Agent skill

Godot Agent Vision

by thedivergentai in thedivergentai/GD-Agentic-Skills

Agentic eyes for Godot work: cross-platform screenshot CLI (asset/region/window/screen) to budgeted WebP, TEMP editor viewport bridge under .gdskills/, and Taste Receptor Atlas v2 (~237…

LGPL-3.0Auto-check passedGame Development

Install Godot Agent Vision

skills CLI
$ npx skills add thedivergentai/GD-Agentic-Skills --skill godot-agent-vision -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install thedivergentai/GD-Agentic-Skills godot-agent-vision --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/thedivergentai/GD-Agentic-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/godot-agent-vision .claude/skills/godot-agent-vision && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
godot-agent-vision
GitHub stars
821
Token cost
~3.5k tokens
SKILL.md length
1,141 words
Files
26 (incl. scripts, references)
Skills in repo
98
Repo updated
First seen
Licence
LGPL-3.0

At a glance

Agentic eyes for Godot work: cross-platform screenshot CLI (asset/region/window/screen) to budgeted WebP, TEMP editor viewport bridge under .gdskills/, and Taste Receptor Atlas v2 (~237…

  • Works in 6 steps: Files on disk? → asset (± sheet) → Read… → Known window? → window (else region) →… → Editor viewport fidelity? → editor →… → …
  • Agents must see UI
  • SKILL.md covers NEVER Do, When to use, Setup (agent host) and Available Scripts, plus 6 more sections
  • Runs Python scripts from its folder

What it does

Godot Agent Vision is an agent skill from thedivergentai/GD-Agentic-Skills. Agentic eyes for Godot work: cross-platform screenshot CLI (asset/region/window/screen) to budgeted WebP, TEMP editor viewport bridge under .gdskills/, and Taste Receptor Atlas v2 (~237 micro-receptors × 0–2: hierarchy, contrast, typography×41, affordance, space, color, icon, composition, light/FX, motion-tells, anti-slop, originality, identity). Use when agents must see UI, assets, or the editor — not for in-game screenshot Autoloads. Keywords: agent vision, screenshot, WebP, visual QA, taste receptors…

Its SKILL.md is about 3.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 27 other files, including scripts and reference files (for example `references/anti-slop-sight.md`, `references/capture-modes.md` and `references/color-icon-receptors.md`).

It sits in Game Development, covering Game development, Humanizing AI text and Typography. It works with Godot. The repository describes itself as: The official "Long-Term Memory" for Godot 4.7+ AI Agents. A high-density library of 99 expert skills and 27 genre blueprints, providing audited, strictly typed GDScript patterns… The licence is LGPL-3.0.

When your agent uses it

  • Agents must see UI
  • The editor — not for in-game screenshot Autoloads

Example prompts

  • “/godot-agent-vision”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Files on disk? → asset (± sheet) → Read → score COLOR/ICON/ORIG/ID/SLOP (+ TYPE if labels) → fixes.
  2. Known window? → window (else region) → Read → score all applicable atlas families → fixes.
  3. Editor viewport fidelity? → editor → teardown → score → fixes.
  4. Else screen (last resort).
  5. TYPE/CTRST illegible at 512? → --detail or text crop → re-score those receptors.
  6. MOT/hit-peak ambiguous? → 2–8 frame sequence → re-score MOT/LIGHT hit receptors.

What it can do on your machine

Read from SKILL.md and the folder at commit 4c4d0ff. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (Python, from the files we listed), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • docs.godotengine.org

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Godot Agent Vision loads about 3.5k tokens when it runs, and up to ~23k if it reads all its reference files. Until then it costs about 148 tokens; SKILL.md has 1,141 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~148
When it runs · the whole SKILL.md, loaded when a task matches
~3.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~23k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from thedivergentai/GD-Agentic-Skills at commit 4c4d0ff, republished under its LGPL-3.0 licence (© thedivergentai). 1,141 words, ~3,537 tokens.

