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 skills add iwritec0de/app-dev --skill knip-cleanupgit clone --depth 1 https://github.com/iwritec0de/app-devWrote 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.
[](https://agentmods.dev/skills/iwritec0de/app-dev/knip-cleanup)<a href="https://agentmods.dev/skills/iwritec0de/app-dev/knip-cleanup"><img src="https://agentmods.dev/badge/skills/iwritec0de/app-dev/knip-cleanup/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.
<a href="https://agentmods.dev/skills/iwritec0de/app-dev/knip-cleanup"><img src="https://agentmods.dev/badge/skills/iwritec0de/app-dev/knip-cleanup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00128 | $0.02151 |
| Opus 5.5 | $0.00051 | $0.00860 |
| Sonnet 5.5 | $0.00026 | $0.00430 |
| Haiku 4.5 | $0.00013 | $0.00215 |
Grade A, and why
knip-cleanup 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knip — Dead Code & Dependency Cleanup
Knip finds unused files, dependencies, exports, types, and duplicate packages in JavaScript/TypeScript projects. Use this skill to analyze, report, and safely clean up projects.
What Knip Detects
| Category | Description | Risk Level |
|---|---|---|
| Unused files | Source files not imported anywhere | Medium |
| Unused dependencies | Packages in dependencies/devDependencies not imported |
High — safe to remove |
| Unlisted dependencies | Packages imported but not in package.json |
Critical — must add |
| Unused exports | Named exports not consumed by other modules | Low — may be public API |
| Unused types | TypeScript types/interfaces not referenced | Low |
| Duplicate packages | Same package at multiple versions in lockfile | Medium |
| Unused binaries | Binaries declared but not used in scripts | Low |
| Unresolved imports | Imports that point to missing modules | Critical |
Installation
# Install as dev dependency (recommended)
pnpm add -D knip
# Or run without installing
pnpm dlx knip
Configuration
Knip works zero-config for many projects but supports knip.json, knip.jsonc, .knip.json, knip.ts, or a knip key in package.json.
Basic Config (knip.json)
{
"$schema": "https://unpkg.com/knip@latest/schema.json",
"entry": ["src/index.ts", "src/main.ts"],
"project": ["src/**/*.ts"],
"ignore": ["**/*.test.ts", "**/*.spec.ts"],
"ignoreDependencies": ["@types/node"]
}
Monorepo Config
{
"$schema": "https://unpkg.com/knip@latest/schema.json",
"workspaces": {
"packages/*": {
"entry": ["src/index.ts"],
"project": ["src/**/*.ts"]
},
"apps/web": {
"entry": ["src/main.tsx", "next.config.{js,ts}"],
"project": ["src/**/*.{ts,tsx}"]
}
}
}
Common Framework Configurations
Next.js:
{
"entry": [
"src/app/**/page.tsx",
"src/app/**/layout.tsx",
"src/app/**/route.ts",
"src/app/**/loading.tsx",
"src/app/**/error.tsx",
"src/app/**/not-found.tsx",
"src/middleware.ts",
"next.config.{js,ts,mjs}"
],
"project": ["src/**/*.{ts,tsx}"]
}
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.
- 2mo ago First seen · 294 lines · 128 tokens per session scan A e28cc926f153
knip-cleanup is a skill published in the GitHub repository iwritec0de/app-dev (3 stars, last pushed 7mo ago), licensed MIT. It adds 128 tokens to every session and 2,151 once invoked, about $0.0005 per session on Opus 5.5. 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.
knip-cleanup compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| knip-cleanupiwritec0de/app-dev | Skill | 3 | 7mo ago | MIT | A | 128 | Claude Code |
| shiny-py-optimizeposit-dev/skills | Skill | 567 | 5d ago | MIT | A | 105 | Claude Code |
| shiny-r-optimizeposit-dev/skills | Skill | 567 | 5d ago | MIT | A | 105 | Claude Code |
| auditoliver-kriska/claude-elixir-phoenix | Skill | 576 | 4d ago | MIT | A | 35 | Claude Code |
| health-checkbitwize-music-studio/claude-ai-music-skills | Skill | 672 | 3d ago | CC0-1.0 | A | 38 | Claude Code |
| investigateoliver-kriska/claude-elixir-phoenix | Skill | 576 | 4d ago | MIT | A | 51 | Claude Code |
| narrow-bare-rescueoliver-kriska/claude-elixir-phoenix | Skill | 576 | 4d ago | MIT | A | 40 | Claude Code |