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 Python-IDE/pythonide-skills --skill pythonide-scenegit clone --depth 1 https://github.com/Python-IDE/pythonide-skillsWrote 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/python-ide/pythonide-skills/pythonide-scene)<a href="https://agentmods.dev/skills/python-ide/pythonide-skills/pythonide-scene"><img src="https://agentmods.dev/badge/skills/python-ide/pythonide-skills/pythonide-scene/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/python-ide/pythonide-skills/pythonide-scene"><img src="https://agentmods.dev/badge/skills/python-ide/pythonide-skills/pythonide-scene.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 | $0.00063 | $0.00883 |
| Opus 5.5 | $0.00025 | $0.00353 |
| Sonnet 5.5 | $0.00013 | $0.00177 |
| Haiku 4.5 | $0.00006 | $0.00088 |
Grade A, and why
pythonide-scene 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 2mo 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PythonIDE Scene
Execution rulebook for scene and turtle runtimes.
Read Before Coding
- Scene module
- Scene API reference
- scene.pyi
- Turtle module for teaching graphics
Do not generate AppUI or widget code for a scene/game request.
Use When
- Continuous drawing, sprite movement, collisions, physics, touch loops, or shaders
- Existing code imports
sceneand needs repair - Turtle teaching demos
Do Not Use When
- The UI is a form, list, settings screen, or AppUI MiniApp
- The user wants imperative UIKit controls →
pythonide-automation(ui) - Static charts or business apps →
pythonide-appui
Workflow
- Subclass
scene.Scene - Create retained nodes in
setup()afterself.sizeis valid - Per-frame logic in
update(); immediate drawing only indraw() - Touch in
touch_began/touch_moved/touch_ended - End with exactly one
scene.run(MyScene(), ...) - Keep assets optional unless the user provides them
Correct Pattern
import scene
class Demo(scene.Scene):
def setup(self):
self.background_color = "#111827"
self.ball = scene.SpriteNode(
color="#2f80ed",
size=(44, 44),
position=(self.size.w / 2, self.size.h / 2),
parent=self,
)
self.label = scene.LabelNode(
"Tap to move",
font=("Helvetica", 18),
position=(self.size.w / 2, 80),
parent=self,
)
def touch_began(self, touch):
self.ball.run_action(
scene.Action.move_to(touch.location.x, touch.location.y, 0.25)
)
self.label.text = f"{touch.location.x:.0f}, {touch.location.y:.0f}"
scene.run(Demo(), show_fps=True)
Hard Stops
- No AppUI (
Button,VStack,NavigationStack, etc.) inside aScene - No blocking
while Trueanimation loops; useupdate()orAction - No
rect,fill,text, etc. outsidedraw() SpriteNode("red")treats"red"as a texture name — useSpriteNode(color="red", ...)- Do not omit
scene.run(...) image_quad/triangle_stripare not implemented
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.
- 2mo ago First seen · 108 lines · 63 tokens per session scan A c4912d856842
pythonide-scene is a skill published in the GitHub repository Python-IDE/pythonide-skills (8 stars, last pushed 3mo ago), licensed MIT. It adds 63 tokens to every session and 883 once invoked, about $0.0003 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.
pythonide-scene compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pythonide-scenePython-IDE/pythonide-skills | Skill | 8 | 3mo ago | MIT | A | 63 | Claude Code |
| temporal-python-testingwshobson/agents | Skill | 42k | yesterday | MIT | A | 45 | Claude Code |
| pygame-coregamedev-skills/awesome-gamedev-agent-skills | Skill | 6.9k | 10d ago | Apache-2.0 | A | 85 | Claude Code |
| manimgl-best-practicescalesthio/OpenMontage | Skill | 77k | 3d ago | AGPL-3.0 | A | 167 | Claude Code, Codex |
| python-guidelinesfcakyon/claude-codex-settings | Skill | 1.2k | yesterday | Apache-2.0 | A | 42 | Claude Code |
| vibeuekevinpbuckley/VibeUE | Skill | 812 | 2d ago | MIT | A | 82 | Claude Code, Codex |
| prismer-python-debugpyPrismer-AI/PrismerCloud | Skill | 1.4k | 15d ago | MIT | A | 19 | Claude Code, Codex |