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/h0rv/d2-mcp/agents-mdgit clone --depth 1 https://github.com/h0rv/d2-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/h0rv/d2-mcp/agents-md)<a href="https://agentmods.dev/instructions/h0rv/d2-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/h0rv/d2-mcp/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 | $0.00703 | $0.00703 |
| Opus 5 | $0.00351 | $0.00351 |
| Sonnet 5 | $0.00141 | $0.00141 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
d2-mcp 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 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 — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
The Go entry point lives in main.go, which wires CLI and SSE flags and registers tool handlers from handlers.go. Rendering helpers and external D2 bindings sit under utils.go and d2/tools.go, while build metadata lives in go.mod and Dockerfile. Automation and release workflows are tracked in .github/workflows; keep additional assets near the features that depend on them.
Build, Test, and Development Commands
go build .: compile the stdio/SSE server against the Go version ingo.mod.go run . --sse --port 8080: start the HTTP SSE service; add--image-type svgor--image-type asciiwhile iterating.go run . --transport http --port 8080: start the streamable HTTP transport for MCP clients.go run . --transport stdio --image-type ascii: default stdio transport tuned for LLM-friendly ASCII output.go test ./...: execute all Go unit tests; add-vlocally when stabilising flaky cases.docker build . -t d2-mcp: produce the container image that matches production runners.npx @modelcontextprotocol/inspector ./d2-mcp: inspect tool contracts during MCP client debugging.
Coding Style & Naming Conventions
Use gofmt (tabs, 2-space visual indent) and goimports before submitting patches; the repo's files follow canonical Go formatting. Name handler functions with *Handler (e.g., RenderD2Handler) and keep package-level configuration prefixed with Global. Go packages should stay singular and lowercase (d2, server), and new flags must use descriptive kebab-case names to match existing CLI expectations.
Testing Guidelines
Prefer table-driven tests in *_test.go files co-located with the code under test, using Go's standard testing package. When exercising diagram rendering, inject the context and stub filesystem interactions via temporary directories to keep runs hermetic. Target full coverage for new handlers and utilities and assert error paths on D2 wrappers.
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 · 26 lines · 703 tokens per session scan A 5332d10e0504
d2-mcp AGENTS.md is an instructions file published in the GitHub repository h0rv/d2-mcp (21 stars, last pushed 4mo ago), licensed MIT. It adds 703 tokens to every session, about $0.0035 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 2026-08-30.
Other instructions, from other repositories
ollama CLAUDE.md
Claude Code instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.
gorest AGENTS.md
AGENTS.md instructions for pilinux/gorest, covering agents.md, project overview, build and run commands, build and tidy dependencies.
chatgpt-cli CLAUDE.md
Claude Code instructions for kardolus/chatgpt-cli, covering chatgpt-cli — release runbook, prerequisites, 1. cut the release, 2. publish the github release + binaries and 3. update the homebrew tap.
kessoku AGENTS.md
AGENTS.md instructions for mazrean/kessoku, covering repository guidelines — kessoku, project structure, common commands, build and test.
ketch CLAUDE.md
Claude Code instructions for 1broseidon/ketch, covering ketch, architecture, build & test, output format and output flags (all commands).