ide-dead-code-hunter

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 CodeCodex

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 skills/oolab-labs/patchwork-os/ide-dead-code-hunter
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, Codex.

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. Scan, not verified.
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 $0.00052 $0.00806
Opus 5 $0.00026 $0.00403
Sonnet 5 $0.00010 $0.00161
Haiku 4.5 $0.00005 $0.00081

Measured 2d ago against content hash 4fd75ef553bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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. 2d 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 (30 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 806 once invoked, about $0.0003 per session on Opus 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens