air-jam: Instructions file for Claude Code

CLAUDE.md

air-jam CLAUDE.md is an instructions file for Claude Code from vucinatim/air-jam. It costs 388 tokens per session, scanned A, original, MIT.

A set of project instructions for developing and testing Air Jam games, including how to start the local server and prove that gameplay works.

In plain words
What is it for?
Use it when changing Air Jam gameplay or preview controls, checking visible game actions, or starting and resetting the local development environment.
Why use it?
It gives coding agents consistent project-specific rules and helps avoid stale local state, broken previews, and unreliable input tests.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is vucinatim/air-jam's own configuration. It tells Claude Code how to work on air-jam itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything air-jam configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vucinatim/air-jam. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vucinatim/air-jam/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/vucinatim/air-jam

Made for: Claude Code.

Wrote 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.

agentmods badge for air-jam CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vucinatim/air-jam/claude-md/github.svg)](https://agentmods.dev/instructions/vucinatim/air-jam/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/vucinatim/air-jam/claude-md"><img src="https://agentmods.dev/badge/instructions/vucinatim/air-jam/claude-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.

agentmods 80×15 button for air-jam CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/vucinatim/air-jam/claude-md"><img src="https://agentmods.dev/badge/instructions/vucinatim/air-jam/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 388 This file is loaded in full into every session.
When invoked 388 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00388 $0.00388
Opus 5 $0.00194 $0.00194
Sonnet 5 $0.00078 $0.00078
Haiku 4.5 $0.00039 $0.00039

Measured 8d ago against content hash 4b5608f8333a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

air-jam CLAUDE.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 8d 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.

CLAUDE.md · 49 lines

What it actually says

Claude Workflow Notes

Use the same Air Jam development path as every other agent.

Local Launch

Start local development with:

pnpm run dev

Do not use raw vite for normal Air Jam work. It skips the local Air Jam server.

Do not create or prefer a separate preview-specific dev command. If local runtime state looks stale, use Air Jam status/log/reset tooling before debugging gameplay code:

pnpm run status
pnpm run reset:local
pnpm exec air-jam-server logs --view=signal

After editing host-only runtime refs, physics loops, or useHostActionListener side effects, hard refresh the host or run pnpm run reset:local if actions appear duplicated or rendered state no longer matches replicated state.

Preview Controllers

Use visible preview controllers for UI smoke proof:

  1. click buttons with real browser clicks
  2. drag controls with real browser drag/release gestures
  3. verify that the controller visually connects and can trigger at least one visible action

Do not synthesize pointer events into controller iframes from parent-page eval. That path is brittle around iframe boundaries, pointer capture, and React event timing.

Gameplay Proof

Use the game-owned agent contract for reliable gameplay assertions:

  1. airjam.open_game_session
  2. airjam.read_game_session
  3. airjam.invoke_game_session_action
  4. airjam.close_game_session

Use semantic actions for gameplay mechanics, physics outcomes, scoring, reset, and state assertions. Preview controllers are for visible UI smoke proof, not the primary automation lane.

Game Authoring Rule

Multiplayer games should be controllable from controllers. If a game has a start, ready, reset, or similar primary flow, expose it through controller UI and semantic agent actions. The host screen should not be the only place where play begins.

Changes

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.

  1. 8d ago First seen · 49 lines · 388 tokens per session scan A 4b5608f8333a

Subscribe to this mod's changes

air-jam CLAUDE.md is an instructions file published in the GitHub repository vucinatim/air-jam (6 stars, last pushed today), licensed MIT. It adds 388 tokens to every session, about $0.0019 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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens