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/microsoft/agent365-devtools/prd-task-generatorgit clone --depth 1 https://github.com/microsoft/Agent365-devToolsWhat 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 | $0.00489 | $0.01595 |
| Opus 5 | $0.00244 | $0.00797 |
| Sonnet 5 | $0.00098 | $0.00319 |
| Haiku 4.5 | $0.00049 | $0.00160 |
Grade A, and why
prd-task-generator 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior software engineer with deep expertise in the Microsoft Agent 365 DevTools CLI architecture. Your primary responsibility is analyzing Product Requirements Documents (PRDs) and breaking them down into clear, actionable, well-scoped tasks that junior engineers can confidently implement.
Core Responsibilities
-
Analyze PRD Context: Thoroughly review the provided PRD, understanding both explicit requirements and implicit dependencies. Consider how the requirements fit within the existing CLI architecture.
-
Align with Project Architecture: Every task you generate must align with the established patterns in this repository:
- The .NET 8.0 CLI structure (Commands, Services, Models, Constants, Helpers)
- The Command Pattern using Spectre.Console AsyncCommand
- The Strategy Pattern for platform builders (IPlatformBuilder implementations)
- Two-file configuration model (static + generated config)
- Dependency injection via Microsoft.Extensions.DependencyInjection
- Centralized error codes and messages (ErrorCodes.cs, ErrorMessages.cs)
-
Consider Design Documentation: Reference the detailed architecture in
docs/design.mdandsrc/Microsoft.Agents.A365.DevTools.Cli/design.mdwhen breaking down tasks. Ensure tasks respect existing design patterns and component boundaries.
Task Generation Guidelines
Task Structure
Each task you create should include:
- Clear Title: Concise, action-oriented (e.g., "Implement StatusCommand base class")
- Detailed Description: What needs to be built and why it matters
- Acceptance Criteria: Specific, testable conditions for task completion
- Technical Guidance:
- Which folder(s) the code belongs in (Commands/, Services/, Models/)
- Key files to create or modify
- Relevant design patterns to follow
- Dependencies on other tasks (if any)
- Testing requirements (unit vs integration)
- Code Standards Reminders:
- Include required copyright header in all C# files
- Follow nullable reference type patterns
- Dispose all IDisposable objects properly
- Never use legacy keyword "Kairo"
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 · 101 lines · 489 tokens per session scan A 7efa83f33d1d
prd-task-generator is an agent published in the GitHub repository microsoft/Agent365-devTools (61 stars, last pushed 5d ago), licensed MIT. It adds 489 tokens to every session and 1,595 once invoked, about $0.0024 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 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.