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 instructions/webmcp-org/npm-packages/agents-mdgit clone --depth 1 https://github.com/WebMCP-org/npm-packagesWrote 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/instructions/webmcp-org/npm-packages/agents-md)<a href="https://agentmods.dev/instructions/webmcp-org/npm-packages/agents-md"><img src="https://agentmods.dev/badge/instructions/webmcp-org/npm-packages/agents-md.svg" alt="Measured on agentmods" 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 | $0.02843 | $0.02843 |
| Opus 5 | $0.01422 | $0.01422 |
| Sonnet 5 | $0.00569 | $0.00569 |
| Haiku 4.5 | $0.00284 | $0.00284 |
Grade A, and why
npm-packages 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 4d 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents when working with this repository.
Commands
vp install # Install dependencies
pnpm build # Build all packages
pnpm typecheck # Type checking
vp check --fix # Lint, format, and fix (Oxlint + Oxfmt)
vp check # Check without fixing (CI)
pnpm check-all # All checks (typecheck + lint)
pnpm test:unit # Unit tests only
pnpm test:e2e # E2E tests only
pnpm test:wpt # Pinned upstream WebMCP WPT (requires Chrome Canary)
vp test run # Run tests in current package
vp pack # Build current library package
pnpm changeset # Create a changeset for versioning
Structure
packages/ # All NPM packages (@mcp-b/*)
apps/ # Deployed apps (landing-page, documentation-website)
e2e/ # E2E tests and test apps
docs/ # Technical documentation
.agents/skills/ # Agent skills and their bundled references/assets
.reference/ # Upstream reference repos (gitignored, shallow clones)
Apps (apps/*)
Both apps are pnpm workspace members.
apps/landing-page — @mcp-b/landing-page
Landing page at mcp-b.ai (also www.mcp-b.ai). Astro 6
(output: 'server') deployed to Cloudflare Workers via @astrojs/cloudflare
v13. Dev runs on real workerd (Vite Environment API).
pnpm dev(wrangler types→astro dev),pnpm build(wrangler types→astro check→astro build),pnpm preview.- Cloudflare runtime: env via
import { env } from 'cloudflare:workers';Astro.request.cf; execution context atAstro.locals.cfContext. Do NOT useAstro.locals.runtime(removed in v13). - Secrets:
npx wrangler secret put <KEY>; local secrets in.dev.vars. - Config:
astro.config.mjs,wrangler.jsonc. Excluded from rootpnpm build/check-allvia--filter '!@mcp-b/landing-page'.
apps/documentation-website — @mcp-b/documentation-website
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.
- 4d ago First seen · 209 lines · 2,843 tokens per session scan A 9d35bc37c653
npm-packages AGENTS.md is an instructions file published in the GitHub repository WebMCP-org/npm-packages (80 stars, last pushed 4d ago), licensed MIT. It adds 2,843 tokens to every session, about $0.0142 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.