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 smileynet/teach-me --skill godot-validationgit clone --depth 1 https://github.com/smileynet/teach-meWrote 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/smileynet/teach-me/godot-validation)<a href="https://agentmods.dev/skills/smileynet/teach-me/godot-validation"><img src="https://agentmods.dev/badge/skills/smileynet/teach-me/godot-validation/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/smileynet/teach-me/godot-validation"><img src="https://agentmods.dev/badge/skills/smileynet/teach-me/godot-validation.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 | $0.00059 | $0.02532 |
| Opus 5.5 | $0.00024 | $0.01013 |
| Sonnet 5.5 | $0.00012 | $0.00506 |
| Haiku 4.5 | $0.00006 | $0.00253 |
Grade A, and why
godot-validation 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 1mo 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Godot Visual Validation
Validate lesson shaders by applying them to PBR-textured meshes in test-scene/ and capturing A/B screenshot proof.
Test Scene
- Project:
D:\code\teach-me\test-scene - PBR assets:
test-scene/assets/polyhaven/(Barrel_01, Camera_01, Lantern_01 — 1K textures) - Shaders:
test-scene/shaders/(copied fromlibrary/godot-gamedev/reference/code/) - Screenshot output:
test-scene/.scratch/screenshots/
glTF Import Fix
MCP reimport/scan do NOT trigger Godot's scene importer for glTF files. If .gltf.import shows valid=false:
- Delete the
.gltf.importfiles - Run
godot --headless --editor --import --quit --path test-scene - Restart the editor (quit + relaunch)
- Then
node_createwithscene_pathwill work
Capturing Screenshots to Disk
editor_screenshot returns inline base64 only — cannot save to files. To get files:
- Run the project (
project_run) - Use
game_evalto position camera, toggle shader, and save:
var img = get_viewport().get_texture().get_image()
img.save_png('user://screenshots/filename.png')
Files land at C:/Users/uosmi/AppData/Roaming/Godot/app_userdata/teach-me-shader-test/screenshots/. Copy to test-scene/.scratch/screenshots/ after capture.
Framing Objects (Fill the Frame)
Calculate camera distance from object AABB so it occupies ~80% of viewport:
var half_fov_tan = tan(cam.fov * 0.5 * PI / 180.0)
var dist = largest_aabb_dimension / half_fov_tan
Position camera at target + offset where offset uses 30° elevation/azimuth:
var elev = 30.0 * PI / 180.0
var azim = 30.0 * PI / 180.0
var offset = Vector3(dist * cos(elev) * sin(azim), dist * sin(elev), dist * cos(elev) * cos(azim))
cam.global_position = target + offset
cam.look_at(target)
MCP Reliability (hard rules — validated 2026-08-26)
The godot-ai MCP has three failure modes that cause silent wrong results:
game_evalmutations are for READING, not persisting. Settingrotation_degreesorset_shader_parameteron a running instance is unreliable — changes may not affect the render or reset on the nextproject_run. Symptom: two different "edits" produce pixel-identical captures. Fix: edit the.tscnon disk (persistent, git-tracked), thenproject_runpicks up saved state. Usegame_evalonly to capture the viewport and sample pixels.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +2 lines 0f12e38c80d2
- 1mo ago Changed · +2 lines 95381bffafb1
- 1mo ago First seen · 125 lines · 59 tokens per session scan A baac5f5e83e8
godot-validation is a skill published in the GitHub repository smileynet/teach-me (3 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 2,532 once invoked, about $0.0002 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.
Other skills, from other repositories
deep-student-cloud-sync-e2e
Run real, UI-driven Deep Student cloud sync E2E tests. Use when Codex needs to validate WebDAV/cloud sync, backup, restore, credentials, conflict behavior, multi-device synchronization, or sync regressions through real Tauri UI operations followed by SQLite/WebDAV/log verification.
deep-student-tauri-lab
Manage Deep Student Tauri desktop test instances through the repo-local tauri-lab CLI. Use when Codex needs to create, start, stop, restart, lease, inspect, or clean up one or many Deep Student Tauri app windows for Computer Use testing, parallel subagents, cloud sync simulations, or local E2E debugging.
onboarding-and-teaching
Use when designing, reviewing, or generating the introduction to ANY mechanic in ANY genre — the four-beat teaching pattern (introduce→test→combine→twist), show-don't-tell level design, progressive disclosure and scaffolding, the mechanic dependency graph, FTUE (first-time user experience), early retention funnels…
anki
Anki spaced repetition learning system reference. Covers the science of SRS and SM-2 algorithm, card design principles, optimal deck settings, FSRS scheduler, study workflow, essential add-ons, custom templates, filtered decks, and AnkiConnect API.
soak-test
Soak test protocol for extended play — what to observe and log for slow leaks, fatigue, late-appearing edge cases.
team-polish
Orchestrate the polish team — performance-analyst, technical-artist, sound-designer, qa-tester — to optimize and harden a feature or area.