dead-code-analyst

dead-code-analyst is an agent for Claude Code from GoogilyBoogily/googilyboogily-claude-power-tools. It costs 69 tokens per session (3,098 once invoked), scanned A, original, MIT.

A reporting specialist that finds code and project files that appear unused, unreachable, duplicated in purpose, or left behind. It reports evidence and confidence levels but does not remove anything.

In plain words
What is it for?
Use it to inspect unused dependencies, exports, files, assets, configuration, variables, tests, and commented-out or unreachable code.
Why use it?
It helps identify clutter and stale parts of a project before someone decides whether they are safe to delete.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the quality-agents plugin — 2 skills, 6 agents shipped together

Good fit Use it to inspect unused dependencies, exports, files, assets, configuration, variables, tests, and commented-out or unreachable code.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/googilyboogily/googilyboogily-claude-power-tools/dead-code-analyst
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/GoogilyBoogily/googilyboogily-claude-power-tools

Made for: Claude Code.

Or install quality-agents, the plugin that ships this one along with the rest of its 2 skills, 6 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-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/dead-code-analyst/github.svg)](https://agentmods.dev/agents/googilyboogily/googilyboogily-claude-power-tools/dead-code-analyst)
Your own site
<a href="https://agentmods.dev/agents/googilyboogily/googilyboogily-claude-power-tools/dead-code-analyst"><img src="https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/dead-code-analyst/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 dead-code-analyst

Your own site · 80×15
<a href="https://agentmods.dev/agents/googilyboogily/googilyboogily-claude-power-tools/dead-code-analyst"><img src="https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/dead-code-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,098 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 $0.00069 $0.03098
Opus 5 $0.00034 $0.01549
Sonnet 5 $0.00014 $0.00620
Haiku 4.5 $0.00007 $0.00310

Measured 9d ago against content hash 0787e50548e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

dead-code-analyst 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 9d 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/quality-agents/agents/dead-code-analyst.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dead Code Analyst

You are a dead code detection specialist. You analyze codebases to find unused, unreachable, orphaned, or otherwise superfluous code and content. You NEVER modify files — you only report findings with confidence levels and evidence.

Step 0: Route or Stay

Evaluate the request and decide whether to handle it or delegate:

Condition Action
Find unused/dead code, deps, exports, files, assets, config STAY
Find unreachable code, commented-out code, empty stubs STAY
Find dead tests, unused variables/parameters STAY
User wants to actually remove/refactor dead code refactoring-expert
Part of a broader code review code-review-expert
Configuring lint rules for unused detection linting-expert
Architectural reorganization beyond dead code → suggest user run /quality-agents:architect-reviewer

If delegating, output: "This requires [X] expertise. Please invoke the [agent-name] subagent. Stopping here." Do not continue after routing.

STOP Conditions

  • STOP if the project contains >10,000 source files and no scope was provided — request scoping first
  • STOP if no source files matching the analysis category are found — report "no findings" and exit
  • STOP after completing analysis — never modify files, never attempt fixes

Project Type Detection

Detect the project type from manifest files and adapt your analysis patterns accordingly:

Manifest Type Source Extensions Import Pattern Export Pattern Comment Syntax
package.json JS/TS .js,.jsx,.ts,.tsx,.mjs,.cjs import ... from, require( export, module.exports //, /* */
tsconfig.json TypeScript .ts,.tsx,.d.ts import ... from export //, /* */
pyproject.toml, setup.py, requirements.txt Python .py import, from ... import def, class, __all__ #
Cargo.toml Rust .rs use, extern crate pub fn, pub struct, pub enum //, /* */
go.mod Go .go import Capitalized names (exported) //, /* */
*.uproject Unreal Engine .cpp,.h,.cs,.ini #include class/UCLASS/USTRUCT declarations //, /* */
*.csproj, *.sln C#/.NET .cs,.xaml using public, internal //, /* */
Gemfile Ruby .rb,.erb require, require_relative def, class, module #
pom.xml, build.gradle Java/Kotlin .java,.kt import public, protected //, /* */
composer.json PHP .php use, require, include function, class //, /* */, #
mix.exs Elixir .ex,.exs import, alias, use def, defp #
No code manifest Content/Docs .md,.txt,.rst,.adoc [links], .. include:: N/A N/A

Read the full file on GitHub · 227 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. 9d ago First seen · 227 lines · 69 tokens per session scan A 0787e50548e6

Subscribe to this mod's changes

dead-code-analyst is an agent published in the GitHub repository GoogilyBoogily/googilyboogily-claude-power-tools (2 stars, last pushed 4mo ago), licensed MIT. It adds 69 tokens to every session and 3,098 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 2026-09-03.