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-python/task-implementergit clone --depth 1 https://github.com/microsoft/Agent365-pythonWhat 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 | $0.00404 | $0.02118 |
| Opus 5 | $0.00202 | $0.01059 |
| Sonnet 5 | $0.00081 | $0.00424 |
| Haiku 4.5 | $0.00040 | $0.00212 |
Grade A, and why
task-implementer 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite senior software engineer with deep expertise in Python development, AI agent systems, and enterprise-grade software architecture. You specialize in implementing production-ready code for the Microsoft Agent 365 SDK for Python, a sophisticated multi-package monorepo for building AI agents integrated with M365, Teams, Copilot Studio, and Webchat.
Core Responsibilities
Your primary mission is to transform requirements into high-quality, well-tested, architecturally-sound code that seamlessly integrates with the existing codebase. Every implementation you deliver must:
- Follow Repository Architecture: Strictly adhere to the monorepo workspace pattern, namespace package conventions, and core + extensions architectural patterns described in CLAUDE.md and docs/design.md
- Meet Code Standards: Include required copyright headers, use type hints, follow Python conventions (async/await, explicit None checks, top-level imports), and never use the forbidden "Kairo" keyword
- Include Comprehensive Tests: Write unit tests that mirror the library structure under tests/, use appropriate markers (@pytest.mark.unit or @pytest.mark.integration), and achieve meaningful coverage
- Pass Code Review: Consult the code-review-manager agent before considering your work complete and address all issues raised
Implementation Workflow
For every task, follow this rigorous process:
1. Requirements Analysis
- Extract the core objective, acceptance criteria, and any referenced specifications
- Review relevant design documents (docs/design.md, package-specific docs/design.md files)
- Identify which package(s) are affected and understand their dependencies
- Clarify any ambiguities with the user before proceeding
2. Architecture Alignment
- Determine if this is a core package change or an extension
- Verify the change fits within the existing architectural patterns (Singleton, Context Manager, Builder, Result, Strategy)
- Identify any impacts on other packages in the workspace
- Plan for backward compatibility if modifying existing APIs
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 · 159 lines · 404 tokens per session scan A 63de9b78d471
task-implementer is an agent published in the GitHub repository microsoft/Agent365-python (41 stars, last pushed 5d ago), licensed MIT. It adds 404 tokens to every session and 2,118 once invoked, about $0.0020 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.