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/noctree/unity-manual-mcp/agents-mdgit clone --depth 1 https://github.com/Noctree/unity-manual-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/noctree/unity-manual-mcp/agents-md)<a href="https://agentmods.dev/instructions/noctree/unity-manual-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/noctree/unity-manual-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 | $0.01249 | $0.01249 |
| Opus 5 | $0.00624 | $0.00624 |
| Sonnet 5 | $0.00250 | $0.00250 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
unity-manual-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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for agents (and humans) working in this repo.
What this is
A local stdio MCP server that serves a local Unity documentation install —
the en folder from a Unity editor's Data\Documentation — as MCP tools. Two
content trees:
Manual/— how-to articles, organized in chapters (~3.5k pages)ScriptReference/— full scripting API reference (~42k pages)
It extracts article text (Mozilla-Readability-style: boilerplate stripped, code examples preserved) and keeps a SQLite full-text index in the OS temp dir so repeated starts are instant.
Layout
core.py— all the logic, no MCP knowledge: docs-root resolution, HTML extraction,IndexStore(SQLite index build/cache/search), and the cache manifest (CACHE_ROOT,manifest.json, stale/orphaned helpers). Depends only on beautifulsoup4 + lxml.server.py— thin FastMCP stdio wrapper: the 4 read-only tools, the argparse CLI (--selftest,--rebuild,--prune), and the_selftestrunner.mcp = FastMCP(...)is at module level;main()sets the global_storebeforemcp.run(transport="stdio").pyproject.toml+uv.lock— uv project ([tool.uv] package = false; no build step). Deps:fastmcp>=3,<4,beautifulsoup4,lxml;requires-python = ">=3.10".
Keep the split: anything that can run without MCP belongs in core.py.
server.py should stay a thin wrapper.
Running
It's a uv project: .venv is the env, managed by uv sync / uv run.
# one-time index build + sample queries, then exit (no server); ~12 min on a fresh cache
uv run server.py --selftest "C:\Program Files\Unity\Hub\Editor\<ver>\Editor\Data\Documentation\en"
# the MCP server itself (stdio; MCP clients spawn this via `uv run --directory <repo> server.py`)
uv run server.py "C:\...\Editor\Data\Documentation\en"
# drop stale manifest entries (db file missing) and exit
uv run server.py --prune
The docs path may be the en folder, or a wrapper (Documentation or
Editor\Data) — core.resolve_docs_root auto-discovers the en folder. It can
also come from the UNITY_DOCS_PATH env var.
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 · 100 lines · 1,249 tokens per session scan A a5eb6967ec90
unity-manual-mcp AGENTS.md is an instructions file published in the GitHub repository Noctree/unity-manual-mcp (0 stars, last pushed 18d ago), licensed MIT. It adds 1,249 tokens to every session, about $0.0062 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
GameDesignOS AGENTS.md
Instructions for DY-2026/GameDesignOS, covering gamedesignos agent 入口, 默认接法, agent 执行规则, 什么时候用整个项目 and 每个 skill 单独怎么用.
claudemon CLAUDE.md
Instructions for zamarrowski/claudemon, covering ai agent guidelines, project shape, general guidelines, general rules and guards & defensive code.
unity-code-style-guide AGENTS.md
Instructions for krogh-jacobsen/unity-code-style-guide, covering agents.md — unity 6 c, project setup — edit this block, never do these — they corrupt the project, deprecated in unity 6 and if you read nothing else.
codex-game-studio AGENTS.md
AGENTS.md instructions for merlinhu1/codex-game-studio, covering codex game studio template, project goal, engine, commands and context bootstrap.
game-and-watch-retro-go-sd CLAUDE.md
Claude Code instructions for sylverb/game-and-watch-retro-go-sd, covering claude.md, what this project is, build / flash workflow, architecture and three storage tiers, one elf.
nes-php-glfw copilot-instructions.md
Instructions for oliverearl/nes-php-glfw, covering github copilot development guidelines for nes emulator, agent document source of truth, project overview, code style & standards and documentation.