Download SKILL.mdSave it as .claude/skills/godot-agent-vision/SKILL.md (or your agent's skills folder). This skill also uses 25 other files; get the full folder from GitHub.
name
godot-agent-vision
description
Agentic eyes for Godot work: cross-platform screenshot CLI (asset/region/window/screen) to budgeted WebP, TEMP editor viewport bridge under .gdskills/, and Taste Receptor Atlas v2 (~237 micro-receptors × 0–2: hierarchy, contrast, typography×41, affordance, space, color, icon, composition, light/FX, motion-tells, anti-slop, originality, identity). Use when agents must see UI, assets, or the editor — not for in-game screenshot Autoloads. Keywords: agent vision, screenshot, WebP, visual QA, taste receptors, typography, UI review, asset sheet, editor viewport, anti-slop.

Godot Agent Vision

Host-side eyes for coding agents building Godot projects: capture → budgeted WebP → scored visual review. Not a game Autoload, not an exportable screenshot API.

Do NOT Load every reference for one task. Load the MANDATORY file for the active mode, then only the rubric axes you are scoring.

NEVER Do

  • NEVER ship the editor bridge as an Autoload or leave addons/_gdskills_agent_vision/ committed — stage, capture, teardown.
  • NEVER leave --keep-bridge on after debugging — skips teardown and dirties the consumer project.
  • NEVER dump uncompressed PNG walls into model context — WebP only; default short-edge 512; --detail only when pixels fail (especially type).
  • NEVER replace scored taste with binary PASS/FAIL or vibes — score applicable rows in taste-receptors.md (Atlas v2, 237 receptors × 0–2); V1–V8 /120 in vision-review-rubric.md is rollup only.
  • NEVER invent taste without loading Family deep refs when those pixels are present: TYPE → typography-sight.md; HIER/CTRST → hier-contrast-receptors.md; SPACE/AFF → space-affordance-receptors.md; COLOR/ICON → color-icon-receptors.md; COMP/LIGHT/MOT → composition-fx-receptors.md; plus anti-slop-sight.md / ui-taste-sight.md.
  • NEVER treat purple-gradient / glow-card / cream-serif AI defaults as “good UI” unless the capture owns that identity with legible critical info and type discipline (SLOP-STACK / TYPE-DISPLAY-HUD-SPLIT).
  • NEVER put ornate display faces on ammo/HP/timers — TYPE-DISPLAY-HUD-SPLIT ship blocker; data type is boring on purpose.
  • NEVER promise silent window-by-title on Wayland — region, grim, X11, or editor bridge.
  • NEVER trust black fullscreen BitBlt/mss frames — exclusive fullscreen / some GPU paths return empty; windowed, region, DXGI-only if justified, or editor bridge.
  • NEVER commit .gdskills/vision/** — ensure .gdskills/ is gitignored first.

When to use

NeedModeMANDATORY loads
Asset files / sheetsassetcapture-modes.md, webp-budgets.md, rubric V6–V8 + originality-sight.md
Desktop rectangleregioncapture-modes + budgets + rubric axes in frame
Godot/editor/game windowwindow --titlecapture-modes (OS limits!)
Full monitorscreenlast resort (secret chrome)
Editor 2D/3D pixelseditoreditor-bridge-lifecycle.md

After capture: Read WebP(s) → score Taste Receptor Atlas (not vibes) → zero-list + ordered fixes keyed to receptor IDs. If any TYPE-* / micro-seam ≤1 for illegibility at 512 short-edge, re-capture --detail or text crop before locking.

Setup (agent host)

text
pip install -r skills/godot-agent-vision/requirements-vision.txt
# optional macOS window titles:
# pip install pyobjc-framework-Quartz

Requires a display session. Use repo/project venv Python.

