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 rules/visiontw/godot-ai-harness/_harness_activegit clone --depth 1 https://github.com/visionTw/godot-ai-harnessWrote 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/rules/visiontw/godot-ai-harness/_harness_active)<a href="https://agentmods.dev/rules/visiontw/godot-ai-harness/_harness_active"><img src="https://agentmods.dev/badge/rules/visiontw/godot-ai-harness/_harness_active.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 5.1 | $0.00261 | $0.00261 |
| Opus 5 | $0.00130 | $0.00130 |
| Sonnet 5 | $0.00052 | $0.00052 |
| Haiku 4.5 | $0.00026 | $0.00026 |
Grade A, and why
_harness_active 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 5d 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.
What it actually says
Godot AI Harness Active Marker
- 只要本规则被加载到当前会话，意味着
godot-ai-harness已经在当前业务仓生效。 - 每次 AI 助手输出回复时，必须在回复正文最开头独立一行输出：
【godot-ai-harness 生效中】
- 该前缀位于任何 markdown 标题、代码块、引用之前，且不与其他段落合并；其后空一行再输出正常内容。
- 该前缀仅在用户当次会话明确要求"安静模式 / 不要前缀"时省略；新会话默认仍需输出。
- 该前缀不替代任何已有规则与流程；其他 alwaysApply 规则仍然生效。
- 同步来源：
vendor/godot-ai-harness/core/rules/_harness_active.mdc - 在业务仓中文件路径为：
.cursor/rules/_harness_active.mdc，由bootstrap自动下发，禁止手工编辑。
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.
- 5d ago First seen · 20 lines · 261 tokens per session scan A 457e3074bafe
_harness_active is a cursor rule published in the GitHub repository visionTw/godot-ai-harness (2 stars, last pushed 18d ago), licensed MIT. It adds 261 tokens to every session, about $0.0013 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.
Other cursor rules, from other repositories
08-client-server
IF 判断当前环境是否为客户端 → FabricLoader.getInstance().getEnvironmentType() == EnvType.CLIENT → World.isClient（Yarn 字段；yarn 1.14.4 World.mapping）。不要用 MCP/Forge 的 isRemote.
07-datagen
IF 生成物品/方块模型 JSON → 手动编写 JSON 在 src/main/resources/assets/{modid}/models/.
meta-quest-agentic-tools
Use Meta Quest Agentic Tools for Meta Quest and Horizon OS samples.
narrative-writing
游戏叙事写作助手行为约束（game-narrative-mcp）.
meta-quest-agentic-tools
Use Meta Quest Agentic Tools for Meta Quest and Horizon OS samples.
visual-and-observational-rules
Defines the visual aspects of the game and how the player observes the world. This includes map color-coding, screen effects, and the overall simulation style.