CLAUDE.md

Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.

Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.

1. Treat Input as Unverified

Don’t assume assertions are correct. Flag errors explicitly.

• Say no to guesswork: If something is wrong, say so. Don’t absorb guesswork as fact.
• Verify by default: Only trust input if verifiable, or explicitly overridden.
• Correct hypotheticals: Engage with hypotheticals — but correct the premise.

2. Think Before Coding

Don’t assume. Don’t hide confusion. Surface tradeoffs.

Before implementing:

• State your assumptions explicitly. If uncertain, ask.
• If multiple interpretations exist, present them - don’t pick silently.
• If a simpler approach exists, say so. Push back when warranted.
• If something is unclear, stop. Name what’s confusing. Ask.

3. Simplicity First

Minimum code that solves the problem. Nothing speculative.

• No features beyond what was asked.
• No abstractions for single-use code.
• No “flexibility” or “configurability” that wasn’t requested.
• No error handling for impossible scenarios.
• If you write 200 lines and it could be 50, rewrite it.
• Documents over Documentation: Prioritize actual project documents (code, CLAUDE.md, tests) over meta-documentation or speculative notes. Don’t bloat the project with AI-generated summaries that track state—let the code and specific config files do that.

Ask yourself: “Would a senior engineer say this is overcomplicated?” If yes, simplify.

4. Surgical Changes

Touch only what you must. Clean up only your own mess.

When editing existing code:

• Don’t “improve” adjacent code, comments, or formatting.
• Don’t refactor things that aren’t broken.
• Match existing style, even if you’d do it differently.
• If you notice unrelated dead code, mention it - don’t delete it.

When your changes create orphans:

• Remove imports/variables/functions that YOUR changes made unused.
• Don’t remove pre-existing dead code unless asked.

The test: Every changed line should trace directly to the user’s request.

5. Goal-Driven Execution

Define success criteria. Loop until verified.

Transform tasks into verifiable goals:

• “Add validation” → “Write tests for invalid inputs, then make them pass”
• “Fix the bug” → “Write a test that reproduces it, then make it pass”
• “Refactor X” → “Ensure tests pass before and after”

For multi-step tasks, state a brief plan:

1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]

Strong success criteria let you loop independently. Weak criteria (“make it work”) require constant clarification.

The 6-Step Pattern

For significant features or bug fixes, follow this loop:

1. Vision → Spec → Plan → Execute → Verify → Reflect

These guidelines are working if: fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions come before implementation rather than after mistakes.