Available Scripts

Do NOT Load every script. Call only what the mode needs.

capture.py

Main CLI: doctor, list-windows, screen, region, window, asset, editor. Prints wrote=, bytes=, budget=short-edge:N|long-edge:N.

webp_encode.py

Default fit short-edge 512; --detail / --max-edge switches to long-edge cap (1568). Never upscales. Soft re-encode if >1MB.

asset_sheet.py

Single asset or ≤2×2 contact sheet with labels; res:// resolution against --project-root.

ensure_gitignore.py

Appends .gdskills/ so vision scratch never stages.

stage_editor_bridge.py

Stages TEMP addon, optional --godot launch, handshake wait, WebP encode, teardown + project.godot plugin strip.

Editor bridge templates

Capture CLI (golden path)

text
python skills/godot-agent-vision/scripts/capture.py doctor
python skills/godot-agent-vision/scripts/capture.py window --project-root . --title Godot
python skills/godot-agent-vision/scripts/capture.py asset --project-root . --paths res://ui/icons --sheet
python skills/godot-agent-vision/scripts/capture.py editor --project-root . --editor-mode 3d --godot "%GODOT_PATH%"
# typography / OCR / dense layout only:
python skills/godot-agent-vision/scripts/capture.py window --project-root . --title Godot --detail

Default out: {project}/.gdskills/vision/YYYYMMDD-HHMMSS-<mode>[-label].webp

MANDATORY platform landmines: capture-modes.md. MANDATORY budgets: webp-budgets.md.

Editor bridge (TEMP)

Stages templates → addons/_gdskills_agent_vision/ → .gdskills/vision/{request,raw,done} → WebP → delete addon + restore enabled=.

MANDATORY: editor-bridge-lifecycle.md. Prefer EditorPlugin over EditorScript (await across RefCounted is unsafe).

Structured review (Taste Receptor Atlas → optional /120)

MANDATORY primary: taste-receptors.md — 237 micro-receptors across 13 families (HIER, CTRST, TYPE×41, AFF, SPACE, COLOR, ICON, COMP, LIGHT, MOT, SLOP, ORIG, ID), each 0/1/2, grade by % of applicable, hard gates. Routing + V-rollup: vision-review-rubric.md.

When scoring…Load
Any reviewMANDATORY taste-receptors.md
TYPE-* / HUD numerals / menusMANDATORY typography-sight.md
HIER-* / CTRST-*hier-contrast-receptors.md
SPACE-* / AFF-*space-affordance-receptors.md
COLOR-* / ICON-*color-icon-receptors.md
COMP-* / LIGHT-* / MOT-*composition-fx-receptors.md
SLOP-* / UI cross-checkanti-slop-sight.md, ui-taste-sight.md
ORIG-*originality-sight.md
ID-*identity-sight.md

