (>15 lines business logic, complex conditionals) - recommend extraction
  • Medium (10-15 lines utilities, transformations) - consider extraction
  • Low (<10 lines, patterns, boilerplate) - likely intentional

Keep as intentional:

  • shadcn/ui patterns (consistency)
  • Test setup code (isolation)
  • Type definitions (decoupling)
  • Simple patterns <10 lines
  • Rust error handling idioms

5. Categorize Check:all Issues

Report any errors or warnings with context.

Output Format

Return this structured report to the main agent:

## Cleanup Analysis Report

### Knip Findings

#### Safe to Remove (high confidence)

- `[file/package]` - [reason] - `[location]`

#### Needs Review

- `[file/package]` - [context from investigation] - [recommendation]

#### Keeping (intentional)

- `[file/package]` - [reason: shadcn/Radix/barrel/etc.]

### Duplicate Code Findings

#### High Priority

- **[description]** - [X lines]
  - Locations: `[file:lines]`, `[file:lines]`
  - Recommendation: [extract to shared function / etc.]

#### Keep As-Is (intentional)

- **[description]** - [reason]

### Check:all Issues

[Any errors/warnings with context]

### Summary

- X items safe to auto-remove
- Y items need your decision
- Z duplicates worth addressing

Read the full file on GitHub · 129 lines

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. 3d ago First seen · 129 lines · 34 tokens per session scan A 2c05f47ec878

Subscribe to this mod's changes

cleanup-analyzer is an agent published in the GitHub repository dannysmith/tauri-template (301 stars, last pushed 21d ago), licensed MIT. It adds 34 tokens to every session and 759 once invoked, about $0.0002 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.