wiswa-mcp: Agent for Claude Code

.claude/agents/python-expert.md

python-expert is an agent for Claude Code from Tatsh/wiswa-mcp. It costs 38 tokens per session (2,276 once invoked), scanned A, original, MIT.

An expert coding agent for substantial Python implementation work in the wiswa-mcp project, following that project's coding and testing rules.

In plain words
What is it for?
Writing and maintaining production-quality Python, including tests, formatting, type checking, and Click-based commands.
Why use it?
It provides project-specific guidance for complex Python changes instead of treating them like simple edits.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is Tatsh/wiswa-mcp's own configuration. It tells Claude Code how to work on wiswa-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything wiswa-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Tatsh/wiswa-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Tatsh/wiswa-mcp/master/.claude/agents/python-expert.md
Clone the repo
git clone --depth 1 https://github.com/Tatsh/wiswa-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for python-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/tatsh/wiswa-mcp/python-expert/github.svg)](https://agentmods.dev/agents/tatsh/wiswa-mcp/python-expert)
Your own site
<a href="https://agentmods.dev/agents/tatsh/wiswa-mcp/python-expert"><img src="https://agentmods.dev/badge/agents/tatsh/wiswa-mcp/python-expert/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for python-expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/tatsh/wiswa-mcp/python-expert"><img src="https://agentmods.dev/badge/agents/tatsh/wiswa-mcp/python-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,276 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00038 $0.02276
Opus 5.5 $0.00015 $0.00910
Sonnet 5.5 $0.00008 $0.00455
Haiku 4.5 $0.00004 $0.00228

Measured 1mo ago against content hash 332444f0ad44, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

python-expert 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 1mo 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.

.claude/agents/python-expert.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Python Expert Agent

General-purpose expert-level Python coding agent for the wiswa-mcp project.

Role

You are an expert Python developer. You write idiomatic, production-quality Python code. Follow all conventions defined in the rule files under .claude/rules/.

Key References

  • .claude/rules/general.md - project-wide conventions
  • .claude/rules/python.md - Python coding guidelines
  • .claude/rules/python-tests.md - test conventions

Tooling

  • Build: Hatchling

  • Package manager: uv

  • Linter/formatter: Ruff (check + format)

  • Type checker: mypy (strict mode)

  • CLI framework: Click

  • Logging: bascom sets up logging: setup_logging(). Only use setup_logging in entry points (commands), never in library code.

    from bascom import setup_logging
    
    @click.command()
    @click.option('-d', '--debug', is_flag=True)
    def my_command(debug: bool = False) -> None:
        """Do something."""
        setup_logging(debug=debug, loggers={'wiswa.mcp': {}})
    

    Additional third-party loggers can be added as needed:

    setup_logging(debug=debug, loggers={
        'wiswa.mcp': {},
        'urllib3': {},
        'soupsieve': {},
    })
    

    In library modules, define a module-level logger (not exported):

    log = logging.getLogger(__name__)
    

    Always use %-style formatting in log calls, never f-strings or .format():

    log.debug('Processing file %s.', path)
    log.info('Found %d items in %s.', count, name)
    log.warning('Skipping %s: %s.', path, reason)
    log.error('Failed to read `%s`.', path)
    

    Log messages that are complete sentences must end in a period. Use backticks to delimit an identifier at the end of a sentence so the period is unambiguous: 'A user modified `%s`.'

Comments that are complete sentences must also end in a period.

All code and comments must be word-wrapped at 100 characters.

  • Tests: pytest with pytest-mock and pytest-cov

Module Structure

Read the full file on GitHub · 287 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. 1mo ago Changed 332444f0ad44
  2. 2mo ago First seen · 287 lines · 38 tokens per session scan A 7baef91fcf1e

Subscribe to this mod's changes

python-expert is an agent published in the GitHub repository Tatsh/wiswa-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 2,276 once invoked, about $0.0002 per session on Opus 5.5. 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.

Related

python-expert compared with agents from other repositories

python-expert next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
python-expertTatsh/wiswa-mcpAgent0yesterdayMITA38Claude Code
fastmcp-specialistgensecaihq/MCP-Developer-SubAgentAgent291y agoMITA24Claude Code
Geoprocessing SpecialistSHAdd0WTAka/Zen-Ai-PentestAgent5033d agoMITA45Claude Code, OpenCode
python-proechoVic/blade-codeAgent18124d agoMITA51Claude Code
temporal-test-buildercanonical/copilot-collectionsAgent323d agoApache-2.0A56Claude Code
script-operatorMadGraphTeam/MadAgentsAgent153mo agoMITA24Claude Code
python-reviewerGGGODLIN/claude-pr-reviewAgent1141mo agoMITA43Claude Code