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/slamer59/mcp-python-refactoring/skillnpx skills add slamer59/mcp-python-refactoring --skill skillgit clone --depth 1 https://github.com/slamer59/mcp-python-refactoringWhat 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 | $0.00042 | $0.00936 |
| Opus 5 | $0.00021 | $0.00468 |
| Sonnet 5 | $0.00008 | $0.00187 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
python-refactoring 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Refactoring Assistant
This project ships python-refactor-cli, a CLI that wraps rope, radon, vulture,
pyrefly, mccabe, complexipy, bandit, pip-audit, and refurb into one set of
refactoring-analysis commands. Use it whenever you are about to refactor,
review, or assess the health of Python code in this repository.
Primary usage: CLI
Prefer running the CLI directly via subprocess (e.g. the Bash tool) over starting the MCP server for one-off analysis — it's faster and cheaper:
uv run python-refactor-cli <command> --format json ...
Every analysis command supports --format json for machine-parseable output.
Run uv run python-refactor-cli <command> --help for full option details.
Command reference
| Command | Target | Use it to... |
|---|---|---|
analyze <file> |
file | Full refactoring analysis of a single file |
find-long-functions <file> [-t N] |
file | Find functions at/over N lines (candidates for extraction) |
extraction-guidance <file> [-fn NAME] |
file | Get step-by-step guidance for extracting a specific function |
test-coverage <source> [-t tests/] |
file/dir | Find files/functions missing test coverage |
tdd-guidance <file> [-fn NAME] |
file | Get Red-Green-Refactor guidance for a function |
security-scan <file> |
file | Scan for security vulnerabilities, vulnerable deps, and outdated patterns |
analyze-package <path> |
package/dir | Full structural analysis of a package |
package-metrics <path> |
package/dir | Complexity, cohesion, coupling, health score |
package-issues <path> |
package/dir | Structural issues (god package, circular deps, etc.) |
package-dependencies <path> |
package/dir | Dependency graph and circular-dependency detection |
Example:
uv run python-refactor-cli find-long-functions src/app.py --line-threshold 30 --format json
{
"total_functions_analyzed": 12,
"long_functions_found": 2,
"line_threshold": 30,
"functions": [
{"name": "process_order", "start_line": 40, "end_line": 95, "length": 56, "location": "lines 40-95"}
]
}
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 · 96 lines · 42 tokens per session scan A 8dd418420edc
python-refactoring is a skill published in the GitHub repository slamer59/mcp-python-refactoring (13 stars, last pushed 7d ago), licensed MIT. It adds 42 tokens to every session and 936 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…