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/francescojr/nobu/agents-mdgit clone --depth 1 https://github.com/francescojr/nobuWrote 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/francescojr/nobu/agents-md)<a href="https://agentmods.dev/instructions/francescojr/nobu/agents-md"><img src="https://agentmods.dev/badge/instructions/francescojr/nobu/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 | $0.02081 | $0.02081 |
| Opus 5 | $0.01040 | $0.01040 |
| Sonnet 5 | $0.00416 | $0.00416 |
| Haiku 4.5 | $0.00208 | $0.00208 |
Grade A, and why
nobu 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — nobu
Instructions for coding agents (Cursor, Claude Code, Kilo Code, etc.). Humans: see README.md. Setup detail: .claude/skills/game-music-producer/SETUP.md.
If this workspace was just cloned: run bootstrap immediately. Do not ask.
Mission
nobu is a game-agnostic MCP server + skill for composing chiptune/retro MIDI and rendering game audio. It ships no game-specific data.
First actions after clone (mandatory, automatic)
Trigger this checklist when: the user says install/setup/use nobu, the repo was just cloned, imports fail, or MCP tools are missing. Do not ask for confirmation.
-
Bootstrap (from repo root):
python scripts/bootstrap.py --no-promptHumans may run
python scripts/bootstrap.pywithout flags for an interactive optional-upgrade menu.This creates
.venv, installs deps, ensures folders, verifies imports, and rewrites project-local.cursor/mcp.json+.mcp.json(Cursor) and.kilo/kilo.jsonc(Kilo) with the venv Python + absolutenobu_mcp.py(all gitignored; templates*.example*stay in git).Integrate into a game project:
python scripts/bootstrap.py --integrate /absolute/path/to/game --no-promptMachine-readable status:
python scripts/bootstrap.py --json --no-promptOptional flags:
python scripts/bootstrap.py --with-render --no-prompt # tinysoundfont (hybrid) python scripts/bootstrap.py --doctor # re-check deps, no pip/menu python scripts/bootstrap.py --smoke --no-prompt # end-to-end chip render proofKilo: bootstrap writes
"timeout": 300000in.kilo/kilo.jsonc. Also set Settings → MCP → nobu → Network Timeout → 5 minutes if render fails with-32001. Prefer MCPrender_chipfor first audio; use shell fallback:python scripts/render_track.py assets/midi/{project}.mid --mode chip --json
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 · 162 lines · 2,081 tokens per session scan A 9e2955f4d885
nobu AGENTS.md is an instructions file published in the GitHub repository francescojr/nobu (0 stars, last pushed 27d ago), licensed MIT. It adds 2,081 tokens to every session, about $0.0104 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 2026-09-01.
Other instructions, from other repositories
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.
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.
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.
base-building-trap-defense-design-agent-skill CLAUDE.md
Instructions for dungnotnull/base-building-trap-defense-design-agent-skill, covering claude.md — skill 250: base-building-trap-defense-design, skill identity, problem this skill solves, harness flow summary and sub-skills.
trident-mcp AGENTS.md
Instructions for mordor-forge/trident-mcp, covering agents.md, what this is, build and test, single-file verification and e2e tests.