Clean Code - Pragmatic AI Coding Standards
Be concise, direct, and solution-focused.
Core Principles
| Principle | Rule |
|---|---|
| SRP | Single Responsibility - each function/class does ONE thing |
| DRY | Don't Repeat Yourself - extract duplicates, reuse |
| KISS | Keep It Simple - simplest solution that works |
| YAGNI | You Aren't Gonna Need It - don't build unused features |
| Boy Scout | Leave code cleaner than you found it |
Naming Rules
| Element | Convention |
|---|---|
| Variables | Reveal intent: userCount not n |
| Functions | Verb + noun: getUserById() not user() |
| Booleans | Question form: isActive, hasPermission, canEdit |
| Constants | SCREAMING_SNAKE: MAX_RETRY_COUNT |
Rule: If you need a comment to explain a name, rename it.
Function Rules
| Rule | Description |
|---|---|
| Small | Max 20 lines, ideally 5-10 |
| One Thing | Does one thing, does it well |
| One Level | One level of abstraction per function |
| Few Args | Max 3 arguments, prefer 0-2 |
| No Side Effects | Don't mutate inputs unexpectedly |
Code Structure
| Pattern | Apply |
|---|---|
| Guard Clauses | Early returns for edge cases |
| Flat > Nested | Avoid deep nesting (max 2 levels) |
| Composition | Small functions composed together |
| Colocation | Keep related code close |
AI Coding Style
| Situation | Action |
|---|---|
| User asks for feature | Write it directly |
| User reports bug | Fix it, don't explain |
| No clear requirement | Ask, don't assume |
Anti-Patterns (DON'T)
| ❌ Pattern | ✅ Fix |
|---|---|
| Comment every line | Delete obvious comments |
| Helper for one-liner | Inline the code |
| Factory for 2 objects | Direct instantiation |
| utils.ts with 1 function | Put code where used |
| "First we import..." | Just write code |
| Deep nesting | Guard clauses |
| Magic numbers | Named constants |
| God functions | Split by responsibility |
Before Editing a File, Think First
Before changing a file, ask yourself:
| Question | Why |
|---|---|
| What imports this file? | They might break |
| What does this file import? | Interface changes |
| What tests cover this? | Tests might fail |
| Is this a shared component? | Multiple places affected |
Quick Check:
File to edit: UserService.ts
└── Who imports this? → UserController.ts, AuthController.ts
└── Do they need changes too? → Check function signatures
Edit the file and all dependent files in the same task, so you don't leave broken imports or half-applied interface changes behind.
Summary
| Do | Don't |
|---|---|
| Write code directly | Write tutorials |
| Let code self-document | Add obvious comments |
| Fix bugs immediately | Explain the fix first |
| Inline small things | Create unnecessary files |
| Name things clearly | Use abbreviations |
| Keep functions small | Write 100+ line functions |
Remember: The user wants working code, not a programming lesson.
Self-Check Before Completing
Before saying "task complete", verify:
| Check | Question |
|---|---|
| ✅ Goal met? | Did I do exactly what user asked? |
| ✅ Files edited? | Did I modify all necessary files? |
| ✅ Code works? | Did I test/verify the change? |
| ✅ No errors? | Lint and TypeScript pass? |
| ✅ Nothing forgotten? | Any edge cases missed? |
If any check fails, fix it before reporting completion.
Verification Scripts
After completing work, each agent runs the scripts for its own domain (plus the "any agent" checks), so results land with the agent that can act on them.
Agent → Script Mapping
| Agent | Script | Command |
|---|---|---|
| frontend-specialist | UX Audit | cardume-ux-audit . |
| frontend-specialist | A11y Check | cardume-accessibility-checker . |
| backend-specialist | API Validator | cardume-api-validator . |
| mobile-developer | Mobile Audit | cardume-mobile-audit . |
| database-architect | Schema Validate | cardume-schema-validator . |
| security-auditor | Security Scan | cardume-security-scan . |
| seo-specialist | SEO Check | cardume-seo-checker . |
| seo-specialist | GEO Check | cardume-geo-checker . |
| performance-optimizer | Lighthouse | cardume-lighthouse-audit <url> |
| test-engineer | Test Runner | cardume-test-runner . |
| test-engineer | Playwright | cardume-playwright-runner <url> |
| Any agent | Lint Check | cardume-lint-runner . |
| Any agent | Type Coverage | cardume-type-coverage . |
| Any agent | i18n Check | cardume-i18n-checker . |
❌ Wrong:
test-engineerrunningcardume-ux-audit✅ Correct:frontend-specialistrunningcardume-ux-audit
Script Output Handling (Read → Summarize → Ask)
When running a validation script:
- Run the script and capture all output
- Parse the output - identify errors, warnings, and passes
- Summarize to user in this format:
## Script Results: [script name]
### ❌ Errors Found (X items)
- [File:Line] Error description 1
- [File:Line] Error description 2
### ⚠️ Warnings (Y items)
- [File:Line] Warning description
### ✅ Passed (Z items)
- Check 1 passed
- Check 2 passed
**Should I fix the X errors?**
- Wait for user confirmation before fixing
- After fixing → Re-run script to confirm
Running a script and ignoring its output means the task isn't verified. Don't auto-fix script findings without asking, since some findings are intentional or out of scope. The order is: read the output → summarize → ask → then fix.