Borrowing it
Nothing to install: this file belongs to tech-leads-club/nj-mmo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tech-leads-club/nj-mmo/master/AGENTS.mdgit clone --depth 1 https://github.com/tech-leads-club/nj-mmoWrote 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/tech-leads-club/nj-mmo/agents-md)<a href="https://agentmods.dev/instructions/tech-leads-club/nj-mmo/agents-md"><img src="https://agentmods.dev/badge/instructions/tech-leads-club/nj-mmo/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/tech-leads-club/nj-mmo/agents-md"><img src="https://agentmods.dev/badge/instructions/tech-leads-club/nj-mmo/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01182 | $0.01182 |
| Opus 5 | $0.00591 | $0.00591 |
| Sonnet 5 | $0.00236 | $0.00236 |
| Haiku 4.5 | $0.00118 | $0.00118 |
Grade A, and why
nj-mmo 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 10d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents working in this repository.
What this project is
A browser-playable, low-poly 3D multiplayer MVP of an MMORPG inspired by
L2 — a Talking Island vertical slice. Authoritative Colyseus server,
Three.js client, Nx monorepo (server/ + client/), SQLite first.
L2J_Mobius Classic (~/Dev/L2J_Mobius/L2J_Mobius_Classic_1.0) is a
reference only: parse its open-source XML data to seed our own DB, and translate combat and game mechanics rules from its .java into TypeScript, don't reinvent the wheel, copy and adapt. Never a dependency, never the real L2 protocol.
How we work
Features are built with the spec-driven-execution skill: a Planner,
Implementer, and Verifier sub-agent on top of tlc-spec-driven. Read that
skill before starting any phase or feature.
Testing principles (high level)
These are the rules that govern every test in this repo. Details and tooling versions live with each project; this is the contract.
- Server authority is the test boundary. All game-outcome logic (damage, XP, drops, position, cooldowns, peace zone) is tested on the server. The client is never trusted and never the source of truth in a test.
- Tests derive from spec acceptance criteria. A test asserts a spec-defined outcome. It never mirrors the implementation, and we never weaken or skip a test to make it pass. The test runner decides "done".
- Three test layers — pick the cheapest one that proves the criterion:
- Unit (server + client) — formulas, curves, rules, DOM/hook mapping. The bulk of our tests.
- Room integration (
@colyseus/testing) — join/leave, intent validation, state broadcast, persistence/reconnect. Proves "no client trust" without a browser. - Seed/data — the L2J XML → SQLite seed produced the expected Classic values (mobs, NPCs, skill, XP curve).
- WebGL is not directly testable in Vitest. Assert HUD/DOM in client unit
tests, and assert logical game state through
window.__GAME_STATE__andwireRoomtests. Do not anchor correctness on pixel screenshots in the test gate. - Determinism. Anything random (drop chance, damage variance) runs through an injected seeded RNG so tests and the Verifier's fault-injection are reliable.
- Independent verification. After implementation, a fresh Verifier (author ≠ verifier) re-checks against the spec and injects behavior-level faults to confirm the tests actually catch regressions.
- Run only what changed. Use
nx affectedand Nx caching so the gate is fast every time; never disable the cache to force a pass. - Tests are the source of confidence — keep them HIGH QUALITY and FAST. The test suite is what lets agents (and humans) trust a change without re-reading everything. Treat tests as first-class code: clear, deterministic, isolated, and quick. Fast feedback is a hard requirement, not a nice-to-have — agents stall and burn cycles waiting on slow suites, which is a real failure mode here.
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.
- 10d ago First seen · 88 lines · 1,182 tokens per session scan A 4b9f9239eb49
nj-mmo AGENTS.md is an instructions file published in the GitHub repository tech-leads-club/nj-mmo (23 stars, last pushed 2mo ago), licensed MIT. It adds 1,182 tokens to every session, about $0.0059 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.