agentmods.dev

node-modules-inspector AGENTS.md

A project instruction file for antfu/node-modules-inspector, a tool that shows how a project's installed packages depend on one another. It covers the repository layout, commands, and coding conventions.

In plain words
What is it for?
Use it when adding features, fixing bugs, changing dependencies, or running builds, tests, linting, and type checks in this pnpm monorepo, meaning a repository containing multiple related packages.
Why use it?
It gives coding agents one source of truth for working in the project and running its checks correctly.

Instructions file for CodexOpenCode

2.9k 8d ago A scan 354 tokens original MIT
View the source file antfu/node-modules-inspector
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 instructions/antfu/node-modules-inspector/agents-md
Clone the repo
git clone --depth 1 https://github.com/antfu/node-modules-inspector

Made for: Codex, OpenCode.

Per session 354 This file is loaded in full into every session.
When invoked 354 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00354 $0.00354
Opus 5 $0.00177 $0.00177
Sonnet 5 $0.00071 $0.00071
Haiku 4.5 $0.00035 $0.00035

Measured 2d ago against content hash 560626d109f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

node-modules-inspector AGENTS.md 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.

AGENTS.md · 28 lines

What it actually says

AGENTS.md

CLI + web UI to visualize a project's node_modules. Supports pnpm, npm, bun. Hosted version: node-modules.dev.

Layout

  • packages/node-modules-inspector/ — CLI + Nuxt SPA + devframe RPC server
  • packages/node-modules-tools/ — core lib: package-manager agents, resolution, types
  • test/e2e/ — Playwright

RPC functions live in packages/node-modules-inspector/src/node/rpc/<name>.ts — one per file, wired up in handlers.ts.

Commands (from repo root)

  • pnpm dev — dev server
  • pnpm build — full build
  • pnpm test / pnpm test:e2e / pnpm test:a11y — vitest / playwright e2e / playwright accessibility (axe-core)
  • pnpm lint / pnpm typecheck

Conventions

  • TypeScript only. Vue 3 Composition API + <script setup lang="ts">.
  • pnpm 11 with catalogs — new deps go in pnpm-workspace.yaml, referenced as catalog:<name>.
  • Lint: @antfu/eslint-config. Pre-commit runs eslint --fix via nano-staged.
  • Commits: conventional, optional scope — feat(inspector): ..., fix: ....
  • AGENTS.md is the source of truth; CLAUDE.md is a symlink to it.
  • E2E runs single-worker (stateful WS backend) — don't parallelize.
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 · 28 lines · 354 tokens per session scan A 560626d109f5

Subscribe to this mod's changes

node-modules-inspector AGENTS.md is an instructions file published in the GitHub repository antfu/node-modules-inspector (2,934 stars, last pushed 8d ago), licensed MIT. It adds 354 tokens to every session, about $0.0018 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.

DebuggingTestingdevframedevtoolsinspectornode-modulesnpm
Related

Other instructions, from other repositories

rn-devtools-hub CLAUDE.md

Instructions for rn-devtools-hub/rn-devtools-hub: Instructions for Claude Code in this repo.

rn-devtools-hub/rn-devtools-hub · 268 tokens

rn-devtools-hub AGENTS.md

Instructions for rn-devtools-hub/rn-devtools-hub, covering agents.md: guide for ai agents, if you are working on this repo and driving a running app (mcp).

rn-devtools-hub/rn-devtools-hub · 4,694 tokens

dev3000 AGENTS.md

Instructions for vercel-labs/dev3000, covering agents.md, runtime, local ui, production workflows, browser tools and development rules.

vercel-labs/dev3000 · 1,320 tokens

agent-inspect AGENTS.md

Instructions for rajudandigam/agent-inspect, covering agentinspect ai maintainer instructions, product boundary, source of truth, public-copy rule and start every task.

rajudandigam/agent-inspect · 1,932 tokens

jenkins-cli CLAUDE.md

Instructions for avivsinai/jenkins-cli, covering claude.md, build & test commands, run a single test, skip e2e tests during unit testing and e2e with colima on macos (if docker is unreachable).

avivsinai/jenkins-cli · 1,057 tokens

huly-mcp CLAUDE.md

Instructions for dearlordylord/huly-mcp, covering project instructions, design principle: llm-first api, project harness (copy to new projects), package manager and verification.

dearlordylord/huly-mcp · 3,317 tokens