A review of Knip, a tool that finds unused files, exports, and dependencies in JavaScript projects. It checks the Knip configuration and its reports against current official guidance.

Use it when reviewing a Knip setup or running `/review-knip`, including focused checks of production settings or workspace overrides.

It helps avoid inaccurate results and poorly managed exceptions, especially in projects with multiple workspaces. It also identifies whether Knip is checking production code correctly.

review-knip — Skill for Claude Code by louisbrulenaudet

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 louisbrulenaudet/monorepo-template --skill review-knip

Clone the repo

git clone --depth 1 https://github.com/louisbrulenaudet/monorepo-template

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/louisbrulenaudet/monorepo-template/review-knip/github.svg)](https://agentmods.dev/skills/louisbrulenaudet/monorepo-template/review-knip)

Your own site

<a href="https://agentmods.dev/skills/louisbrulenaudet/monorepo-template/review-knip"><img src="https://agentmods.dev/badge/skills/louisbrulenaudet/monorepo-template/review-knip/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/louisbrulenaudet/monorepo-template/review-knip"><img src="https://agentmods.dev/badge/skills/louisbrulenaudet/monorepo-template/review-knip.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 961 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.

Model	Per session	Once invoked
Fable 5.1	$0.00066	$0.00961
Opus 5	$0.00033	$0.00481
Sonnet 5	$0.00013	$0.00192
Haiku 4.5	$0.00007	$0.00096

Measured 12d ago against content hash a1fa3d70809b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

review-knip 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 12d 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.

.agents/skills/review-knip/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Knip

Review the Knip setup for alignment with current official best practices - unused file/export/dependency detection accuracy across workspaces, false-positive suppression discipline, and the agent-facing symbols reporter. Your reply must be a plan of suggested changes: concise, actionable, structured - not only prose.

Invocation

Text after the slash command is additional scope/focus (e.g. "production pass only", "workspace overrides") - narrow the review accordingly.

Ground truth (mandatory)

Your pre-trained knowledge of Knip may be outdated (frequent releases; plugin and issue-type surface evolves). Do not draft suggestions from memory alone.

Resolve "Knip" via the Context7 MCP (resolve-library-id → query-docs) at the installed major: config schema (workspaces, ignoreIssues, includeEntryExports), issue types, plugin detection (Vite/Vitest/Turbo/Cloudflare), reporters, --fix/--fix-type behavior.
For anything Context7 lacks, use Firecrawl search/scrape restricted to the official domain (knip.dev) - configuration reference, issue-type docs, release notes for breaking changes.
Version currency: catalog knip in pnpm-workspace.yaml vs latest stable; flag deprecated config keys or removed issue types still present.
Cite the retrieved source next to every finding; label anything unverifiable as Unverified.

Scope artifacts

knip.jsonc - workspace entries, treatConfigHintsAsErrors, includeEntryExports, per-workspace overrides
Root scripts in package.json: knip, knip:production (--production --strict), knip:agent (--reporter symbols)
Gate position inside pnpm run ci; JSDoc @internal tagging convention for test-only exports
Knip policy docs: .claude/rules/quality/knip.md ↔ .cursor/rules/quality/knip.mdc

Analysis axes

Coverage: both the default and production passes stay green; entry points/plugins detected correctly for Vite/Vitest/Turbo/Wrangler surfaces; no whole-workspace ignoreWorkspaces masking real debt (current packages/vitest-config! entry should carry a justification).
Suppression discipline: no blanket ignore; scoped patterns only (ignoreIssues, suffixed patterns like "dep!"/"!tests/**!"); every override traceable to a reason; treatConfigHintsAsErrors keeps config honest.
Production pass: --production --strict reflects shipped-code reality (dev-only deps like devtools excluded deliberately); workspace isolation verified.
Fix workflow: knip --fix --fix-type dependencies,catalog safe for agents to run; results verified by reinstall + gates.
Version currency: new issue types/plugins worth adopting; renamed options migrated.

Read the full file on GitHub · 61 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.

12d ago First seen · 61 lines · 66 tokens per session scan A a1fa3d70809b

Subscribe to this mod's changes

review-knip is a skill published in the GitHub repository louisbrulenaudet/monorepo-template (19 stars, last pushed 11d ago), licensed Apache-2.0. It adds 66 tokens to every session and 961 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 2026-08-30.

Claude Code Code review agent ai-agents cloudflare cloudflare-workers cursor

review-knip

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Review Knip

Invocation

Ground truth (mandatory)

Scope artifacts

Analysis axes

What this file has done since we first saw it

Other skills, from other repositories

resolve-fixed-pr-comments

review-local-changes

review-pr

attach-review-to-pr

critique

load-pr-comments