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/satriotsubasa/powerplatform-core/code-appsnpx skills add satriotsubasa/PowerPlatform-Core --skill code-appsgit clone --depth 1 https://github.com/satriotsubasa/PowerPlatform-CoreWhat 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 | $0.00203 | $0.01560 |
| Opus 5 | $0.00102 | $0.00780 |
| Sonnet 5 | $0.00041 | $0.00312 |
| Haiku 4.5 | $0.00020 | $0.00156 |
Grade A, and why
code-apps 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 2d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Power Apps Code Apps
Power Apps Code Apps is the code-first SPA hosting model: a standard web app (React/Vue/TS, built with Vite) that imports the @microsoft/power-apps client library and is published into a Power Platform environment, where the platform handles Entra authentication, DLP, sharing, and Conditional Access. It is distinct from PCF (components inside model-driven forms) and Canvas apps (built in maker studio). Keep the app source-controlled, build before every push, and treat power.config.json as the bridge between the local project and the target environment.
When to use this
- Scaffold a new code app from the Microsoft Vite template and initialize it against an environment.
- Add Dataverse (or connector) data sources and use the generated typed services for CRUD.
- Run the app locally, build it, and push it to a Power Platform environment.
- Work in a repo that uses the multi-app
CodeApp/folder pattern (several code apps side by side). - Plan ALM promotion (Dev → Test → Prod) via solutions, pipelines, and connection references.
For a control embedded inside a model-driven form, use pcf-and-web-resources. For Dataverse schema or data operations behind the app, use dataverse-schema and data-operations.
Helpers
Helpers live in the plugin's scripts/ directory at the plugin root, not inside this skill folder. Resolve the plugin root and invoke them:
- Claude Code:
python "$CLAUDE_PLUGIN_ROOT/scripts/push_code_app.py" --help - Codex:
python "$CODEX_PLUGIN_ROOT/scripts/push_code_app.py" --help(also exposed as$PLUGIN_ROOT) - Standalone / unsure: the
scripts/folder sits beside this skill bundle; invoke by its path within the install.
| Helper | Use it to |
|---|---|
push_code_app.py |
Build (npm run build) and push a code app. Defaults to the npm CLI (npx power-apps push); pass --cli pac for legacy pac code push and --solution-name <unique> to target a specific solution. Use --path <dir> to point at one app, --all to push every app under a CodeApp/ folder in sequence, --dry-run to preview, and --skip-build only when pushing already-compiled output. |
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.
- 2d ago First seen · 66 lines · 203 tokens per session scan A 9e6501bc85f7
code-apps is a skill published in the GitHub repository satriotsubasa/PowerPlatform-Core (17 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 203 tokens to every session and 1,560 once invoked, about $0.0010 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.