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 skills add acaprino/daodan --skill python-refactorgit clone --depth 1 https://github.com/acaprino/daodanWrote 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.
[](https://agentmods.dev/skills/acaprino/daodan/python-refactor)<a href="https://agentmods.dev/skills/acaprino/daodan/python-refactor"><img src="https://agentmods.dev/badge/skills/acaprino/daodan/python-refactor.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.02966 |
| Opus 5 | $0.00028 | $0.01483 |
| Sonnet 5 | $0.00011 | $0.00593 |
| Haiku 4.5 | $0.00006 | $0.00297 |
Grade A, and why
python-refactor 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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Refactor
Transform complex Python into clear, maintainable code while preserving correctness. Phased workflow with safety-by-design and continuous validation. For deep references (anti-patterns, OOP principles, cognitive complexity, regression prevention), see the references/ directory.
When to invoke
- Explicit "human", "readable", "maintainable", "clean", or "refactor" request
- Code review flags comprehension or maintainability issues
- Legacy code modernization
- Onboarding / educational contexts
- Complexity metrics exceed thresholds
- Red flags: file > 500 lines with scattered functions and global state, multiple
globalstatements, no clear module/class organization, configuration mixed with business logic
Do NOT invoke when
- Code is performance-critical and profiling shows perf optimization is needed first
- Code is scheduled for deletion or replacement
- External dependencies require upstream contributions instead
- User explicitly requested perf optimization over readability
Core principles (priority order)
- Prefer structured OOP for complex code -- shared state, multiple concerns, scattered globals = restructure into classes/modules. (But: simple modules with pure functions, click/argparse CLIs, and functional pipelines DON'T need to be forced into classes.)
- Clarity over cleverness -- explicit beats implicit
- Preserve correctness -- all tests pass, behavior identical
- Single Responsibility -- one thing per class/function (SOLID)
- Self-documenting structure -- code = what, comments = why
- Progressive disclosure -- reveal complexity in layers
- Reasonable performance -- never sacrifice >2× without explicit approval
Hard constraints
- SAFETY BY DESIGN -- mandatory migration checklists for destructive changes. CREATE → SEARCH → MIGRATE → VERIFY → only then REMOVE. NEVER remove before 100% migration verified.
- STATIC ANALYSIS FIRST --
flake8 --select=F821,E0602(orruff check --select=F821) BEFORE tests. Catches NameErrors immediately. - PRESERVE BEHAVIOR -- all existing tests pass after.
- NO PERF REGRESSION -- never degrade > 2× without explicit approval.
- NO API CHANGES -- public APIs unchanged unless explicitly requested + documented.
- NO OVER-ENGINEERING -- simple stays simple.
- NO MAGIC -- no framework magic, no metaprogramming unless absolutely necessary.
- VALIDATE CONTINUOUSLY -- static analysis + tests after each logical change.
What ships with it
20 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/pyproject.toml 3.9 KB
- assets/templates/analysis_template.md 5.7 KB
- assets/templates/flake8_report_template.md 11 KB
- assets/templates/summary_template.md 5.9 KB
- references/anti-patterns.md 20 KB
- references/cognitive_complexity_guide.md 16 KB
- references/examples/python_complexity_reduction.md 12 KB
- references/examples/script_to_oop_transformation.md 32 KB
- references/examples/typescript_naming_improvements.md 11 KB
- references/flake8_plugins_guide.md 7.5 KB
- references/oop_principles.md 21 KB
- references/patterns.md 25 KB
- references/REGRESSION_PREVENTION.md 15 KB
- scripts/analyze_multi_metrics.py 16 KB runs code
- scripts/analyze_with_flake8.py 25 KB runs code
- scripts/benchmark_changes.py 10 KB runs code
- scripts/check_documentation.py 12 KB runs code
- scripts/compare_flake8_reports.py 20 KB runs code
- scripts/compare_metrics.py 8.8 KB runs code
- scripts/measure_complexity.py 9.3 KB runs code
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 · 271 lines · 55 tokens per session scan A 1421e4684fe4
python-refactor is a skill published in the GitHub repository acaprino/daodan (8 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 2,966 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 2026-09-05.
Other skills, from other repositories
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
pennylane
Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with…
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
rocm-kernels
Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…
holoscan-install-wheel
Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.
typing-exclusion-worker
Python typing exclusion worker: remove assigned mypy exclusion modules in small scoped batches, fix typing issues, run validation, and produce a structured completion summary. Use when running parallel typing-debt workers or when asked to remove modules from pyproject mypy exclusion overrides.