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/tatsh/wiswa-mcp/python-expertgit clone --depth 1 https://github.com/Tatsh/wiswa-mcpWhat 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 | $0.00038 | $0.02269 |
| Opus 5 | $0.00019 | $0.01135 |
| Sonnet 5 | $0.00008 | $0.00454 |
| Haiku 4.5 | $0.00004 | $0.00227 |
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 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 — 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 usesetup_loggingin 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
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 · 287 lines · 38 tokens per session scan A 7baef91fcf1e
python-expert is an agent published in the GitHub repository Tatsh/wiswa-mcp (0 stars, last pushed 5d ago), licensed MIT. It adds 38 tokens to every session and 2,269 once invoked, about $0.0002 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
ci-medic
Runs the ci-settle loop (formula convergence, step X3) — watches CI checks, triages bot comments, fixes real findings or declines with a stated reason, regenerates generated artifacts. No merge authority.
kingdee-qa-engineer
QA & Test Engineer for the kingdee-mcp project. Authors evals/ and tests/ cases, reproduces bugs against the live K3Cloud environment, and runs regression scans via bin/kmcp test.
gsc-content-optimizer
Finds content optimization targets across two zones, striking distance (positions 4-10) and page-two quick wins (positions 11-20). Use when asked for content ideas, quick wins, or optimization opportunities. Aussi déclenché en français par "quelles pages optimiser en priorité", "où je peux gagner vite", "mes pages en…
gsc-sitemap-auditor
Audits all submitted sitemaps for a property. Use when asked about sitemap health, submitted vs. indexed counts, sitemap errors, or why certain pages are not getting crawled. Aussi déclenché en français par "mon sitemap est à jour", "problème de sitemap", "pourquoi les URLs de mon sitemap sont pas indexées", "combien…
operations-analyst
Operations and process analysis agent. Handles statistical process control, optimization, capacity planning, and efficiency analysis. Use when analyzing operational performance, quality control, or resource allocation.
rust-refactor-expert
Use this agent when you need to refactor, optimize, or improve existing Rust code for better maintainability, performance, and idiomatic style. This agent specializes in applying Rust best practices, identifying anti-patterns, and optimizing code for both human and AI readability.\n\nExamples:\n\n \nContext: User has…