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.
npx agentmods add skills/quangphu1912/codebase-analyzer/detecting-dead-codenpx skills add quangphu1912/codebase-analyzer --skill detecting-dead-codegit clone --depth 1 https://github.com/quangphu1912/codebase-analyzerWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00032 | $0.00832 |
| Opus 5 | $0.00016 | $0.00416 |
| Sonnet 5 | $0.00006 | $0.00166 |
| Haiku 4.5 | $0.00003 | $0.00083 |
Grade A, and why
detecting-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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Announce at start: "Using codebase-analyzer to detect dead code."
Overview
Find code that is unreachable, unused, or orphaned. Classify findings by removal safety.
Process
- Find unused exports: symbols exported but never imported elsewhere
- Find unreachable code: after return/throw, behind false conditions
- Find orphaned files: files not imported/required by anything
- Find dead config: config keys no code reads
- Find unused dependencies in package manifests
- Classify: safe-to-remove, needs-verification, keep-for-compat
Classification
| Category | Confidence | Action |
|---|---|---|
| Exported, nothing imports it | HIGH safe | Remove |
| Behind false compile condition | HIGH safe | Remove |
| Not imported but may be dynamic | MEDIUM verify | Check dynamic imports |
| Platform-conditional code | LOW verify | May be alive in other builds |
| Public API for external use | KEEP | Document if missing |
Trigger Signals
- HIGH confidence: Code dead in THIS build but build flags suggest alive in other configs ->
map-feature-gates - HIGH confidence: Significant dead code behind feature flags ->
analyze-build-pipeline - MEDIUM confidence: Dead code that was recently killed ->
analyze-agent-loop(check git history) - LOW confidence: Standard unused code -> refactoring candidate only
Warning: False Positives
Dynamic imports, reflection, plugin systems, and eval() can make live code appear dead. Always check for these before reporting.
Dead Code Archaeology
Before removing anything, determine why code died. Use git log -p -- <file> to investigate. The story matters more than the fact of death.
| Pattern | Meaning | Action |
|---|---|---|
| Behind feature flag | Upcoming, not dead (not yet released) | Keep, check flag status |
| Recently deleted | Changed requirement | Verify removal was intentional |
| Commented out | Broken migration, someone couldn't finish | Check linked tickets/PRs |
| Conditionally excluded | Configuration-dependent | May be alive in other builds |
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.
- yesterday First seen · 89 lines · 32 tokens per session scan A 332a1a109dd2
detecting-dead-code is a skill published in the GitHub repository quangphu1912/codebase-analyzer (2 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 832 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…