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/nighthawk42/gbdocs-mcp/agents-mdgit clone --depth 1 https://github.com/Nighthawk42/gbdocs-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/nighthawk42/gbdocs-mcp/agents-md)<a href="https://agentmods.dev/instructions/nighthawk42/gbdocs-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/nighthawk42/gbdocs-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 | $0.01500 | $0.01500 |
| Opus 5 | $0.00750 | $0.00750 |
| Sonnet 5 | $0.00300 | $0.00300 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
gbdocs-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 3d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for coding agents (and humans) working on gbdocs-mcp.
What this project is
An MCP server that turns the Game Boy Pan Docs into
structured, citable lookups for decompilation work. It is a reformatter, not an
author: every fact it returns comes out of the documentation, and every response
carries a source block pointing back at the page and section it came from.
Two rules that override convenience
1. Never fabricate hardware facts
If Pan Docs does not document something, say so. The codebase already does this in several places and new code must follow suit:
decode_value()returns"note": "Pan Docs documents no bitfield layout..."rather than inventing bit meanings, and listsundocumented_bitsseparately.gb_decode_opcodelabels cycle counts and flagssource: "gb-opcodes"because Pan Docs deliberately omits them.lookup_cart_codereturnsmeaning: nullwith"Not a documented value"instead of guessing.
Do not add a lookup table of hardware knowledge you happen to know. Parse it out of the docs, or report the gap.
2. pandocs/ is read-only input
Nothing in src/ writes to the docs. A local clone, if present, wins over the
bundled copy so git pull inside it takes effect with no rebuild.
Architecture
mdparse.py Pan Docs' custom markdown syntax. Ports of the upstream preprocessor.
corpus.py Loads the docs into Page/Section objects; SUMMARY.md -> chapter tree.
render.py Section -> compact text for an LLM to read.
registers.py Register index, bitfield semantics, value decode/encode.
memory.py Address-space regions, I/O ranges, jump vectors.
cartridge.py Header fields and code tables; header byte decoder.
mbc.py Mapper banking ranges and write identification.
opcodes.py SM83 decoder built from the docs, merged with vendored cycles/flags.
search.py BM25 + optional embeddings, fused with RRF.
api.py The Docs facade -- all tool logic lives here.
server.py Thin MCP wrapper: 21 tool definitions and one resource template.
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.
- 3d ago First seen · 135 lines · 1,500 tokens per session scan A 22af3ce0be2d
gbdocs-mcp AGENTS.md is an instructions file published in the GitHub repository Nighthawk42/gbdocs-mcp (0 stars, last pushed 20d ago), licensed MIT. It adds 1,500 tokens to every session, about $0.0075 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
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
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).
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
second-brain AGENTS.md
Instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.