ingenious: Command for Claude Code

.claude/commands/quality/py-quality/radon.md

radon is a command for Claude Code from Insight-Services-APAC/ingenious. It costs 0 tokens per session (619 once invoked), scanned A, original, MIT.

A procedure for using Radon, a Python code-analysis tool, to find complex functions and files that are difficult to maintain.

In plain words
What is it for?
Use it to scan Python code, rank refactoring hotspots, add safety tests, and simplify one area at a time.
Why use it?
It helps prioritize refactoring by measuring complexity and maintainability, while requiring focused tests before changing behavior.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is Insight-Services-APAC/ingenious's own configuration. It tells Claude Code how to work on ingenious 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 ingenious configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Insight-Services-APAC/ingenious. 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/Insight-Services-APAC/ingenious/main/.claude/commands/quality/py-quality/radon.md
Clone the repo
git clone --depth 1 https://github.com/Insight-Services-APAC/ingenious

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 radon

README.md
[![agentmods](https://agentmods.dev/badge/commands/insight-services-apac/ingenious/radon.svg)](https://agentmods.dev/commands/insight-services-apac/ingenious/radon)
Your own site
<a href="https://agentmods.dev/commands/insight-services-apac/ingenious/radon"><img src="https://agentmods.dev/badge/commands/insight-services-apac/ingenious/radon.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 619 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 $0.00000 $0.00619
Opus 5 $0.00000 $0.00309
Sonnet 5 $0.00000 $0.00124
Haiku 4.5 $0.00000 $0.00062

Measured 2d ago against content hash 634e8f59140c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

radon 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.

.claude/commands/quality/py-quality/radon.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refactor Using Radon (Complexity & Maintainability)

Use Radon to identify high-complexity / low-maintainability hotspots and refactor them safely and incrementally.

1. Run Radon Reports

uv run radon cc -s -a .          # Cyclomatic complexity (A best → F worst)
uv run radon mi -s .              # Maintainability Index (100 best → 0 worst)
uv run radon hal .                # (Optional) Halstead metrics

Record functions / classes with:

  • Complexity grade >= C (or numeric > 10)
  • Maintainability Index < 65

2. Prioritize Hotspots

Rank by (a) worst grade, (b) frequency of change (git log -S / blame), (c) business criticality.

3. Establish Safety Net

For each target file/function:

  1. Add / improve focused tests (behavioral, edge cases, error paths).
  2. Run: uv run pytest <relevant-tests> (fast feedback) before refactor.

4. Refactor Tactics (Apply One At A Time)

  • Extract Function / Method for cohesive blocks
  • Decompose long conditional chains (strategy map, dict dispatch, guard clauses)
  • Remove duplication (DRY) or inline trivial indirections
  • Simplify boolean logic (early returns, De Morgan)
  • Replace deep nesting with fail-fast exits
  • Clarify names; remove commented‑out code
  • Isolate side effects from pure logic
  • Reduce parameter count (introduce small dataclass / typed object)
  • Split large classes by responsibility (SRP)

After each micro-change:

uv run pytest <focused-scope>
uv run radon cc -s target_file.py
uv run radon mi -s target_file.py

Commit if green:

git add target_file.py tests/
git commit -m "refactor(radon): reduce complexity in <symbol> (C→B)"

5. Validate No Regression

When a file is “done”:

uv run radon cc -s -a .
uv run radon mi -s .
uv run pytest
uv run pre-commit run --all-files

6. Avoid Over-Refactoring

Stop when: (a) complexity ≤ B, (b) MI ≥ 70, (c) further change risks churn.

7. Handling Hard Cases

If complexity resists decomposition:

  • Introduce a decision table / data-driven structure
  • Split algorithm into phases (parse → transform → emit)
  • Accept temporary adapter layer while migrating callers

Read the full file on GitHub · 75 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. 2d ago First seen · 75 lines · 0 tokens per session scan A 634e8f59140c

Subscribe to this mod's changes

radon is a command published in the GitHub repository Insight-Services-APAC/ingenious (24 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 619 tokens. 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 2026-09-04.