Blog
New perspectives, new possibilities.
87 results
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
Get a Desktop Alert When Claude Code Needs You
Came back to find Claude stuck on a permission prompt? Set up a Notification Hook for desktop alerts: where it goes, why exec form, when it fires, and async runs.
2026-11-12 ·DeepDojo.AI
Claude Code Hook Not Firing? Check Four Layers
The script works by hand but never fires in Claude Code? Check registration, triggering, input, and result with /hooks, a minimal event JSON, and debug logs.
2026-11-12 ·DeepDojo.AI
How to Run Claude Code Subagents in Parallel Safely
Two subagents passed their tests, but the merged code doesn't fit. Split work by research, file ownership, or worktrees, and settle shared decisions first.
2026-11-12 ·DeepDojo.AI
A Read-Only Code Review Subagent for Claude Code
Tired of restating review rules? Define the role in .claude/agents, limit its tools, model, and permissions, and recheck mode inheritance and memory write access.
2026-11-12 ·DeepDojo.AI
How to Verify a Subagent's Findings
A subagent returns a tidy summary with line numbers. It never saw your session, so brief it fully, then check files, logs, and repro steps before acting on it.
2026-11-12 ·DeepDojo.AI