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/ggoodman/mcp-server-go/agents-mdgit clone --depth 1 https://github.com/ggoodman/mcp-server-goWrote 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/ggoodman/mcp-server-go/agents-md)<a href="https://agentmods.dev/instructions/ggoodman/mcp-server-go/agents-md"><img src="https://agentmods.dev/badge/instructions/ggoodman/mcp-server-go/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 5.1 | $0.00701 | $0.00701 |
| Opus 5 | $0.00351 | $0.00351 |
| Sonnet 5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
mcp-server-go 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 5d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The goal of this project is to provide a drop-in http.Handler for developers to mount to their server and get a horizontally-scalable solution for MCP's streaming HTTP Transport.
Key specs
This library MUST adhere to the following specs.
- MCP Spec:
./specs/mcp.md- We are targeting the streaming http transport. You can find it alone at
./specs/transport.md(it is also contained in./specs/mcp.md).
- We are targeting the streaming http transport. You can find it alone at
- MCP Schema:
./specs/mcp-schema.ts - JSON-RPC Spec:
./specs/json-rpc.html- We do NOT leverage json-rpc batching. It is forbidden in the streaming http transport.
Code style
- Idiomatic go. Use the standard library when possible. Only fall back to top-tier packages when re-implementation would be overly complex or risky.
- Layered approach that supports drop-in scenarios but allows users to peel back the layers and adapt to more complex scenarios.
- Horizontally scalable. JSON-RPC requests, notifications and responses may land on any node and the library must support coordination in such an environment.
- Designed for production users with minimal internal library opinions
- Security is a first-class concern. We take no risks when it comes to cross-user contamination.
- Aim for mutually exclusive and collectively exhaustive capabilities. Avoid having duplicate ways of doing things but make sure everything can be done.
- Give code room to breathe by using newlines and idiomatic formatting. Scanning the code should show white space between logical breaks in intent and structure.
Tool usage
- NEVER run
go buildif a similar outcome can be achieved by using the "Go Please" tool suite. It is the language server and will give faster more easily-understood feedback. - AVOID running
go testif the built-in test runner can achieve the same thing. - NEVER run a shell command when a tool can provide the same outcome.
Discussion style
- Format your content in markdown.
- Wrap tiny bits of code in inline code markup.
- Wrap multi-line bits of code in fenced code blocks and tag the block according to the language therein.
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.
- 5d ago First seen · 45 lines · 701 tokens per session scan A 9ebf738235c4
mcp-server-go AGENTS.md is an instructions file published in the GitHub repository ggoodman/mcp-server-go (3 stars, last pushed 5mo ago), licensed MIT. It adds 701 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 2026-08-31.
Other instructions, from other repositories
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Claude Code instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
flyto-core CLAUDE.md
Claude Code instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.