Setting up notification triggers
System notifications for .env access, tool errors, and high token usage. Plus custom regex triggers on any field with per-repo scoping — no Claude Code hooks required.
claude-devtools supports system notifications triggered by patterns in your session. Built-in triggers include:
.envFile Access — alerts when Claude reads any.envfile- Tool Result Error — alerts on
is_error: trueresponses - High Token Usage — alerts when a single turn exceeds a token threshold (default: 8,000)
You can create custom triggers with regex patterns that match against specific fields (file paths, commands, prompt content, thinking). Assign colors, set ignore patterns, and scope triggers to specific repositories.
This replaces the need to wire up Claude Code hooks manually for every project. The triggers are evaluated on the same JSONL transcript stream that powers the rest of claude-devtools, so they fire whether the session is running in the terminal, in an IDE, or via any other Claude Code surface.
Related
Debugging Claude Code subagents and teams
Each subagent renders as its own execution tree with tool traces, tokens, duration, and cost. Nested agents render recursively. Teammate messages are color-coded by sender.
Inspecting remote sessions over SSH
claude-devtools reads ~/.ssh/config for host aliases, opens SFTP to remote ~/.claude/, and isolates each host's state. Useful for CI machines, cloud instances, and team servers.