Borrowing it
Nothing to install: this file belongs to cyanheads/docgen-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cyanheads/docgen-mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/cyanheads/docgen-mcp-serverWrote 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/cyanheads/docgen-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/cyanheads/docgen-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/cyanheads/docgen-mcp-server/claude-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 5.1 | $0.06707 | $0.06707 |
| Opus 5 | $0.03354 | $0.03354 |
| Sonnet 5 | $0.01341 | $0.01341 |
| Haiku 4.5 | $0.00671 | $0.00671 |
Grade A, and why
docgen-mcp-server CLAUDE.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 7d 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.
This is a copy
75% identical to obsidian-mcp-server AGENTS.md — 393 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 462 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developer Protocol
Server: docgen-mcp-server
Version: 0.2.2
Framework: @cyanheads/mcp-ts-core ^0.12.3
Engines: Bun ≥1.3.0, Node ≥24.0.0
MCP SDK: @modelcontextprotocol/server ^2.0.0
Zod: ^4.4.3
Read the framework docs first:
node_modules/@cyanheads/mcp-ts-core/CLAUDE.mdcontains the full API reference — builders, Context, error codes, exports, patterns. This file covers server-specific conventions only.
What this server does
docgen-mcp-server renders structured agent content into downloadable binary documents. The agent composes the content; the server prints the file a human downloads. Every render is stored tenant-scoped under a TTL and handed back as a DocumentEnvelope (a documentId + resource URI + inline base64 when small enough); a later call re-fetches it within the TTL.
Surface:
| Definition | Kind | What it does |
|---|---|---|
docgen_render_pdf |
tool | HTML / markdown / {{template}}+data → PDF (lightweight pdf-lib engine). Sets a degraded enrichment flag when it drops unsupported styling (CSS, images, scripts). |
docgen_export_spreadsheet |
tool | One or more named row sheets → .xlsx (exceljs), with an optional per-column type/format spec. |
docgen_fill_form |
tool | Fill (and optionally flatten) the AcroForm fields of a supplied PDF — source as { base64 } or an { url } fetched behind an SSRF guard. Unmatched field names come back in unmatchedFields[]. |
docgen_get_document |
tool | Re-fetch a previously rendered document by its documentId. Pure read; document_expired once the TTL lapses. |
docgen://document/{documentId} |
resource | The stable-URI delivery surface — a byte blob (real mime type) + a JSON metadata block. |
Services (src/services/document/):
render-service.ts— the bundled rendering stack (PDF, xlsx, form-fill); enforces the byte ceiling + per-render timeout and classifies failures into the typed reasons the tools declare.document-store.ts— mints opaque ids, persists bytes + metadata via tenant-scopedctx.stateunder a shared TTL, builds the envelope. A leaked id never crosses the tenant boundary.fetch-guard.ts— SSRF-guarded PDF fetcher for thefill_formURL source: https-only, blocks private/loopback/link-local/metadata destinations by resolving DNS and checking the resolved IP, re-validates every redirect hop, enforcesapplication/pdf, caps the body. Every failure path is normalized to a leak-freesource_unfetchableerror.html-blocks.ts— reduces HTML/markdown to a linear block model for the lightweight engine (no JS execution, no remote-resource fetch); flagsdegradedfor anything it can't render.format-envelope.ts/types.ts/render-types.ts— the sharedDocumentEnvelopeformatter, domain types, and render-input schemas.
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.
- 7d ago First seen · 462 lines · 6,707 tokens per session scan A 087227589e75
docgen-mcp-server CLAUDE.md is an instructions file published in the GitHub repository cyanheads/docgen-mcp-server (1 stars, last pushed 17d ago), licensed Apache-2.0. It adds 6,707 tokens to every session, about $0.0335 per session on Opus 5. A static security scan graded it A with 0 findings. It is 75% identical to obsidian-mcp-server AGENTS.md, differing in 393 lines, and is treated as a copy.
Other instructions, from other repositories
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.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
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.