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/new1direction/webmcp-anything/agents-mdgit clone --depth 1 https://github.com/New1Direction/webmcp-anythingWrote 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/new1direction/webmcp-anything/agents-md)<a href="https://agentmods.dev/instructions/new1direction/webmcp-anything/agents-md"><img src="https://agentmods.dev/badge/instructions/new1direction/webmcp-anything/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 | $0.04267 | $0.04267 |
| Opus 5 | $0.02133 | $0.02133 |
| Sonnet 5 | $0.00853 | $0.00853 |
| Haiku 4.5 | $0.00427 | $0.00427 |
Grade A, and why
webmcp-anything AGENTS.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`wrangler deploy` ships to production. Pre-deploy: verify typecheck passes. Post-deploy: smoke test the affected route with `curl -i`. How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Workspace rules for AI coding agents (Claude Code, Cursor, Cline, Gemini CLI, Aider, etc.). Read this first before modifying anything in this repo.
This file is the single source of truth. If CLAUDE.md, .cursorrules, or any other IDE-specific file contradicts it, this file wins — fix the other file.
1. What this project is
wmcp.sh — a hosted Cloudflare Worker that turns any URL into agent-callable MCP tools, plus a Chrome extension, plus open-source adapters, plus SDKs.
- Production worker:
https://wmcp.sh(Cloudflare account[email protected], zone0284dbcc5d7326bc016b28e3295f4dca) - Public repo:
https://github.com/New1Direction/webmcp-anything(private during pre-launch, will flip public) - Stack: Hono + Cloudflare Workers + KV. TypeScript in
worker/, plain ES modules inadapters/.
2. Repo layout
.
├── adapters/ canonical adapter library (shared by worker + extension)
│ ├── shopify.js live Shopify (read + add_to_cart)
│ ├── jsonld.js generic schema.org Product
│ ├── openapi.js any OpenAPI 3.x / Swagger 2.0 spec → tools
│ ├── llm.js last-resort LLM-fallback via Haiku
│ ├── CONTRACT.md the detect() / extract() / actions interface
│ ├── _template/ starter scaffold for new adapters
│ ├── _fixtures/ captured pages for offline tests
│ └── _test/run.mjs node:test harness, zero deps
├── worker/ hosted API
│ ├── src/*.ts Hono routes, OAuth, billing, SEO pages, token vault
│ ├── wrangler.toml CF Worker config + KV bindings
│ └── tsconfig.json
├── extension/ Chrome MV3 extension (cache-back path)
├── sdks/
│ ├── python/wmcp/ Python SDK (pip install wmcp)
│ └── javascript/src/ TypeScript SDK (@wmcp/sdk)
├── scripts/seed_directory.py pre-cache URLs to populate /u/* SEO pages
├── launch/ launch-day assets (show-hn, twitter, substack, demo)
└── ADAPTERS_WANTED.md sites where PRs are welcome
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 · 280 lines · 4,267 tokens per session scan A c2d6dfb49c95
webmcp-anything AGENTS.md is an instructions file published in the GitHub repository New1Direction/webmcp-anything (6 stars, last pushed 2mo ago), licensed MIT. It adds 4,267 tokens to every session, about $0.0213 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
claude-prompts-mcp CLAUDE.md
Claude Code instructions for minipuft/claude-prompts-mcp, covering claude prompts mcp -- operator handbook, core principles, node.js support boundaries, validation gates (one contract, impact-aware subsets) and fleet standards upstream (minipuft/repository-standards).
mcp-ts-core AGENTS.md
AGENTS.md instructions for cyanheads/mcp-ts-core, covering developer protocol, consumers, core rules, exports reference and import conventions.
senado-br-mcp-cloudflare CLAUDE.md
Claude Code instructions for SidneyBissoli/senado-br-mcp-cloudflare, covering claude.md, project, commands, architecture and testing convention.
gmail-mcp CLAUDE.md
Instructions for cunicopia-dev/gmail-mcp, covering gmail mcp — development guide, what it is, layout, module responsibilities and oauth model.
pubcrawl CLAUDE.md
Claude Code instructions for nickjlamb/pubcrawl, covering claude.md, project overview, commands, testing and architecture.
ctxlayer CLAUDE.md
Claude Code instructions for stevenn/ctxlayer, covering ctxlayer — claude code briefing, what runs where, architecture pointers, how a claude session should work in this repo and conventions.