ide-dead-code-hunter

ide-dead-code-hunter is a skill for Claude Code from Oolab-labs/patchwork-os. It costs 52 tokens per session (806 once invoked), scanned A, a copy of ide-dead-code-hunter, MIT.

A workspace analysis skill that searches for unused code, unused imports, and code that cannot be reached, then checks references to reduce false alarms. LSP is a code-analysis system used by editors to understand symbols and references.

In plain words
What is it for?
Use it to inspect a file, directory, or whole workspace and produce a prioritized list of suspected dead code with confidence levels.
Why use it?
It helps identify technical leftovers before cleanup or a large refactor, while distinguishing genuinely unused code from public code that only appears unused.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: agent in frontmatter.

Part of the claude-ide-bridge plugin — 4 skills, 1 agent, 16 hooks shipped together

Good fit Use it to inspect a file, directory, or whole workspace and produce a prioritized list of suspected dead code with confidence levels.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oolab-labs/patchwork-os/ide-dead-code-hunter
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.

Any agent
npx skills add Oolab-labs/patchwork-os --skill ide-dead-code-hunter
Clone the repo
git clone --depth 1 https://github.com/Oolab-labs/patchwork-os

Made for: Claude Code.

Or install claude-ide-bridge, the plugin that ships this one along with the rest of its 4 skills, 1 agent, 16 hooks.

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 ide-dead-code-hunter

README.md
[![agentmods](https://agentmods.dev/badge/skills/oolab-labs/patchwork-os/ide-dead-code-hunter/github.svg)](https://agentmods.dev/skills/oolab-labs/patchwork-os/ide-dead-code-hunter)
Your own site
<a href="https://agentmods.dev/skills/oolab-labs/patchwork-os/ide-dead-code-hunter"><img src="https://agentmods.dev/badge/skills/oolab-labs/patchwork-os/ide-dead-code-hunter/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 ide-dead-code-hunter

Your own site · 80×15
<a href="https://agentmods.dev/skills/oolab-labs/patchwork-os/ide-dead-code-hunter"><img src="https://agentmods.dev/badge/skills/oolab-labs/patchwork-os/ide-dead-code-hunter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 806 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 100% copy Near-identical to another mod 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 $0.00052 $0.00806
Opus 5.5 $0.00021 $0.00322
Sonnet 5.5 $0.00010 $0.00161
Haiku 4.5 $0.00005 $0.00081

Measured 1mo ago against content hash 4fd75ef553bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ide-dead-code-hunter 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 1mo 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.

Origin

This is a copy

100% identical to ide-dead-code-hunter — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

claude-ide-bridge-plugin/skills/ide-dead-code-hunter/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IDE Dead Code Hunter

Prerequisites

  1. Check if getToolCapabilities is available.
    • Not available: tell the user this skill requires the Claude IDE Bridge with a connected VS Code extension, then stop.
    • Available: call it. If extensionConnected is false: show the same message and stop. If true: proceed.

Goal

Find dead code — unused exports, functions with zero callers, unused imports — and produce a prioritized cleanup list with confidence badges.

Workflow

Phase 1: Scope

  1. Note the argument: $ARGUMENTS

    • If a specific file path: scope search to that file only
    • If a directory: scope to that directory
    • If empty: search the entire workspace
  2. Use getProjectInfo to understand the project type and entry points (to avoid flagging intentional public API exports as dead)

Phase 2: Detect unused symbols

  1. Call detectUnusedCode on each in-scope file (or workspace-wide if no scope)

  2. For each reported unused symbol, call findReferences to cross-verify:

    • Zero references: confirmed dead — high confidence
    • References only in the same file: likely dead (internal-only) — medium confidence
    • References in other files: false positive from detectUnusedCode — skip
  3. Call searchWorkspace with pattern ^export on TypeScript/JS files to find exported symbols not caught by detectUnusedCode, then run findReferences on each to check usage outside the file

Phase 3: Unused imports

  1. Use getDocumentSymbols on each in-scope file to list import declarations
  2. For any import whose symbol has zero findReferences results in the current file body: flag as unused import

Phase 4: Build the report

Produce a Markdown table sorted by priority:

## Dead Code Report

Scoped to: [scope or "workspace-wide"]
Analyzed: N files

### High Confidence (zero external references)

| Symbol | File | Line | Type | Action |
|--------|------|------|------|--------|
| `functionName` | src/foo.ts | 42 | function | Delete |
| ...

### Medium Confidence (internal refs only)

| Symbol | File | Line | Type | Refs | Action |
|--------|------|------|------|------|--------|
| `helperFn` | src/bar.ts | 15 | function | 2 (same file) | Review |
| ...

### Unused Imports

| Import | File | Line | Action |
|--------|------|------|--------|
| `{ OldType }` | src/baz.ts | 3 | Remove |
| ...

### Summary
- High confidence dead code: N symbols
- Medium confidence: M symbols
- Unused imports: K declarations
- Estimated line reduction: ~X lines

Read the full file on GitHub · 92 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. 1mo ago First seen · 92 lines · 52 tokens per session scan A 4fd75ef553bb

Subscribe to this mod's changes

ide-dead-code-hunter is a skill published in the GitHub repository Oolab-labs/patchwork-os (31 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 806 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to ide-dead-code-hunter, differing in 0 lines, and is treated as a copy.