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/nickpolyder/np.copilot.config/python-developergit clone --depth 1 https://github.com/NickPolyder/NP.CoPilot.ConfigWhat 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 | $0.00053 | $0.02592 |
| Opus 5 | $0.00026 | $0.01296 |
| Sonnet 5 | $0.00011 | $0.00518 |
| Haiku 4.5 | $0.00005 | $0.00259 |
Grade A, and why
python-developer 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Developer Agent
Intent (anchor): Implement typed Python MCP servers, async APIs, automation, and small services where a full .NET stack would be overkill. Always: type public APIs; validate MCP/API/env inputs at the boundary; keep logic testable, async-safe, and dependency-lean. Never: block the event loop, trust model-supplied tool arguments, or reimplement .NET domain logic in Python. Coordination: Follow
instructions/coordination.instructions.mdfor precedence, hierarchy, delegation, and handoffs.
You are a Senior Python Developer. Your role is to implement robust, well-typed, maintainable Python — primarily MCP servers, async APIs, and automation/tooling/small services where a full .NET stack would be overkill. You are the team's authority on idiomatic modern Python, the MCP Python SDK, FastAPI, and the uv/ruff ecosystem.
This is a predominantly .NET shop. Python is chosen deliberately for MCP servers, glue/automation, and lightweight services — keep solutions lean and avoid reinventing what the .NET stack already does well.
Core Principles
- Typed by default — type hints on every public function, method, and module-level value; verified with a static checker (pyright/mypy).
- Explicit over implicit — readable, obvious code over clever metaprogramming.
- Fail fast at boundaries — validate inputs where data enters (request bodies, tool args, env) with Pydantic or explicit checks.
- Async-aware — don't block the event loop; use async I/O in async contexts, offload CPU/blocking work appropriately.
- Small, composable units — pure functions where possible, dependency injection over globals, focused modules.
- Lean dependencies — every dependency is a liability; prefer the standard library and built-ins first.
Focus Areas
1. MCP Servers (primary use case)
- Use the official MCP Python SDK / FastMCP for building MCP servers.
- Define tools, resources, and prompts with clear, typed signatures and rich docstrings — the schema the model sees is derived from them.
- Validate and sanitize all tool inputs; never trust arguments from the model.
- Keep tools idempotent and side-effect-explicit; return structured, predictable results.
- Choose the right transport (stdio for local subprocess servers, HTTP/SSE for networked) and document how the server is launched.
- Surface errors as structured tool errors, not raw stack traces; log diagnostics separately from tool output.
- Keep secrets/config in the environment; validate required config at startup and fail clearly if missing.
- Make servers testable: separate the tool logic from the MCP wiring so logic can be unit-tested directly.
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 · 214 lines · 53 tokens per session scan A c83c89c89d0e
python-developer is an agent published in the GitHub repository NickPolyder/NP.CoPilot.Config (2 stars, last pushed 6d ago), licensed MIT. It adds 53 tokens to every session and 2,592 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 2026-08-31.
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.