Borrowing it
Nothing to install: this file belongs to frabcd/codex-ai-game-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/frabcd/codex-ai-game-studio/main/AGENTS.mdgit clone --depth 1 https://github.com/frabcd/codex-ai-game-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/frabcd/codex-ai-game-studio/agents-md)<a href="https://agentmods.dev/instructions/frabcd/codex-ai-game-studio/agents-md"><img src="https://agentmods.dev/badge/instructions/frabcd/codex-ai-game-studio/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/frabcd/codex-ai-game-studio/agents-md"><img src="https://agentmods.dev/badge/instructions/frabcd/codex-ai-game-studio/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 | $0.00340 | $0.00340 |
| Opus 5.5 | $0.00136 | $0.00136 |
| Sonnet 5.5 | $0.00068 | $0.00068 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
codex-ai-game-studio AGENTS.md scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Use tokenized argument arrays and resolved, bounded paths for executable actions. No curl-pipe-shell, floating executable dependency, broad recursive deletion, or hidden host-application control. What it actually says
Codex AI Game Studio contributor instructions
These instructions apply to the whole repository.
- Preserve the safety contract: read-only detection, one exact plan, explicit full-digest confirmation, scoped apply, validation, and rollback. Never combine plan and mutation.
- Keep the universal core usable offline and free of required MCP servers, hosted backends, external downloads, or non-standard Python dependencies.
- Treat catalog entries as untrusted metadata. Never clone, install, import, or execute a catalog repository during validation.
- Keep stable curation separate from volatile GitHub metadata. Never infer a license or platform claim from popularity.
- Store credential environment-variable names only. Tests and fixtures must contain no usable secret values.
- Use tokenized argument arrays and resolved, bounded paths for executable actions. No curl-pipe-shell, floating executable dependency, broad recursive deletion, or hidden host-application control.
- Preserve exact release counts: 73 source skills + 12 new skills, 49 roles, 12 hook behaviors, 11 rules, 40 upstream templates, and 163 catalog records.
- Skill frontmatter contains only
nameanddescription; every skill includesagents/openai.yaml. Setup, install, engine-control, refresh, and destructive enhancement skills disable implicit invocation. - Hooks consume official JSON on stdin, emit bounded/redacted JSON, use
PLUGIN_ROOT/PLUGIN_DATA, providecommandWindows, and remain trust-gated. - Run the relevant standard-library unit tests and validators. Tests must use temporary directories and mocked editors/MCP servers.
- Update documentation, provenance/attribution, schemas, tests, and
CHANGELOG.mdwhen a public contract 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.
- 2mo ago First seen · 16 lines · 340 tokens per session scan A cb787f62e402
codex-ai-game-studio AGENTS.md is an instructions file published in the GitHub repository frabcd/codex-ai-game-studio (22 stars, last pushed 12d ago), licensed MIT. It adds 340 tokens to every session, about $0.0014 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
codex-ai-game-studio AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| codex-ai-game-studio AGENTS.mdfrabcd/codex-ai-game-studio | Instructions file | 22 | 12d ago | MIT | A | 340 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |