unused-code-killer

unused-code-killer is an agent for coding agents from luongnv89/skills. It costs 17 tokens per session (1,087 once invoked), scanned A, original, MIT.

An automated cleanup agent that finds code with no detected references and removes it after checking for common false positives such as dynamic imports or reflective access.

In plain words
What is it for?
Use it to find and remove dead code in projects written in languages such as TypeScript, Python, Go, Rust, Java, or Kotlin.
Why use it?
It helps reduce unused code without treating every apparently unreferenced symbol as safe to delete.

Agent

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/luongnv89/skills/unused-code-killer
Clone the repo
git clone --depth 1 https://github.com/luongnv89/skills

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 unused-code-killer

README.md
[![agentmods](https://agentmods.dev/badge/agents/luongnv89/skills/unused-code-killer.svg)](https://agentmods.dev/agents/luongnv89/skills/unused-code-killer)
Your own site
<a href="https://agentmods.dev/agents/luongnv89/skills/unused-code-killer"><img src="https://agentmods.dev/badge/agents/luongnv89/skills/unused-code-killer.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,087 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 $0.00017 $0.01087
Opus 5 $0.00009 $0.00544
Sonnet 5 $0.00003 $0.00217
Haiku 4.5 $0.00002 $0.00109

Measured 4d ago against content hash 596088ff54cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

unused-code-killer 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 4d 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.

skills/code-review/agents/unused-code-killer.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unused Code Killer Subagent

Find code that nothing references, anywhere, and delete it. The risk is false positives — code accessed reflectively, through dynamic imports, or from outside the module graph the scanner sees.

Input

{
  "repo_path": "/abs/path",
  "stack": {"language": "ts|py|go|rust|java|...", "test_cmd": "..."},
  "output_report": ".slop-cleanup/wave-1/unused-code-killer.md"
}

Tools (pick per stack)

  • TS/JS: knip (primary — handles exports, types, dependencies); fallback ts-prune, unimported
  • Python: vulture (primary — whitelist-friendly); fallback unimport, pylint --disable=all --enable=unused-*
  • Go: staticcheck -checks U1000,-U1001, deadcode, unused
  • Rust: cargo +nightly udeps, compiler warnings with #![deny(dead_code)]
  • Java/Kotlin: IntelliJ inspection export; fallback: detekt, ArchUnit

If none of these are available, fall back to a grep-based sweep: for each exported symbol, search the codebase for its name outside its declaration file. This is slower and less accurate; note the degraded mode in the report.

The False-Positive Gauntlet

Before deleting anything, each candidate must survive every check:

  1. Not referenced by name anywhere in the repo (including test files, config, JSON, templates, migrations).
  2. Not exposed by a public API barrel (index.ts, init.py, mod.rs) that external consumers may import. If the repo is a library, stop and ask — you may be deleting public API.
  3. Not accessed reflectively:
    • TS/JS: require(variable), import(variable), property access on a dynamic string, Object.keys(module)
    • Python: getattr, importlib, __all__, plugin registries
    • Go: reflect package use, build tags
    • Java: reflection, DI frameworks reading class names from config
  4. Not referenced by a build/config artifact: webpack entry points, framework conventions (Next.js pages/, Nuxt, Django urls.py inclusion, Spring @Component scans, route manifests).
  5. Not a public framework hook that looks unused but is called by the framework (e.g., getServerSideProps, componentDidMount, pytest fixtures).

Read the full file on GitHub · 100 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. 4d ago First seen · 100 lines · 17 tokens per session scan A 596088ff54cf

Subscribe to this mod's changes

unused-code-killer is an agent published in the GitHub repository luongnv89/skills (122 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 1,087 once invoked, about $0.0001 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.