Borrowing it
Nothing to install: this file belongs to theisegoria/game-development-studio. 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/theisegoria/game-development-studio/main/CLAUDE.mdgit clone --depth 1 https://github.com/theisegoria/game-development-studioWrote 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/theisegoria/game-development-studio/claude-md)<a href="https://agentmods.dev/instructions/theisegoria/game-development-studio/claude-md"><img src="https://agentmods.dev/badge/instructions/theisegoria/game-development-studio/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.
<a href="https://agentmods.dev/instructions/theisegoria/game-development-studio/claude-md"><img src="https://agentmods.dev/badge/instructions/theisegoria/game-development-studio/claude-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 | $0.01051 | $0.01051 |
| Opus 5.5 | $0.00420 | $0.00420 |
| Sonnet 5.5 | $0.00210 | $0.00210 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
game-development-studio 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 18d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in this repository
These are the conventions the code actually enforces. Every one of them was tribal knowledge encoded only in review comments until now, and several of them were learned by shipping the bug.
stdout is the protocol
game-dev --json emits exactly one game_dev.result.v1 object; --jsonl
emits game_dev.event.v1 lines; the MCP server emits JSON-RPC. A single stray
console.log corrupts every caller. ESLint bans console outside
scripts/**/*.mjs; diagnostics go to stderr through the logger. The install
verifier spawns the packed MCP server and fails on any non-JSON-RPC byte.
Every result carries an evidence ceiling
Results include evidenceCeiling and an evidence object whose
impossible-to-claim fields are z.literal(false):
hardwareGpuExecutionProvenByHarnessAlone,
hardwarePerformanceMeasuredByHarnessAlone, humanVisualReviewPerformed.
A new surface must say what it does not prove. Prose summaries describe
statistics — phrase interpretation as "consistent with", never "because".
A software renderer is not a GPU
rendererClass: software makes the harness overwrite the adapter's GPU
and timing claims and record them in refusedAdapterClaims. Do not weaken
this. The default is unknown, because "unknown" is true where "hardware"
is a claim nobody made.
Authority cannot come from an argument the caller writes
No tool schema has an approval input. Spending needs a human-written spend
ceiling plus per-call elicitation; execution needs GAME_DEV_MCP_ALLOW_*
in the launch environment plus per-call elicitation; writes into a user's
project need GAME_DEV_MCP_ALLOW_PROJECT_WRITE=1 plus per-call elicitation.
Every non-acceptance path fails closed, and the tests assert the provider was
never contacted and nothing was written. Every gated write has a free
plan_* twin. The environment check lives in the handler, because
game-dev tool call reaches the same handler.
Plan, then confirm — and where the line actually is
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.
- 18d ago First seen · 101 lines · 1,051 tokens per session scan A 9269215cd28a
game-development-studio CLAUDE.md is an instructions file published in the GitHub repository theisegoria/game-development-studio (11 stars, last pushed 7d ago), licensed MIT. It adds 1,051 tokens to every session, about $0.0042 per session on Opus 5.5. 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 2026-10-02.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.