Godot AI is a Godot add-on and Model Context Protocol server that connects AI assistants to a live Godot editor. It is used to let coding agents create and modify game scenes, scripts, nodes, and other engine settings through the editor.
Borrowing it
Nothing to install: this file belongs to hi-godot/godot-ai. 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/hi-godot/godot-ai/main/.claude/skills/verification/SKILL.mdgit clone --depth 1 https://github.com/hi-godot/godot-aiWrote 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/hi-godot/godot-ai/verification)<a href="https://agentmods.dev/skills/hi-godot/godot-ai/verification"><img src="https://agentmods.dev/badge/skills/hi-godot/godot-ai/verification/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/hi-godot/godot-ai/verification"><img src="https://agentmods.dev/badge/skills/hi-godot/godot-ai/verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 13 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00050 | $0.00239 |
| Opus 5 | $0.00025 | $0.00120 |
| Sonnet 5 | $0.00010 | $0.00048 |
| Haiku 4.5 | $0.00005 | $0.00024 |
Grade A, and why
verification 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 11d 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
Verifying a Godot AI change
This skill is an adapter. The vendor-neutral source of truth is docs/verification.md.
Read that file and follow it. It covers the full pre-commit gauntlet: lint,
Python tests, GDScript suites via test_run against a running editor, the
live-smoke checklist for new or changed tools, and the self-update smoke
trigger.
Two things worth knowing before you start:
- Python mocks do not catch GDScript bugs, editor API regressions, or
undo/redo breakage. A green
pytestis not a verified change. - Running a scene persists in-memory scene mutations to disk. See
"Live-smoke scene hygiene" in AGENTS.md before smoking
against
main.tscn.
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.
- 11d ago First seen · 23 lines · 50 tokens per session scan A f10835c56251
verification is a skill published in the GitHub repository hi-godot/godot-ai (2,298 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 239 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
smoke-check
Run the critical path smoke test gate before QA hand-off. Executes the automated test suite, verifies core functionality, and produces a PASS/FAIL report. Run after a sprint's stories are implemented and before manual QA begins. A failed smoke check means the build is not ready for QA.
qa-plan
Generate a QA test plan for a sprint or feature. Reads GDDs and story files, classifies stories by test type (Logic/Integration/Visual/UI), and produces a structured test plan covering automated tests required, manual test cases, smoke test scope, and playtest sign-off requirements. Run before sprint begins or when…
automated-smoke-test
Run an automated smoke test using the godot-mcp server. Launches the project, captures debug output, and checks for errors or crashes.
cgs-vertical-slice
Use for vertical slice tasks that validate whether a full game loop can be built at representative quality before production commitment; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-adopt
Use for adopt tasks that inventory existing source, assets, docs, and tests before mapping work into CGS structure; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-architecture-review
Use for architecture review tasks that review architecture for layer violations, scalability risks, engine misuse, testing seams, and production readiness; produce verification evidence, changed or proposed files, and handoff boundaries.