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/AGENTS.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/agents-md)<a href="https://agentmods.dev/instructions/cyanheads/docgen-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/cyanheads/docgen-mcp-server/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/cyanheads/docgen-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/cyanheads/docgen-mcp-server/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.08228 | $0.08228 |
| Opus 5.5 | $0.03291 | $0.03291 |
| Sonnet 5.5 | $0.01646 | $0.01646 |
| Haiku 4.5 | $0.00823 | $0.00823 |
Grade A, and why
docgen-mcp-server 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 6d 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 — 436 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 — 493 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developer Protocol
Server: docgen-mcp-server
Version: 0.3.0
Framework: @cyanheads/mcp-ts-core ^0.13.15
Engines: Bun ≥1.4.0, Node ≥24.0.0
MCP SDK: @modelcontextprotocol/server ^2.3.1
Zod: ^4.6.5
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 degraded for dropped styling or character replacement on any text surface; smart-punctuation transliteration alone remains non-degraded. |
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_list_form_fields |
tool | Read-only field discovery from the same source: { fields: [{ name, type, required, options? }] }. Types: text, checkbox, dropdown, optionList, radioGroup, signature, button. Only choice fields include options; signatures/buttons are discovery only. No PDF modification or document storage. |
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. |
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.
- 6d ago Changed · +6 lines · +230 tokens per session b7fb40c9bf49
- 12d ago Changed · -4 lines · -48 tokens per session 4782622993a9
- 28d ago Changed · +29 lines · +1,339 tokens per session fe187ba0aba5
- 1mo ago First seen · 462 lines · 6,707 tokens per session scan A 087227589e75
docgen-mcp-server AGENTS.md is an instructions file published in the GitHub repository cyanheads/docgen-mcp-server (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 8,228 tokens to every session, about $0.0329 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 75% identical to obsidian-mcp-server AGENTS.md, differing in 436 lines, and is treated as a copy.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.