Expert Knowledge Delta

Capture / OS
  • Windows: Per-Monitor DPI V2 before geometry; mss before DPI-clobbering imports; monitors[0] virtual union can be negative-origin; longest title match for Godot’s path-in-title windows.
  • Windows black frames: minimized / exclusive fullscreen / GPU-protected content — not “empty UI.” Prefer windowed + region or editor bridge; DXGI is optional weight, not default.
  • macOS: Screen Recording attaches to responsible binary; wallpaper-only = hard fail; screencapture CLI attribution breaks under agents — prefer in-process Quartz/mss.
  • macOS Retina: pick logical points (automation) vs backing pixels (OCR) and do not mix without scale metadata.
  • Linux: Wayland → skip mss; grim on wlroots; no silent title grab; portal paths are interactive.
  • Asset res:// resolves against --project-root; missing paths must error loudly — never invent files.
WebP / context
  • Vision tokens track pixel area; request size tracks codec. Default short-edge 512 for identity/overview/anti-slop; escalate long-edge 1568 only for glyphs, seams, dense full-layout.
  • Contact sheets ≤2×2 with gutters — 3×3+ makes panel text sub-pixel after model downscale.
  • Never upscale tiny icons to fill 512/1568 — wastes tokens without information.
Show full SKILL.md (445 more words)Show less
Editor bridge
  • EditorPlugin (Node) can await RenderingServer.frame_post_draw safely; EditorScript is RefCounted and can free mid-await.
  • Capture: EditorInterface.get_editor_viewport_2d/3d → get_texture().get_image() after ≥1–2 frame waits; set main screen 2D/3D first or texture is stale/empty.
  • Empty get_image() ⇒ missing await or wrong main screen — not proof the GPU is fine.
  • Handshake: write PNG under raw/, then done flag; Python waits for size-stable PNG.
  • Teardown must strip res://addons/_gdskills_agent_vision/plugin.cfg from [editor_plugins] enabled= and delete the addon — underscore name signals private/temp.
  • Control crops: full editor image + get_global_rect → Image.get_region, clamped to bounds.
Sight / taste (why the atlas is heavy)
  • Score receptors, not vibes: hierarchy is composite size×contrast×motion×sat (HIER-WEIGHT-MATH); peripheral HUD must read as shape (HIER-PERIPH-READ); contrast is worst-case on plates (CTRST-GRAD-WORST, CTRST-BODY-45).
  • Agents default to AI UI centroids (purple wash, neon glow cards, cream+serif, Lucide soup). T≥3 without ownership ⇒ SLOP-STACK=0 / overall F.
  • Typography is ship-blocking (41 TYPE receptors): TYPE-DISPLAY-HUD-SPLIT, TYPE-OPSZ-MATCH, TYPE-NUM-TABULAR/TIMER-STABLE, TYPE-GLYPH-INTEGRITY, TYPE-FACE-CAP — display cuts at HUD size and tabular wobble are zeroes, not “style.”
  • Color/icon: 4–6 semantic roles + accent budget ~5–15%; silhouette test on icon sets; CVD shape backup (COLOR-ONLY / ICON-SIL).
  • Composition/FX/motion: power-point vs HUD conflict (COMP-POWER-CONFLICT); bloom/particles must not replace hierarchy or occlude UI; freeze-frames leak shake/tween artifacts (MOT-*) — sequence capture when peak ambiguous.
  • Originality: filter scènes à faire first; fail franchise silhouette/mark matches and stacked construction tells.
  • Identity: palette roles + edge grammar + motif recurrence (2–4) + type pairing + icon grid + HUD↔menu↔key-art DNA — gradient-alone is not a brand.

Decision tree

  1. Files on disk? → asset (± sheet) → Read → score COLOR/ICON/ORIG/ID/SLOP (+ TYPE if labels) → fixes.
  2. Known window? → window (else region) → Read → score all applicable atlas families → fixes.
  3. Editor viewport fidelity? → editor → teardown → score → fixes.
  4. Else screen (last resort).
  5. TYPE/CTRST illegible at 512? → --detail or text crop → re-score those receptors.
  6. MOT/hit-peak ambiguous? → 2–8 frame sequence → re-score MOT/LIGHT hit receptors.

Reference

Progressive disclosure: open Official Documentation only for a specific API; load Related Skills when routing to a peer domain — do not preload the whole lattice.

Official Documentation
Prerequisites
Complements
Downstream / consumers
  • Genre and UI skills that ship screens — route here when agents must see results, not guess.
Master
  • godot-master — Decision matrix row Agent Eyes / Visual QA.

© thedivergentai, LGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 25 other files (scripts, references) in skills/godot-agent-vision of thedivergentai/GD-Agentic-Skills.

