You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
docs(CLAUDE.md): refine working style to essentials
Distilled to actionable principles:
- Think first, code second
- Own problems autonomously
- Verify work, don't assume
- Rethink when stuck, update CLAUDE.md when wrong
- Use subagents to stay focused
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Copy file name to clipboardExpand all lines: CLAUDE.md
+11-14Lines changed: 11 additions & 14 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -48,22 +48,19 @@ Single-file library with a main function and helper exports:
48
48
49
49
---
50
50
51
-
## How Claude Should Work
51
+
## Working Style
52
52
53
-
### Planning Before Coding
54
-
For complex tasks, thoroughly plan before writing code. Create a clear implementation plan, identify affected files, and consider edge cases. A well-thought-out plan enables one-shot implementations with fewer iterations.
53
+
### Think First, Code Second
54
+
For anything non-trivial, plan the approach before writing code. Identify which files change, what the edge cases are, and how to verify it works. A solid plan means fewer iterations and cleaner implementations.
55
55
56
-
### Self-Improvement
57
-
When corrected on a mistake, propose an update to this CLAUDE.md file to prevent the same mistake in future sessions. Be specific about what went wrong and how to avoid it.
56
+
### Own the Problem
57
+
When something's broken - CI failing, bug reported, error in logs - just go fix it. Read the error, trace the cause, implement the fix. Don't wait for instructions on each step.
58
58
59
-
### Autonomous Problem Solving
60
-
When asked to fix bugs or failing tests, investigate independently. Check CI logs, read error messages, trace the issue, and fix it without requiring step-by-step guidance. Use subagents for complex multi-file investigations to keep the main context focused.
59
+
### Verify, Don't Assume
60
+
After making changes, prove they work. Run the tests. Check the output. If asked to review code, be genuinely critical - find the issues, don't just approve.
61
61
62
-
### Code Review Mindset
63
-
When asked to review changes, be critical and thorough. Identify potential issues, suggest improvements, and verify the solution actually works. Don't just rubber-stamp changes - challenge assumptions and prove correctness.
62
+
### When Stuck or Wrong
63
+
If a solution feels hacky, stop. Rethink from scratch using what you learned. If corrected on a mistake, suggest a CLAUDE.md update to prevent it happening again - be specific about what to avoid.
64
64
65
-
### Iterative Refinement
66
-
If an initial solution feels hacky or overly complex, step back and reconsider. Sometimes the best approach is to scrap a mediocre implementation and design a cleaner solution from scratch, using everything learned from the first attempt.
67
-
68
-
### Context Efficiency
69
-
Offload discrete subtasks to subagents to preserve main context for high-level coordination. This is especially useful for research, file exploration, and isolated fixes that don't need full conversation history.
65
+
### Stay Focused
66
+
Use subagents for research, exploration, or isolated subtasks. Keep the main conversation for coordinating and making decisions.
0 commit comments