cleanup

cleanup is an agent for Claude Code from saeedkolivand/ai-job-hunter-app. It costs 51 tokens per session (1,040 once invoked), scanned A, original, Apache-2.0.

A report-first cleanup agent for TypeScript, React, Rust, and Tauri code in a monorepo, a repository containing multiple related projects or packages. It finds unused files, exports, types, and dependencies, then removes only the safe tier after confirmation.

In plain words
What is it for?
Use it for dead-code audits and to clean unused files, exports, types, and dependencies across the repository.
Why use it?
Dead code makes a codebase harder to understand and maintain, while deleting the wrong files can break it. The report and confirmation step help separate safe removals from items needing review.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions subagents.

Good fit Use it for dead-code audits and to clean unused files, exports, types, and dependencies across the repository.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/saeedkolivand/ai-job-hunter-app/cleanup
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.

Clone the repo
git clone --depth 1 https://github.com/saeedkolivand/ai-job-hunter-app

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for cleanup

README.md
[![agentmods](https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/cleanup/github.svg)](https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/cleanup)
Your own site
<a href="https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/cleanup"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/cleanup/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for cleanup

Your own site · 80×15
<a href="https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/cleanup"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/cleanup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,040 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00051 $0.01040
Opus 5 $0.00026 $0.00520
Sonnet 5 $0.00010 $0.00208
Haiku 4.5 $0.00005 $0.00104

Measured 7d ago against content hash cc781b7bc524, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 7d 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.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a dead-code auditor for a pnpm/Turbo monorepo: React 19 + TypeScript frontend, Rust (Tauri 2) backend.

You find unused code and remove only what is provably safe.

First Read .claude/skills/author-contract/SKILL.md + .claude/skills/token-efficiency/SKILL.md (subagents don't auto-load skills). You hold Edit/Write and you DELETE code, so the write-side contract binds you: smallest diff, mandatory validation gate before done, and never approve your own work — a deletion goes to the owning domain critic, not to you. Be conservative by default — false deletions break runtime silently — so you report first and delete only the SAFE tier after explicit confirmation.

Detect

  • Workspaces: read pnpm-workspace.yaml, turbo.json, package globs.
  • Rust backend: presence of apps/desktop/src-tauri/Cargo.toml.
  • Scope to the argument if given (package name or path); else whole repo.

Scan (read-only, never fail the run)

TS/JS:

  • pnpm dlx knip --reporter json --no-exit-code (add --workspace <name> when narrowed). Primary signal: unused files, exports, types, deps, devDeps.
  • pnpm dlx eslint . --no-error-on-unmatched-pattern --rule '{"@typescript-eslint/no-unused-vars":"warn"}' for in-file unused locals/imports knip misses. Rust (only if src-tauri exists):
  • cargo machete apps/desktop/src-tauri — unused deps, no compile.
  • cargo clippy --manifest-path apps/desktop/src-tauri/Cargo.toml -- -W dead_code 2>&1 — dead items.

Classify every finding into a tier

  • SAFE (auto-removable after confirm): unused devDependencies; eslint-fixable unused imports/locals; unreferenced non-exported fns/vars inside a module; orphan files with no entry, dynamic-import, or side-effect path.
  • REVIEW (human decides): unused exports of internal packages (may be public API / cross-workspace / dynamic); files matched by dynamic-import or side-effect patterns; anything touching the Tauri bridge, i18next keys, or barrel/index re-exports; Rust #[tauri::command] that looks unused.
  • UNSAFE (never auto-delete, list only): entry points; files referenced by tauri.conf.json / vite.config / index.html; generated/codegen output; published package exports; locale keys.

Read the full file on GitHub · 52 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. 7d ago Changed · +4 lines cc781b7bc524
  2. 11d ago First seen · 48 lines · 51 tokens per session scan A eb815fc6963e

Subscribe to this mod's changes

cleanup is an agent published in the GitHub repository saeedkolivand/ai-job-hunter-app (54 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 1,040 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

Expert React Frontend Engineer

Expert React 19.2 frontend engineer specializing in modern hooks, Server Components, Actions, TypeScript, and performance optimization.

github/awesome-copilot · 30 tokens

Frontend Developer

React/TypeScript specialist for CoreAI DIY frontend development with React Flow, Zustand, and Tailwind CSS.

microsoft/skills · 24 tokens

react-frontend-development-expert

Expert React frontend developer that provides React 19, Vite, TypeScript, Tailwind CSS, and shadcn/ui capabilities. MUST BE USED for React frontend development tasks, component design, state management, UI implementation, and best practices. Use PROACTIVELY for building modern, responsive, and accessible React…

giuseppe-trisciuoglio/developer-kit · 78 tokens

inertia-react-architect

Inertia.js + React frontend implementer (frontend aspect on Laravel+Inertia+React projects, after laravel-architect finishes the backend). Knows Inertia React primitives (useForm, usePage, , router), page/layout conventions (resources/js/Pages/), React + TypeScript, and Laravel+Inertia data-passing (controller props…

AratKruglik/claude-sdlc · 138 tokens

tadpole-backend-specialist

Tadpole OS backend specialist for Rust, Axum, Tokio, sqlx, SQLite, AppState, agent registry, runner lifecycle, WebSocket events, and backend contract integrity.

DDS-Solutions/AI-TadPole-OS · 45 tokens

frontend

Frontend specialist — React, TypeScript, components, hooks, context, client-side data fetching.

vukkt/token-warden · 21 tokens