  • SKILL.md
  • references/anti-slop-sight.md
  • references/capture-modes.md
  • references/color-icon-receptors.md
  • references/composition-fx-receptors.md
  • references/editor-bridge-lifecycle.md
  • references/hier-contrast-receptors.md
  • references/identity-sight.md
  • references/migration-notes.md
  • references/originality-sight.md
  • references/space-affordance-receptors.md
  • references/taste-receptors.md
  • references/typography-sight.md
  • references/ui-taste-sight.md
  • references/vision-review-rubric.md
  • references/webp-budgets.md
  • requirements-vision.txt
  • scripts/asset_sheet.py
  • scripts/capture.py
  • … and 7 more

Open the folder on GitHubat commit 4c4d0ff

Compare with similar skills

Godot Agent Vision next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Godot Agent Vision compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Godot Agent Vision this skillthedivergentai/GD-Agentic-Skills821—~3.5kAutomated safety check: PassLGPL-3.0
Godogenliangdabiao/Godogen126—~1.5kAutomated safety check: PassMIT
Visual QAvalkor-ai/loom1.2k—~438Automated safety check: PassApache-2.0
Godot Gdscript Patterns925236118/AlphaAgent10310 repos~5kAutomated safety check: PassMIT
2D Map and Scene Generator0x0funky/agent-sprite-forge4.4k—~2.9kAutomated safety check: PassMIT
Godot UI Integrationzimo-xiao-zheng/godot-ui-integration285—~1.5kAutomated safety check: PassMIT

Similar skills

  • Godogen

    liangdabiao/Godogen

    This skill should be used when the user asks to "make a game", "build a game", "generate a game", or wants to generate or update a complete Godot game from a natural language description.

    126 GitHub stars~1.5k tokensUpdated 5 mo ago
    Game DevelopmentAuto-check passed
  • Visual QA

    valkor-ai/loom

    Inspect Godot screenshots or short frame sequences for acceptance issues.

    1.2k GitHub stars~438 tokensUpdated 4 days ago
    Game DevelopmentAuto-check passed
  • Godot Gdscript Patterns

    925236118/AlphaAgent

    Master Godot 4 GDScript patterns including signals, scenes, state machines, and optimization.

    103 GitHub starsUsed in 10 repos~5k tokens
    Game DevelopmentAuto-check passed
  • 2D Map and Scene Generator

    0x0funky/agent-sprite-forge

    Plans and builds 2D game maps and scenes, from tilemaps and parallax backgrounds to HD-2D plates, with collision checks, a playable HTML preview and Tiled, Godot or LDtk export.

    4.4k GitHub stars~2.9k tokensUpdated 4 days ago
    Game DevelopmentAuto-check passed
  • Godot UI Integration

    zimo-xiao-zheng/godot-ui-integration

    Build or revise Godot UI from an approved design, separated art, or a visual reference when scene structure, gameplay binding, and runtime visual verification all matter.

    285 GitHub stars~1.5k tokensUpdated 1 mo ago
    Game DevelopmentAuto-check passed
  • Godot Wechat Minigame Adapter

    godothub/godot-minigame

    Apply the bundled self-contained Godot WeChat Mini Game adapter kit to an official Godot checkout.

    187 GitHub stars~1.5k tokensUpdated 25 days ago
    Game DevelopmentAuto-check passed

More from thedivergentai/GD-Agentic-Skills

All 98 skills in this repo
  • Godot 2D Animation

    thedivergentai/GD-Agentic-Skills

    Expert patterns for 2D animation in Godot using AnimatedSprite2D and skeletal cutout rigs.

    821 GitHub stars~3.6k tokensUpdated 1 mo ago
    Auto-check passed
  • Godot 3D World Building

    thedivergentai/GD-Agentic-Skills

    Expert patterns for 3D level design using GridMap with MeshLibrary, CSG constructive solid geometry, occlusion, and runtime GridMap builders.

