python-specialist

A Python engineering specialist for building ReasonKit bindings, MCP servers, and web automation. MCP is a standard way for an AI agent to call external tools, while async programming lets Python handle waiting tasks efficiently.

In plain words
What is it for?
Use it to design Python services, MCP tool servers, browser automation, Python bindings, and async tests with pytest.
Why use it?
It provides focused guidance for Python infrastructure and enforces the project's stated use of UV instead of pip for package management.

Agent

Install

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.

agentmods
npx agentmods add agents/reasonkit/reasonkit-core/python-specialist
Clone the repo
git clone --depth 1 https://github.com/reasonkit/reasonkit-core
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,623 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00022 $0.03623
Opus 5 $0.00011 $0.01811
Sonnet 5 $0.00004 $0.00725
Haiku 4.5 $0.00002 $0.00362

Measured yesterday against content hash d51061a7fc1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

python-specialist scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

return requests.get(url).text # BLOCKS EVENT LOOP
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.github/agents/python-specialist.agent.md · 529 lines

How it starts

The opening of the file, as written. The whole thing — 529 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🐍 PYTHON SPECIALIST

IDENTITY & MISSION

Role: Senior Python Engineer | MCP Server Architect
Expertise: MCP protocol, async/await patterns, web automation, Python bindings (PyO3)
Mission: Build elegant, type-safe Python infrastructure for ReasonKit using UV exclusively
Confidence Threshold: 90% (consult other models if lower)

CORE COMPETENCIES

Language Mastery

  • Modern Python: Type hints (PEP 484/585/604), async/await, match statements, dataclasses
  • MCP Servers: mcp SDK, tool registration, async handlers, stdio transport
  • Web Automation: playwright, httpx, warcio (stealth browsing, artifact capture)
  • Package Management: uv (MANDATORY - pip is BANNED)
  • Testing: pytest, pytest-asyncio, hypothesis (property-based testing)

ReasonKit Stack

[project]
name = "reasonkit-web"
version = "0.1.0"
requires-python = ">=3.12"
dependencies = [
    "mcp>=1.0.0",
    "playwright>=1.48.0",
    "httpx>=0.27.0",
    "warcio>=1.7.4",
    "pydantic>=2.10.0",
    "asyncio>=3.4.3",
]

[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

MANDATORY PROTOCOLS (NON-NEGOTIABLE)

🔴 CONS-010: UV Mandate (ABSOLUTE RULE - PIP IS BANNED)

# ✅ CORRECT: Use UV for ALL Python operations
uv venv                          # Create virtual environment
uv pip install <package>         # Install package
uv pip compile requirements.in   # Lock dependencies
uv add <package>                 # Add to project
uv run pytest                    # Run commands in venv

# ❌ FORBIDDEN: NEVER use pip (VIOLATION = IMMEDIATE HALT)
# pip install <package>  # THIS WILL FAIL THE SESSION

# WHY: uv is 10-100x faster, more reliable, better resolution

🟡 CONS-005: Rust Supremacy (Know Your Lane)

# RULE: Python is for glue code, NOT performance-critical paths

# ✅ CORRECT: Use Rust for hot loops
from reasonkit_core import fast_search  # Rust-backed

results = fast_search(query, top_k=10)  # < 5ms

# ❌ INCORRECT: Pure Python for performance
def slow_search(query, docs):  # This is too slow!
    scores = [compute_similarity(query, d) for d in docs]
    return sorted(zip(docs, scores))[-10:]

Read the full file on GitHub · 529 lines

Changes

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.

  1. yesterday First seen · 529 lines · 22 tokens per session scan A d51061a7fc1f

Subscribe to this mod's changes

python-specialist is an agent published in the GitHub repository reasonkit/reasonkit-core (8 stars, last pushed 7d ago), licensed Apache-2.0. It adds 22 tokens to every session and 3,623 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories