canvas-app-planner

canvas-app-planner is an agent for Claude Code from microsoft/power-platform-skills. It costs 67 tokens per session (5,546 once invoked), scanned A, original, MIT.

A planning agent for Microsoft Power Apps Canvas Apps, which are apps built by arranging screens and controls. It turns an approved app request into shared instructions and a separate plan for each screen.

In plain words
What is it for?
Use it to plan a new Canvas App or a complex edit before implementation. It creates a dispatch index, shared conventions, screen-specific briefs, and, for new apps, the main app file.
Why use it?
It removes the need to work out every screen, control, data source, and interaction while building the app. It also records when a requested interaction cannot be implemented exactly.

Agent for Claude Code ✓ vendor

Written for Claude Code: user-invocable in frontmatter.

Part of the canvas-apps plugin — 4 skills, 2 agents, 1 hook, 1 MCP server shipped together

Good fit Use it to plan a new Canvas App or a complex edit before implementation. It creates a dispatch index, shared conventions, screen-specific briefs, and, for new apps, the main app file.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/microsoft/power-platform-skills/canvas-app-planner
About the project

microsoft/power-platform-skills is a plugin marketplace containing reusable skills, agents, and commands for developing with Microsoft Power Platform. Developers use it to build and deploy Power Pages sites, model-driven Power Apps, and related solutions through Claude Code or GitHub Copilot. The catalogue entries are the marketplace's included skills, agents, plugins, and other agent components.

microsoft/power-platform-skills · 829 stars · on GitHub · aka.ms

Install

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.

Clone the repo
git clone --depth 1 https://github.com/microsoft/power-platform-skills

Made for: Claude Code.

Or install canvas-apps, the plugin that ships this one along with the rest of its 4 skills, 2 agents, 1 hook, 1 MCP server.

Wrote 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.

agentmods badge for canvas-app-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/microsoft/power-platform-skills/canvas-app-planner.svg)](https://agentmods.dev/agents/microsoft/power-platform-skills/canvas-app-planner)
Your own site
<a href="https://agentmods.dev/agents/microsoft/power-platform-skills/canvas-app-planner"><img src="https://agentmods.dev/badge/agents/microsoft/power-platform-skills/canvas-app-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,546 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00067 $0.05546
Opus 5 $0.00034 $0.02773
Sonnet 5 $0.00013 $0.01109
Haiku 4.5 $0.00007 $0.00555

Measured 7d ago against content hash 87a92009d135, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

canvas-app-planner 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 7d 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.

plugins/canvas-apps/agents/canvas-app-planner.md · 458 lines

How it starts

The opening of the file, as written. The whole thing — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Canvas App Plan Writer

You receive an approved CREATE or EDIT plan. Do not redesign it or ask questions.

Your invocation includes:

  • Mode: CREATE or EDIT
  • Working directory: an absolute path supplied by the orchestrator
  • Plan index: [working directory]/canvas-app-plan.md
  • Shared plan: [working directory]/canvas-app-shared.md
  • User requirements and approved plan
  • CREATE context: target users and device
  • EDIT context: current app state and synced files

Preserve requirement semantics. Map every concrete requested noun and interaction to an exact visible affordance in the plan index. If discovery cannot support an interaction exactly, record an explicit approximation and reason; never silently rename buttons as "drag-style", call buttons "handles", or put copy in the app that promises an interaction the controls do not provide.

Plan in functional-first order: shared state and stable identity, complete executable workflows, observable evidence, responsive/accessibility behavior, then visual polish. When a control or screen budget is tight, remove decorative complexity before omitting, combining, or weakening a requested action.

Use ModernTabList only when it switches visible panels within one screen. For navigation between separate screen files, plan a repeated ModernButton row with direct OnSelect: =Navigate(...) actions and an explicit current-screen appearance.

1. Read Guidance

Read:

  • ${PLUGIN_ROOT}/references/YamlSyntax.md — file structure, syntax rules, parse-error triage
  • ${PLUGIN_ROOT}/references/ControlGuide.md — control selection, per-control properties, enums
  • ${PLUGIN_ROOT}/references/LayoutGuide.md — responsive layout, scrolling, color contrast
  • ${PLUGIN_ROOT}/references/PowerFxGuide.md — state, events, named formulas, mock data
  • ${PLUGIN_ROOT}/references/BehaviorGuide.md — action contracts, lifecycle behavior, mutation evidence
  • ${PLUGIN_ROOT}/references/DesignGuide.md — aesthetic direction and design process
  • ${PLUGIN_ROOT}/references/PlanTemplates.md — the exact shape of every artifact you write

Read the full file on GitHub · 458 lines

Changes

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.

  1. 7d ago First seen · 458 lines · 67 tokens per session scan A 87a92009d135

Subscribe to this mod's changes

canvas-app-planner is an agent published in the GitHub repository microsoft/power-platform-skills (829 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 5,546 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

catchup-runner

Does the catch-up fan-out, impact analysis, and brief assembly for /catchup on Sonnet (cheaper/faster than the caller's session). Spawned by the /catchup and /ketchup skills with a pre-resolved time window. Not user-invoked directly.

oliver-kriska/claude-elixir-phoenix · 63 tokens

verification-runner

Run project-aware verification loop. Reads mix.exs to discover tools (credo, dialyzer, sobelow, excheck), test commands, and custom aliases. Use proactively after code changes.

oliver-kriska/claude-elixir-phoenix · 44 tokens

web-researcher

Fetches and extracts information from web sources efficiently. Optimized for ElixirForum, HexDocs, and GitHub. Spawned by /phx:research or planning-orchestrator with pre-searched URLs or focused queries.

oliver-kriska/claude-elixir-phoenix · 51 tokens

geo-routing-engineer

Geospatial and routing specialist for Product-Builder products with maps, scheduling-by-location, or vehicle routing (route-optimization in logistics, dispatch in home services, field-booking). Owns the routing contract — geocoding, the VRP/routing model (constraints, objective), maps/distance-matrix provider…

avelikiy/great_cto · 112 tokens

senior-dev

Use to implement tasks from Beads backlog. Claims a task, implements with TDD, closes when done. Can run in parallel.

avelikiy/great_cto · 31 tokens

fec-design-token-mapper

Use this subagent to map styles and variables in Figma, Sketch, MasterGo, Pixso, Mokou, or Mockup to existing design tokens, theme variables, and style conventions in the project, and save the mapping report as a Markdown file.

bovinphang/frontend-craft · 58 tokens