    821 GitHub stars~3.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Godot Adapt 2D To 3D

    thedivergentai/GD-Agentic-Skills

    Expert patterns for migrating 2D games to 3D including node type conversions, camera systems (third-person, first-person, orbit), physics layer migration, sprite-to-model art pipeline, and control…

    821 GitHub stars~4.7k tokensUpdated 1 mo ago
    Auto-check passed
  • Godot Adapt 3D To 2D

    thedivergentai/GD-Agentic-Skills

    Expert patterns for simplifying 3D games to 2D including dimension reduction strategies, 2.5D fake-depth, isometric ports, camera flattening, physics conversion, 3D-to-sprite art pipeline, and…

    821 GitHub stars~4.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Godot Animation Tree Mastery

    thedivergentai/GD-Agentic-Skills

    Expert patterns for AnimationTree including StateMachine transitions, BlendSpace2D for directional movement, BlendTree for layered animations, root motion, transition conditions, advance…

    821 GitHub stars~3.6k tokensUpdated 1 mo ago
    Auto-check passed
  • Godot Autoload Architecture

    thedivergentai/GD-Agentic-Skills

    Expert patterns for Godot AutoLoad (singleton) architecture including global state management, scene transitions, signal-based communication, dependency injection, autoload initialization order, and…

    821 GitHub stars~3.4k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Questions about Godot Agent Vision

What does Godot Agent Vision do?

Agentic eyes for Godot work: cross-platform screenshot CLI (asset/region/window/screen) to budgeted WebP, TEMP editor viewport bridge under .gdskills/, and Taste Receptor Atlas v2 (~237…. Godot Agent Vision is an agent skill from thedivergentai/GD-Agentic-Skills.gdskills/, and Taste Receptor Atlas v2 (~237 micro-receptors × 0–2: hierarchy, contrast, typography×41, affordance, space, color, icon, composition, light/FX, motion-tells, anti-slop, originality, identity).

When should I use Godot Agent Vision?

Godot Agent Vision fits situations like: agents must see UI; the editor — not for in-game screenshot Autoloads.

How do I install Godot Agent Vision in Claude Code?

Run `npx skills add thedivergentai/GD-Agentic-Skills --skill godot-agent-vision -a claude-code`. Or copy the skill folder (skills/godot-agent-vision in thedivergentai/GD-Agentic-Skills) into .claude/skills/godot-agent-vision in your project. Claude Code loads it when a task matches its description.

How do I install Godot Agent Vision in Codex?

Run `npx skills add thedivergentai/GD-Agentic-Skills --skill godot-agent-vision -a codex`. Or copy the skill folder (skills/godot-agent-vision in thedivergentai/GD-Agentic-Skills) into .agents/skills/godot-agent-vision in your project. Codex loads it when a task matches its description.

Can I use Godot Agent Vision in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add thedivergentai/GD-Agentic-Skills --skill godot-agent-vision -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/godot-agent-vision, .gemini/skills/godot-agent-vision, .github/skills/godot-agent-vision and .opencode/skills/godot-agent-vision in your project.

What does Godot Agent Vision need to run?

Going by SKILL.md and its folder, Godot Agent Vision needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Godot Agent Vision access the network?

SKILL.md names 1 domain. As links in the text: docs.godotengine.org. This is read from the text; nothing was executed.

Is Godot Agent Vision safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Godot Agent Vision use?

Godot Agent Vision is published under the LGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Godot Agent Vision use?

About 3.5k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 19k tokens, read only when the agent opens those files.

What are the alternatives to Godot Agent Vision?

Skills that share tags, products or a category with Godot Agent Vision: Godogen (liangdabiao/Godogen, 126 stars), Visual QA (valkor-ai/loom, 1.2k stars), Godot Gdscript Patterns (925236118/AlphaAgent, 103 stars) and 2D Map and Scene Generator (0x0funky/agent-sprite-forge, 4.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Godot Agent Vision?

thedivergentai (a GitHub user) maintains it in thedivergentai/GD-Agentic-Skills, which has 821 GitHub stars. The repository holds 98 skills in this directory. The repository was last updated on September 9, 2026.

Source: thedivergentai/GD-Agentic-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.