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 skills add jxoesneon/Ciel --skill godot-mcpgit clone --depth 1 https://github.com/jxoesneon/CielWrote 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/skills/jxoesneon/ciel/godot-mcp)<a href="https://agentmods.dev/skills/jxoesneon/ciel/godot-mcp"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/godot-mcp/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/skills/jxoesneon/ciel/godot-mcp"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/godot-mcp.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 | $0.00042 | $0.01085 |
| Opus 5 | $0.00021 | $0.00543 |
| Sonnet 5 | $0.00008 | $0.00217 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade A, and why
godot-mcp 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 7d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CIEL ADAPTATION: Godot MCP & Visual Verification
Bridges LLM reasoning with live Godot 4 editor execution via the godot-mcp MCP server. Provides real-time introspection, visual screenshot verification, live GDScript evaluation, and runtime error telemetry. Ciel's runtime safety gates handle execution gating; this skill declares shell/network side effects from the TCP bridge (port 6505) and GDScript execution.
Tool Domains
- Visual Verification:
take_screenshot,focus_editor_viewport_3d— high-res capture of 3D/2D viewports, running scenes, editor windows with artifact auto-save. - Live Editor Bridge:
get_editor_selection,set_editor_selection,get_active_script_editor,execute_gdscript— introspection, node selection, camera framing, live GDScript eval with UndoRedo. - Debugger Telemetry:
get_debugger_errors,clear_debugger_errors,get_debugger_error_counts— runtime error detection, warning audits, break session tracking. - Scene/Node Authoring:
add_node,modify_node_properties,delete_node,reparent_node,instantiate_scene— programmatic scene tree construction. - Shaders & Audio:
create_shader_material,set_shader_parameter,configure_audio_bus,create_audio_stream_player— material overrides, uniform binding, audio bus routing.
Screenshot Target Modes
viewport_3d: Active 3D editor viewport (frame target viafocus_editor_viewport_3dfirst).viewport_2d: 2D scene canvas (CanvasLayer UI, Control hierarchy, HUDs).main_screen/editor: Full editor interface (docks, scene tree, inspector).scene+scene_path: Headless/offscreenSubViewportrender of any.tscn— no editor focus required.output_path: Direct disk write (e.g.<artifactDir>/screenshots/view.png); returns markdown image link.- Options:
format(png/jpg/webp),max_width/max_height(Lanczos downscale),quality(0.0–1.0).
Live Script Execution (execute_gdscript)
- Instantiates a clean
@toolGDScriptobject viascript.new(). - Runs synchronously on the Godot editor thread with full access to
EditorInterface,ClassDB,ProjectSettings,RenderingServer. - Use for: querying live node properties, inspecting singleton states, one-shot verification routines.
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.
- 7d ago First seen · 67 lines · 42 tokens per session scan A e37dbbc0a24e
godot-mcp is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,085 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
swallowtail
Use the complete Godot development loop from the swallowtail CLI: discover the live engine API, build and edit in the open editor, run and play the game, observe state, debug failures, fix them in place, and verify the result. Use when the task involves creating or modifying a Godot project, testing game behavior…
dialogue-content-pipeline
Manage dialogue and text content so it remains editable, implementable, localizable, and testable.
cgs-bugfix
Use for bugfix tasks that fix a bounded bug with reproduction evidence, minimal change, regression coverage, and handoff notes; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-content-audit
Use for content audit tasks that audit content coverage, duplication, tone consistency, localization needs, and production completeness; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-help
Use for help tasks that summarize available CGS workflows, next phase options, required artifacts, and safe commands; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-standards-prototype-code
Use for prototype code standards: review target files, apply Codex-native boundaries, produce violations, fixes, verification evidence, and handoff notes.