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 agentmods add skills/python-ide/pythonide-skills/pythonide-appuinpx skills add Python-IDE/pythonide-skills --skill pythonide-appuigit clone --depth 1 https://github.com/Python-IDE/pythonide-skillsWhat 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 | $0.00078 | $0.02109 |
| Opus 5 | $0.00039 | $0.01055 |
| Sonnet 5 | $0.00016 | $0.00422 |
| Haiku 4.5 | $0.00008 | $0.00211 |
Grade A, and why
pythonide-appui 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 yesterday.
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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PythonIDE AppUI
Execution rulebook for native AppUI MiniApps. Pair with pythonide-native whenever the workflow touches iOS permissions, sensors, media capture, networking side effects, or secure storage.
Read Before Coding
- appui quickstart
- AppUI module
- UI patterns
- AppUI schema and appui.pyi for signatures
- llms-full.txt when unsure about exported symbols
- Load
pythonide-nativebefore importing anyphotos,location,permission,notification, etc.
Chinese module pages on pythonide.xin are valid deep references for scenarios and examples.
Workflow
- Confirm AppUI is the right runtime (
pythoniderouter). Do not use AppUI for widgets or frame-loop games. - Choose structure first:
Form,List,TabView,NavigationStack, dashboardScrollView. - Define module-level
appui.StateorReactiveState. - Write named zero-argument callbacks; callbacks mutate state or call native APIs.
- Keep
body()pure: return a view tree only. No permissions, network, storage writes, notifications, timers started, or navigation side effects insidebody(). - End with exactly one
appui.run(body, state=state, presentation=...). - For editable business data, use
storage.get_json(..., default)only for small settings; usedatabasefor queryable records, caches, favorites, history, playlists, or large lists.
Entry Pattern
import appui
state = appui.State(count=0, status="Ready")
def increment():
state.count += 1
state.status = "Updated"
def body():
return appui.NavigationStack(
appui.Form([
appui.Section("Counter", [
appui.LabeledContent("Value", value=str(state.count)),
appui.Button("+1", action=increment).button_style("bordered_prominent"),
], footer=state.status),
]).navigation_title("Counter")
)
appui.run(body, state=state, presentation="fullscreen_with_close")
What ships with it
2 files 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.
- yesterday First seen · 169 lines · 78 tokens per session scan A 51dad44bf7ee
pythonide-appui is a skill published in the GitHub repository Python-IDE/pythonide-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 2,109 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
build-run-debug
Build, run, and debug local macOS apps and desktop executables using shell-first Xcode and Swift workflows. Use when asked to build a Mac app, launch it, diagnose compiler or linker failures, inspect startup problems, or debug desktop-only runtime issues.
macos-swiftpm
Build, run, and test SwiftPM macOS packages and executables. Use when the repo is package-first or has no Xcode project.
firebase-messaging
Use when setting up Firebase Cloud Messaging, managing permissions and tokens, handling background/foreground notification taps, or dispatching messages server-side (HTTP v1).
curate-a-team-library
Use when building a managed team skills library for a real stack. Map work to shelves, browse before curating, write meaningful whyHere notes, and create a starter pack once the first pass is solid.
effective-dart
Use when writing Dart code, reviewing for style, refactoring naming, adding doc comments, structuring imports, or enforcing type annotations.
firebase-ai
Use when setting up firebaseai, generating text/chat with Gemini, streaming AI output, building multimodal prompts, or handling AI errors.