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/drolosoft/go-docs-mcp/claude-mdgit clone --depth 1 https://github.com/drolosoft/go-docs-mcpWrote 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/drolosoft/go-docs-mcp/claude-md)<a href="https://agentmods.dev/instructions/drolosoft/go-docs-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/drolosoft/go-docs-mcp/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 | $0.00718 | $0.00718 |
| Opus 5 | $0.00359 | $0.00359 |
| Sonnet 5 | $0.00144 | $0.00144 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
go-docs-mcp 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 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
go-docs-mcp
Go MCP server serving documents (PDF, TXT, MD, CSV, images) to LLMs via stdio.
Build & Run
make build # ./go-docs-mcp binary
make install # /usr/local/bin/go-docs-mcp
make test # go test -v -race ./...
DOCS_MCP_DIR=~/docs ./go-docs-mcp # custom dir
Architecture
main.go— MCP server init, 12 tool registrations, stdio transportinternal/pdf/reader.go— Document extraction (pdftotext/pdfinfo/pdfimages/tesseract), mtime cache, search, metadata, images, OCR, outlines, tables
Key Decisions
- Uses
pdftotext -layoutfor text extraction (preserves formatting) - mtime-based cache: re-extracts only when file changes
- Path traversal blocked via
filepath.Base()+ extension allowlist check - Page tracking uses form feed (
\f) characters from pdftotext output - Homebrew path detection for macOS (
/opt/homebrew/bin/) - Env var:
DOCS_MCP_DIR(primary),PDF_MCP_DIR(backward compat),DROLO_DOCS_DIR(legacy) - Default directory:
~/.docs-mcp/documents/ - URL downloads limited to 50MB, validated Content-Type
- Image extraction limited to 10 per call to avoid huge responses
- Supports multiple document types: PDF, TXT, MD, CSV, DOCX (with pandoc), images (with tesseract)
Tools
| Tool | Params | Notes |
|---|---|---|
list_documents |
none | Scans docsDir for supported files, returns JSON array |
read_document |
filename (req), page (opt), pages (opt) |
Full text, single page, or page ranges |
search_document |
filename (req), query (req) |
Case-insensitive, 2-line context |
get_document_summary |
filename (req) |
First 3 pages |
get_document_metadata |
filename (req) |
Full PDF metadata via pdfinfo |
extract_images |
filename (req), page (opt) |
Extract images as base64 (max 10) |
read_url |
url (req), pages (opt) |
Download PDF from URL + extract text |
ocr_document |
filename (req), page (opt), language (opt) |
Force OCR on PDF |
list_formats |
none | Show supported formats and dependency status |
read_image |
filename (req), language (opt) |
OCR standalone image file |
get_document_outline |
filename (req) |
Extract heading structure |
extract_tables |
filename (req), page (opt) |
Extract table-like structures |
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 · 54 lines · 718 tokens per session scan A 768fb5a08ae5
go-docs-mcp CLAUDE.md is an instructions file published in the GitHub repository drolosoft/go-docs-mcp (10 stars, last pushed 18d ago), licensed MIT. It adds 718 tokens to every session, about $0.0036 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 instructions, from other repositories
docsift CLAUDE.md
Instructions for anishmoncivarghese/docsift, covering docsift, key documents (read before making product decisions), commands, architecture (src layout, package docsift) and hard rules.
agentic-resume-builder CLAUDE.md
Claude Code instructions for WtotdeD/agentic-resume-builder, covering agentic-resume-builder development guidelines, what this repo is, active technologies, package manager and validation.
md-anything copilot-instructions.md
Instructions for ojspace/md-anything, covering copilot instructions for md-anything, build, test, and lint commands, full suite, contributor-safe required subset and regenerate generated pdf/epub fixtures when needed.
asset-aware-mcp copilot-instructions.md
Copilot instructions for u9401066/asset-aware-mcp, covering copilot 自定義指令, 專案概述, 核心功能, llm 後端 and pdf → 資產引擎選擇 🚦.
agentic-reviewer AGENTS.md
Instructions for FilippoScaramuzza/agentic-reviewer, covering agentic reviewer — journal paper review framework, project overview, directory structure, workflow and phase 0: setup & paper conversion.
flexberry-markitdown-mcp CLAUDE.md
Claude Code instructions for Flexberry/flexberry-markitdown-mcp, covering claude.md, project overview, commands, install in development mode (all test/lint deps) and install with both pdf backends.