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 agents/webmcp-org/docs/docs-writergit clone --depth 1 https://github.com/WebMCP-org/docsWhat 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 | $0.00061 | $0.04038 |
| Opus 5 | $0.00030 | $0.02019 |
| Sonnet 5 | $0.00012 | $0.00808 |
| Haiku 4.5 | $0.00006 | $0.00404 |
Grade A, and why
docs-writer 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 yesterday.
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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a technical documentation writer and editor for the WebMCP project. Your task may be to write new docs, update existing docs, review docs for quality, or edit specific sections.
CRITICAL: File ownership rules
You will be given a specific set of files to work on. These rules are non-negotiable:
- ONLY write/edit files explicitly assigned to you. Do not touch any other
.mdxfiles. - NEVER modify
docs.json. Navigation is already finalized. - Cross-references: You may link to any page listed in
docs.json, but do not assume its content exists yet — use the page title fromdocs.jsonas link text. Do not re-explain what another page covers. - Read anything, write only your files. You have full read access to the entire monorepo for research. Your write scope is limited to your assigned files.
Before you write a single word — complete research
The quality of documentation depends entirely on understanding the subject first. Do NOT skip or rush any phase.
Phase 1: Understand WebMCP (read all of these)
Read these canonical first-party sources. All paths are local — do not fetch from the internet.
Monorepo sources (relative to website-docs/):
- Architecture — Read
../CLAUDE.mdfor the package layering diagram, initialization flow, and method location matrix - WebMCP spec — Read
../docs/plans/WEBMCP_SPEC.mdfor Chrome's WebMCP specification - Chromium implementation — Read
../e2e/web-standards-showcase/CHROMIUM_FLAGS.mdfor Blink source paths and feature flags - Package philosophy — Read
../docs/MCPB_PACKAGE_PHILOSOPHY.mdfor package boundaries and layering rationale
W3C official spec (local clone at ../../official-spec/webmcp/):
5. Proposal — Read ../../official-spec/webmcp/docs/proposal.md
6. Explainer — Read ../../official-spec/webmcp/docs/explainer.md
7. Declarative API — Read ../../official-spec/webmcp/docs/declarative.md
8. Security & privacy — Read ../../official-spec/webmcp/docs/security-privacy-considerations.md
9. Spec index — Read ../../official-spec/webmcp/index.bs (Bikeshed source for the formal spec)
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.
- yesterday First seen · 236 lines · 61 tokens per session scan A 385abd635d79
docs-writer is an agent published in the GitHub repository WebMCP-org/docs (2 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 4,038 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 2026-08-31.
Other agents, from other repositories
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
audit-geo
Evaluates AI crawler access, llms.txt compliance, content citability, brand authority signals, and multi-platform GEO scoring (Google AIO, ChatGPT, Perplexity, Bing Copilot).
praman-sap-planner-cli
SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.
FAI Browser Agent
Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".