Blog
New perspectives, new possibilities.
72 results
Cleaning Up a Messy CLAUDE.md
CLAUDE.md rules go stale, land on the wrong layer, or never load. Pick a layer by who needs the rule, keep only lines that change actions, and verify with /context.
2026-11-13 ·DeepDojo.AI
Why Claude Code's "Read-Only" Command Edits Files
allowed-tools listed only Read and Grep, yet Claude Code edited files. Treat who starts a command, what skips approval, and what is blocked as separate controls.
2026-11-13 ·DeepDojo.AI
Turn Repeated Prompts Into Claude Code Commands
Rewriting the same request each time makes review standards drift. Write it as a skill-based slash command with clear inputs, context, output, and stop points.
2026-11-13 ·DeepDojo.AI
Which Claude Code Features Should You Learn First?
Turn on commands, memory, hooks, MCP, and subagents at once, and failures get hard to trace. Start with what you repeat daily, then add features one gap at a time.
2026-11-13 ·DeepDojo.AI
Find the Config Breaking Claude Code With Safe Mode
Only one repo breaks, and every customization is a suspect. Narrow it down with --safe-mode, restore one category at a time, and verify the fix on the original path.
2026-11-12 ·DeepDojo.AI
Troubleshooting Claude Code Errors Layer by Layer
A string of errors in the log and one vague message on screen? Write a reproducible record, assign the symptom to a layer, and find the earliest error.
2026-11-12 ·DeepDojo.AI
When to Stop Claude From Retrying a Failing Fix
Told Claude to fix until tests pass, and it loosened assertions and skipped a test? Set stop conditions for success, progress, budget, and dependencies first.
2026-11-12 ·DeepDojo.AI
Building Big Features With Claude Code, Step by Step
Your failing test failed because the service was down. Split big tasks into research, planning, and implementation, with exit conditions and behavior-based slices.
2026-11-12 ·DeepDojo.AI
How to Accept Work When Claude Code Says It's Done
Asked Claude to just fix it, and now can't tell whether to accept the result? Define behavioral, compatibility, automated, and review evidence before work begins.
2026-11-12 ·DeepDojo.AI
Block Claude Code From Editing .env With a Hook
Your protection script crashed with exit code 1 and the write went through. Build a PreToolUse Hook that blocks on failure, with the right exit codes and onFailure.
2026-11-12 ·DeepDojo.AI