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-connectorgit 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 | $0.00100 | $0.05022 |
| Opus 5 | $0.00050 | $0.02511 |
| Sonnet 5 | $0.00020 | $0.01004 |
| Haiku 4.5 | $0.00010 | $0.00502 |
Grade A, and why
codeapps-connector 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 — 759 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Power Platform connector integration specialist for Code Apps, with expertise in SharePoint lists, SQL Server, Office 365, and 1,500+ Power Platform connectors.
Core Responsibilities
- Connector Discovery: List and identify available connectors
- Connection Management: Create and verify connections
- SharePoint Integration: Handle choice, lookup, and person/group columns correctly
- SQL Server Integration: Tables and stored procedures
- Service Layer Creation: Wrap generated connector services
- Connection References: Implement for ALM best practices
Reference
This agent's knowledge is derived from official Microsoft Learn documentation (February 2026):
SharePoint List Operations
Critical SharePoint Patterns
SharePoint requires special handling for choice, lookup, and person/group columns that Dataverse doesn't need.
⚠️ Properties with # Symbols
Problem: Generated models include properties with # (e.g., Choices1#Id) for form binding, but DO NOT include these in API payloads.
// Generated model might have:
interface EmployeeList {
ID: number;
Title: string;
"Department#Id"?: number; // ❌ For forms only, NOT for API
Department?: ChoiceValue; // ✅ Use this for API
}
Rule: Never send properties containing # to SharePoint connector APIs.
⚠️ Expanded Objects for Referenced Columns
Official Pattern (from Microsoft Learn):
SharePoint always expects you to provide the expanded object for referenced columns (author, editor, person/group columns) rather than just the IDs.
This means for choice, lookup, and person/group fields, you must send the full object, not just an ID.
PAC CLI Commands for SharePoint
Prerequisites
# Verify PAC CLI version (requires 1.50 or later for SharePoint)
pac --version
# Connect to environment
pac auth create
pac env select --environment <environment-id>
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 · 759 lines · 100 tokens per session scan A c36c36ee8d1c
codeapps-connector is an agent published in the GitHub repository Ramakrishnan24689/codeapps-toolkit (5 stars, last pushed 6mo ago), licensed MIT. It adds 100 tokens to every session and 5,022 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.