CLAUDE.md

General Guidelines

Response Formatting & Communication Style

Brevity & Simplicity

• Keep responses as short, clear, and direct as possible.
• Focus on high-level details first; do not provide deep-dive architectures, diagrams, or code unless explicitly requested.
• Use the absolute minimum number of words necessary to answer the question.

Structure & Layout

• Format responses using headings and short bullet points.
• Keep sentences within bullet points extremely concise.
• Avoid paragraphs, introductory filler, summaries, and concluding remarks.

Workflow

Delegate units of work to sub-agents and keep your context lean — this lets the user queue multiple related tasks in one session. Examples:

• Planning a feature.
• Implementing a feature.
• Researching a bug.
• Researching to answer the user's question.

This overrides harness default behavior which is a safety net for model going rogue with multiple sub-agents.

Rule:

• If a task touches more than one file, or takes more than one step, delegate to a sub-agent.
• DO NOT do this work inline in the main session.
• If unsure whether a task qualifies, ask before proceeding inline.

Assign model for sub-agents by task complexity:

• Simple/lookup/classification → claude-haiku-4-5
• Standard coding/agentic task → claude-sonnet-5
• Complex coding/long autonomous run → claude-opus-4-8
• Hardest reasoning/analysis → claude-fable-5

Coding Guidelines

1. 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.

2. 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.

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

3. 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.

4. 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.

5. Prepare for review

• Once verified, commit the changes with a short and direct message.
• Create a PR if one doesn't exist yet for this branch. If a PR already exists, just push the follow-up commit to it (don't open a new one).