Borrowing it
Nothing to install: this file belongs to TomasLucasUTN/godot-mcp-bridge. 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/TomasLucasUTN/godot-mcp-bridge/main/CLAUDE.mdgit clone --depth 1 https://github.com/TomasLucasUTN/godot-mcp-bridgeWrote 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/tomaslucasutn/godot-mcp-bridge/claude-md)<a href="https://agentmods.dev/instructions/tomaslucasutn/godot-mcp-bridge/claude-md"><img src="https://agentmods.dev/badge/instructions/tomaslucasutn/godot-mcp-bridge/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/tomaslucasutn/godot-mcp-bridge/claude-md"><img src="https://agentmods.dev/badge/instructions/tomaslucasutn/godot-mcp-bridge/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 | $0.01878 | $0.01878 |
| Opus 5 | $0.00939 | $0.00939 |
| Sonnet 5 | $0.00376 | $0.00376 |
| Haiku 4.5 | $0.00188 | $0.00188 |
Grade A, and why
godot-mcp-bridge 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 6d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
godot-mcp-bridge — project guide
Godot 4 MCP server: a GDScript editor addon (addons/godot_mcp/) talking over a
WebSocket (port 6505) to a TypeScript MCP server (mcp-server/). 231 tools.
Architecture is the converged standard for the space (Node stdio ↔ WS ↔ editor plugin).
Two rules that keep the codebase healthy (apply these first)
Extend SceneToolBase for scene work. Every tool node that reads or mutates
scenes extends SceneToolBase (tools/scene_tool_base.gd) and inherits the shared
helpers: _ensure_res_path, _load_scene, _instantiate_packed_scene_for_edit,
_save_scene, _find_node, _refresh_and_reload, _edited_root_if_open,
_get_undo_redo, _acquire_scene, _finish_scene_edit, _discard_scene,
_set_node_properties. Fix any shared-helper bug in the base, in one place. (These
were once copy-pasted across ~12 files and drifted into 3 divergent _load_scene
versions — extending the base keeps that from returning.)
Edit the live tree when the scene is open. A mutating tool checks whether its target scene is the one open in the editor and, if so, edits the LIVE tree so unsaved edits survive. Two supported patterns:
- Structural ops (
scene_tools.gd):_edited_root_if_open+EditorUndoRedoManager(undoable). - Everything else:
_acquire_scene(path)→ mutateroot→_finish_scene_edit(root, path, is_live), using_discard_scene(root, is_live)on every error path. A rawroot.queue_free()on the live root would crash the editor, so_discard_sceneguards it (no-op when live). The live path marks the scene dirty; closed scenes save to disk as before.
Adding or changing a tool
Most tools run inside Godot and are wired in three places — the tool stays dark until all three exist:
- GDScript handler in
addons/godot_mcp/tools/<area>_tools.gd(editor) oraddons/godot_mcp/runtime/mcp_runtime.gd(in-game runtime tools). - Dispatch entry in
addons/godot_mcp/tool_executor.gd(&"name": [_x_tools, &"fn"]). - JSON schema +
annotationsinmcp-server/src/tools/<area>-tools.ts.
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.
- 6d ago Changed 018f45c20462
- 11d ago First seen · 119 lines · 1,878 tokens per session scan A 9b79b15db35a
godot-mcp-bridge CLAUDE.md is an instructions file published in the GitHub repository TomasLucasUTN/godot-mcp-bridge (5 stars, last pushed 6d ago), licensed MIT. It adds 1,878 tokens to every session, about $0.0094 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 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.
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.
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).
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.
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 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).