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 korchard333/claude-power-platform-community --skill canvas-appsgit clone --depth 1 https://github.com/korchard333/claude-power-platform-communityWrote 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/korchard333/claude-power-platform-community/canvas-apps)<a href="https://agentmods.dev/skills/korchard333/claude-power-platform-community/canvas-apps"><img src="https://agentmods.dev/badge/skills/korchard333/claude-power-platform-community/canvas-apps/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/korchard333/claude-power-platform-community/canvas-apps"><img src="https://agentmods.dev/badge/skills/korchard333/claude-power-platform-community/canvas-apps.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 | $0.00046 | $0.01492 |
| Opus 5.5 | $0.00018 | $0.00597 |
| Sonnet 5.5 | $0.00009 | $0.00298 |
| Haiku 4.5 | $0.00005 | $0.00149 |
Grade A, and why
canvas-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 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Canvas Apps Development
When to Use
Trigger when building, reviewing, or debugging Canvas Apps — low-code Power Apps built with Power Fx formulas, connectors, and drag-and-drop controls for mobile, tablet, and web scenarios.
AI Accuracy Warning
LLMs produce less accurate Power Fx than mainstream languages (JavaScript, C#, Python) due to smaller training datasets. Always verify AI-generated Power Fx formulas — especially complex ones involving delegation, ThisItem/ThisRecord, concurrent collections, or nested If/Switch logic. Use Power Apps Test Engine to validate formulas before promoting to production.
When to Use Canvas Apps vs Alternatives
| Scenario | Best Choice | Why |
|---|---|---|
| Standard Dataverse CRUD + business process | Model-Driven App | Built-in forms, views, business rules |
| Custom pixel-perfect UI + pro-dev team | Code App | Full React/TypeScript control |
| Mobile-first field app | Canvas App | Power Apps mobile, offline, camera, GPS |
| SharePoint list frontend | Canvas App | SharePoint form customization |
| Multi-data-source mashup | Canvas App | 1000+ connectors |
| Quick internal tool / form | Canvas App | Fastest time-to-value |
| Citizen developer / maker | Canvas App | Low-code, no TypeScript needed |
| Complex interactive dashboards | Code App | Better performance, charting libraries |
⚠️ REQUIRED: Load Sub-Files Before Implementation
SKILL.md is a summary only — it is NOT sufficient for implementation.
The detailed content (complete payloads, XML templates, working examples, edge-case handling) lives in sub-files in the same directory as this SKILL.md. Before writing any code, you MUST use read_file on the sub-files relevant to your task:
- Power Fx Fundamentals — data types, core functions (CRUD, navigation, variables), named formulas, UDFs
- Delegation — delegable vs non-delegable functions, limits, warning patterns, workarounds
- Components & Modern Controls — component library, property types, Fluent 2 modern controls, theming
- Screen Patterns & Responsive Design — master-detail, loading pattern, container layout, phone vs tablet
- Offline Capabilities — LoadData/SaveData, connectivity check, offline queue + sync pattern
- Connectors, Data Sources & Integration — connector types, Dataverse/SharePoint patterns, Power Automate integration, environment variables
- Canvas ALM — solution-aware development, source control (pac canvas unpack/pack), co-authoring
- Performance & Error Handling — Concurrent loading, optimization do's/don'ts, form validation, IfError
- Power Fx Function Reference — Complete function reference by category: Text, Math, Date/Time, Logical, Table, Collection, Behavior, JSON, Environment
- Power Fx Operators Reference — Arithmetic, comparison, logical, membership (
in/exactin), scope (ThisItem/Self/Parent/As/@), chaining, type operators, precedence - Controls Reference — Top 15 Canvas controls (Gallery, EditForm, TextInput, ComboBox, Button, etc.) with key properties, events, patterns, modern vs classic differences
What ships with it
12 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.
- canvas-alm.md 1.2 KB
- components.md 2.3 KB
- connectors-integration.md 3.2 KB
- controls-reference.md 10 KB
- delegation.md 7.4 KB
- evals/canvas-delegation.json 2.8 KB
- offline.md 7.7 KB
- performance.md 2.3 KB
- power-fx-functions.md 12 KB
- power-fx-operators.md 4.5 KB
- power-fx.md 4.1 KB
- screens-responsive.md 2.8 KB
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 · 110 lines · 46 tokens per session scan A 0a6f46bb6197
canvas-apps is a skill published in the GitHub repository korchard333/claude-power-platform-community (50 stars, last pushed 6mo ago), licensed MIT. It adds 46 tokens to every session and 1,492 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 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…