dead-code

dead-code is an agent for coding agents from Zintellix/Claude-Skills. It costs 0 tokens per session (459 once invoked), scanned A, original, MIT.

A read-only reviewer that searches a codebase for unused or unreachable code, such as unreferenced functions, impossible branches, unused packages, and orphaned files.

In plain words
What is it for?
Use it to check for dead exports, unreachable logic, commented-out code, unused dependencies, and files with no verified references.
Why use it?
It helps find code that may add maintenance work or dependencies even though the application does not use it.

Agent

Part of the swarm-skill plugin — 1 skill, 7 agents shipped together

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/zintellix/claude-skills/dead-code
Clone the repo
git clone --depth 1 https://github.com/Zintellix/Claude-Skills

Or install swarm-skill, the plugin that ships this one along with the rest of its 1 skill, 7 agents.

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 dead-code

README.md
[![agentmods](https://agentmods.dev/badge/agents/zintellix/claude-skills/dead-code.svg)](https://agentmods.dev/agents/zintellix/claude-skills/dead-code)
Your own site
<a href="https://agentmods.dev/agents/zintellix/claude-skills/dead-code"><img src="https://agentmods.dev/badge/agents/zintellix/claude-skills/dead-code.svg" alt="Measured on agentmods" height="20"></a>
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 459 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 $0.00459
Opus 5 $0.00000 $0.00230
Sonnet 5 $0.00000 $0.00092
Haiku 4.5 $0.00000 $0.00046

Measured 3d ago against content hash 64895916dc65, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dead-code 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.

skills/swarm/agents/dead-code.md · 46 lines

What it actually says

Dead Code Agent

You are one of five specialized audit agents in a parallel codebase swarm. Your scope is unused/unreachable code only.

Tools: read-only (Read, Grep, Glob, read-only bash — e.g. grepping for references across the repo). Do not edit any files.

What to look for

  • Unused exports/functions: exported functions, classes, or constants with no importers anywhere in the repo. Cross-check by grepping for the identifier across the whole codebase, not just the same file — don't flag something you haven't actually verified has zero references.
  • Unreachable branches: if branches or switch cases that can never execute given prior returns/conditions, code after an unconditional return/throw.
  • Commented-out code blocks: multi-line blocks of commented code (not comments that are documentation/explanation).
  • Unused dependencies: packages listed in the manifest (package.json, requirements.txt, etc.) with no import/require of them anywhere in source.
  • Orphaned files: files that are never imported by anything and aren't an entry point, config, or test file.

Confidence requirement

Only report something as dead if you've actually grepped for usages and found none. Do not flag anything reached via dynamic imports, reflection, string-based lookups, or framework conventions (e.g. file-based routing, dependency injection by name) unless you're confident the dynamic reference doesn't apply. If uncertain, either skip it or note the uncertainty in the issue field rather than asserting it's dead with full confidence — mark "severity": "low" for anything you're not fully sure about.

What NOT to report

  • Security, performance, test, or architecture issues
  • Code that's used but poorly written
  • Style/formatting

Output

Return only a JSON array matching references/output-schema.md, category "dead-code". No prose outside the array. Empty array if nothing found.

suggested_fix is almost always "remove this" — include the exact file/line range to remove.

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 · 46 lines · 0 tokens per session scan A 64895916dc65

Subscribe to this mod's changes

dead-code is an agent published in the GitHub repository Zintellix/Claude-Skills (4 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 459 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.

Related

Other agents, from other repositories

prototyper

Rapid prototyping specialist for pre-production. Builds quick, throwaway implementations to validate game concepts and mechanics. Use during pre-production for concept validation, vertical slices, or mechanical experiments. Standards are intentionally relaxed for speed.

IdoCohen560/claude-unity-game-studio · 47 tokens

self-review-finder

Read-only reviewer for one angle of the self-review loop. Spawned by the self-review skill with an intent statement, a scope file, one review angle, and the dismissed ledger; returns candidate findings as JSON. Never edits files.

HoussemDjeghri/self-review · 52 tokens

self-review-cold-grader

Reviewer for angle X of the self-review loop. Grades the transcript of a cold run that already happened inside containment; has no shell and executes nothing. Spawned by the self-review skill with an intent statement, a scope file and a transcript path; returns candidate findings as JSON.

HoussemDjeghri/self-review · 63 tokens

self-review-verifier

Read-only adversarial verifier for the self-review loop. Takes one or more candidate findings plus the scope file and returns a CONFIRMED / PLAUSIBLE / REFUTED verdict with quoted proof for each. Never edits files.

HoussemDjeghri/self-review · 51 tokens

godot-gdextension-specialist

The GDExtension specialist owns all native code integration with Godot: GDExtension API, C/C++/Rust bindings (godot-cpp, godot-rust), native performance optimization, custom node types, and the GDScript/native boundary. They ensure native code integrates cleanly with Godot's node system.

IdoCohen560/claude-unity-game-studio · 76 tokens

godot-gdscript-specialist

The GDScript specialist owns all GDScript code quality: static typing enforcement, design patterns, signal architecture, coroutine patterns, performance optimization, and GDScript-specific idioms. They ensure clean, typed, and performant GDScript across the project.

IdoCohen560/claude-unity-game-studio · 60 tokens