Borrowing it
Nothing to install: this file belongs to k0nkupa/godot-mcp. 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/k0nkupa/godot-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/k0nkupa/godot-mcpWrote 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/k0nkupa/godot-mcp/agents-md)<a href="https://agentmods.dev/instructions/k0nkupa/godot-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/k0nkupa/godot-mcp/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/k0nkupa/godot-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/k0nkupa/godot-mcp/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 | $0.00308 | $0.00308 |
| Opus 5.5 | $0.00123 | $0.00123 |
| Sonnet 5.5 | $0.00062 | $0.00062 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade A, and why
godot-mcp 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 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.
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 MCP contributor guide
Start here
- Security boundary:
docs/security/threat-model.md - Wire contract:
docs/protocol/bridge-v1.md - Phase gate:
docs/testing/phase-7.md
Guardrails
- Keep MCP on stdio and bind the Godot bridge only to
127.0.0.1; the addon opens no functional protocol listener. Phase 7 may hold Godot's disabled native-DAP port with an inert loopback guard. - Treat loopback as containment, not authentication. Preserve one-use descriptors, signed envelopes, sequence/deadline checks, project identity, and audit redaction.
- Do not add arbitrary shell, host filesystem, network, method invocation, or GDScript evaluation to normal profiles.
- Default sessions expose exactly six observe-only tools. Runtime adds two tools with explicit
runtime_controlplusruntime; input adds exactly one tool with explicitruntime_controlplusinput. - Use disposable fixture copies for editor, destructive, hostile-input, and E2E work. Do not test mutations directly in a real game checkout.
- Preserve reversible, manifest-verified addon installation and refuse independently changed files.
Validation
Use focused Vitest tests while developing. Before claiming Phase 7 complete, run GODOT_BIN=/opt/homebrew/bin/godot pnpm qa:phase-7, then the Phase 0–1 and Phase 2–6 regression gates. Never claim a skipped check passed.
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 · 21 lines · 308 tokens per session scan A cc91bd9cfd64
godot-mcp AGENTS.md is an instructions file published in the GitHub repository k0nkupa/godot-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 308 tokens to every session, about $0.0012 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 2026-08-31.
godot-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| godot-mcp AGENTS.mdk0nkupa/godot-mcp | Instructions file | 0 | 3mo ago | MIT | A | 308 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | 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 |