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 skills/florianbruniaux/google-search-console-mcp/python-clean-codenpx skills add FlorianBruniaux/google-search-console-mcp --skill python-clean-codegit clone --depth 1 https://github.com/FlorianBruniaux/google-search-console-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 | $0.00055 | $0.00753 |
| Opus 5 | $0.00028 | $0.00377 |
| Sonnet 5 | $0.00011 | $0.00151 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
python-clean-code 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Clean Code Review
Reviews Python code in gsc-mcp for quality issues. Read-only analysis: produces a findings report, applies no fixes.
When to use
Invoke before opening a PR, after adding a new tool, or when a module feels hard to read. Pass a file path or module name as the argument.
Review Dimensions
1. Function Size and Focus
Flag any function exceeding 30 lines (excluding docstring and blank lines). A function that does more than one thing usually has a name with "and" in it, or a docstring that lists multiple behaviors. Each tool function in tools/ should do exactly one thing: call the API, transform the response, and return the JSON string.
2. Type Hints
Every function signature must be fully annotated. Check for:
- Missing return type (
-> str:,-> None:) - Missing parameter types
- Use of
Anywithout justification listanddictwithout subscripts where the shape is known (e.g.list[dict]not justlist)
3. Naming
Private helpers must start with _. Constants at module level must be in _SCREAMING_SNAKE_CASE. Tool functions exposed to MCP must be lowercase with underscores. No abbreviations that require context to decode (r for rows; svc is acceptable because it appears consistently across the codebase).
4. Error Handling
Tool functions must not silently swallow exceptions. They may catch specific exceptions to convert them into user-friendly error messages, but they must not use bare except: or except Exception: without re-raising or returning a structured error response. Transient Google API errors belong in retry.py, not in tool functions.
5. Duplication
Check for logic duplicated across modules. Common candidates: date range calculation (already in analytics._date_range), URL normalization (already in cross._normalize_url), dimension filter construction (already in ga4._build_dimension_filter). If a function re-implements one of these, flag it.
6. Output Contract Compliance
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.
- 2d ago First seen · 74 lines · 55 tokens per session scan A 4dede04073de
python-clean-code is a skill published in the GitHub repository FlorianBruniaux/google-search-console-mcp (9 stars, last pushed 6d ago), licensed MIT. It adds 55 tokens to every session and 753 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 skills, from other repositories
testing-python
Write and evaluate effective Python tests using pytest. Use when writing tests, reviewing test code, debugging test failures, or improving test coverage. Covers test design, fixtures, parameterization, mocking, and async testing.
gsccli
Use when the user wants to query Google Search Console search analytics (clicks/impressions/CTR/position by query/page/country/device), inspect URL indexing status, manage sitemaps, or send Indexing API notifications via the gsccli shell command. Triggers on GSC, Search Console, sitemap, indexing API, mobile…
fastapi-route-change
Use when adding, renaming, or modifying this backend's FastAPI routes, dependencies, middleware, or response behavior.
testing-python-pytest
Generates professional pytest unit test suites for Python source files, ensuring >90% line and branch coverage per file. Analyzes modules with AST inspection to discover all classes, methods, and functions, then produces well-structured tests following the AAA pattern with fixtures, parametrize, mocking, and…
web-analytics
Analyze web traffic, SEO performance, and search engine trends using Google Search Console, Google Analytics 4, and Bing Webmaster Tools. Use when the user asks to analyze traffic, check SEO, or find keyword opportunities.
seo-mcp-reports
Generate professional, visually stunning SEO reports using SEO-MCP tools. Use when generating HTML/PDF SEO reports with charts, metric cards, gradient headers, and agency-quality styling. Covers weekly, monthly, quarterly, technical audit, competitive analysis, and client-friendly agency report formats. Requires…