rshankras/claude-code-apple-skills/code-size

Claude Code and agent skill by rshankras/claude-code-apple-skills

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Enforce complexity and size limits on Swift code with SwiftLint threshold rules — cyclomatic complexity, function/type/file length, parameter count — adopted via a violations baseline so existing code never blocks. Use when agent-written code needs deterministic size constraints.

Install

npx vskill@latest install rshankras/claude-code-apple-skills/code-size

SKILL.md

Code Size & Complexity Limits

Complexity is the strongest single predictor of defect density, and code written by agents balloons fastest — an agent under pressure adds one more branch to an existing function far more readily than it extracts a new one. These five SwiftLint threshold rules are the deterministic cap: they keep functions small enough that tests can actually cover their branches, and they keep agents from wrangling with their own tangles.

When This Skill Activates

Use this skill when:

  • Setting up quality gates for a project where agents write most of the code
  • A review keeps flagging "this function is too long/branchy" by hand
  • Functions have grown past what their tests plausibly cover
  • Adopting the deterministic gauntlet (see testing/fitness-functions/)

The Rules

The fragment at rules/swiftlint.yml configures five built-in SwiftLint rules (all enabled by default in SwiftLint — this fragment sets the thresholds):

RuleWarningErrorWhat it caps
cyclomatic_complexity1020Independent paths through one function
function_body_length50100Lines per function body
type_body_length300500Lines per type body
file_length5001000Lines per file
function_parameter_count58Parameters per function

Merge the fragment into the project's .swiftlint.yml (alongside any opt_in_rules/custom_rules fragments already adopted).

Brownfield Adoption: Baseline, Never Mass-Refactor

Turning these rules on in an existing codebase must not trigger a refactoring spree — bulk rewrites to satisfy a linter are how working code gets broken. Freeze today's violations and gate only new ones:

bash
# One-time: record existing violations (SwiftLint 0.55+)
swiftlint lint --write-baseline .swiftlint-baseline.json
# The gate from then on — fails only on NEW violations
swiftlint lint --strict --baseline .swiftlint-baseline.json

Commit .swiftlint-baseline.json. Shrink it opportunistically: when touching a baselined function for other reasons, fix its violation and regenerate the baseline in the same commit.

Fallback for older SwiftLint (before 0.55, no baseline support): record the violation count instead —

bash
swiftlint lint --quiet | wc -l > .swiftlint-count
# Gate: current count must not exceed the committed count

When a Rule Fires

The fix is structural, not suppressive:

  • cyclomatic_complexity / function_body_length → extract the branches into named functions, or replace the branch ladder with a table/enum dispatch
  • type_body_length / file_length → split by responsibility (extensions in separate files count separately)
  • function_parameter_count → introduce a parameter struct

// swiftlint:disable is not a fix. The rare legitimate exemption (a generated file, a big-but-flat data table) belongs in .swiftlint.yml's excluded: list with a comment — visible in one place, not scattered through source.

Common Pitfalls

PitfallProblemSolution
Enabling without a baselineDay-one wall of violations, gate ignored--write-baseline first, gate on new only
Mass-refactoring to satisfy thresholdsWorking code broken for a numberFreeze old violations; fix opportunistically
Inline swiftlint:disable commentsExemptions scattered and invisibleexcluded: list in config, with reasons
Thresholds loosened per-projectCap quietly stops cappingChange thresholds only with a written reason

References

  • testing/fitness-functions/ — set/count invariants a per-line rule can't express
  • testing/coverage-ratchet/ — the coverage half of the metrics gauntlet
  • ios/coding-best-practices/ — iOS-specific lint fragment (style/API rules)
  • generators/ci-cd-setup/ — base .swiftlint.yml template these fragments merge into

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
770
Repository forks
74
7-day trend score
33

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/rshankras/claude-code-apple-skills/code-size/badge)](https://verified-skill.com/skills/rshankras/claude-code-apple-skills/code-size)

Something wrong with this skill or its page? Tell us.