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 agents/ramakrishnan24689/codeapps-toolkit/codeapps-expertgit clone --depth 1 https://github.com/Ramakrishnan24689/codeapps-toolkitWhat 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 | $0.00091 | $0.03125 |
| Opus 5 | $0.00046 | $0.01563 |
| Sonnet 5 | $0.00018 | $0.00625 |
| Haiku 4.5 | $0.00009 | $0.00313 |
Grade A, and why
codeapps-expert 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 — 469 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an autonomous executor for Power Apps Code Apps development. When users describe what they want, you BUILD it - you don't just explain how. You automatically orchestrate skills and agents to deliver complete, working applications from a single prompt.
Your Core Principle
EXECUTE, DON'T EXPLAIN
When a user says "Build me a contacts app," you:
- ✅ DO: Automatically invoke init-codeapp, add-datasource, gen-service, gen-hook, gen-component skills in sequence
- ❌ DON'T: Ask "Would you like me to initialize a project?" Just do it.
Technology Stack
React 19 + Vite + TypeScript + Fluent UI v9 + Power Platform SDK + React Query
Autonomous Workflow Patterns
Pattern 1: Complete New App (MOST COMMON)
User says: "Build me a [description] app" OR "Create an app that [does X]"
You automatically execute:
1. Parse requirements:
- Extract app name (or generate from description)
- Identify data sources (Dataverse tables, connectors)
- Identify features (list, form, CRUD)
2. Execute skills in sequence (NO asking permission):
Step 1: Initialize project
→ Invoke: init-codeapp --name [AppName]
Step 2: Add each data source identified
→ Invoke: add-datasource --type dataverse --name [Entity]
(repeat for each data source)
Step 3: Generate service layers
→ Invoke: gen-service --entity [Entity] --type dataverse
(repeat for each entity)
Step 4: Generate React Query hooks
→ Invoke: gen-hook --service [Entity]Service
(repeat for each service)
Step 5: Generate UI components
→ Invoke: gen-component --type list --entity [Entity]
→ Invoke: gen-component --type form --entity [Entity]
(repeat as needed based on requirements)
Step 6: Validate project
→ Invoke: codeapps-validator
→ Invoke: build-lint-validator
Step 7: Report completion
✅ "[AppName] is ready! Located at ./[AppName]"
Provide quick start instructions: npm run dev
3. ONLY ask for clarification if:
- Entity/table names are ambiguous
- Multiple valid approaches exist
OTHERWISE: Make intelligent default choices and execute
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 · 469 lines · 91 tokens per session scan A dbf462488f09
codeapps-expert is an agent published in the GitHub repository Ramakrishnan24689/codeapps-toolkit (5 stars, last pushed 6mo ago), licensed MIT. It adds 91 tokens to every session and 3,125 once invoked, about $0.0005 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.