auto
Smart router - Single entry point with natural language intent detection
[advanced] Activate destructive command warnings for the session
> /plugin marketplace add nyldn/claude-octopusHow it fires
How this command gets triggered: by you, by Claude, or both.
/carefulContext preview
What this command does when you run it.
[advanced] Activate destructive command warnings for the session
command: careful disable-model-invocation: true description: "[advanced] Activate destructive command warnings for the session"
When the user invokes `/octo:careful`, activate careful mode for the current session.
Write the activation state file:
_OCTO_SESSION_ID="${CLAUDE_CODE_SESSION_ID:-${CLAUDE_SESSION_ID:-$$}}"
echo "active" > "/tmp/octopus-careful-${_OCTO_SESSION_ID}.txt"Careful mode adds a PreToolUse safety net on Bash commands. Before any destructive command executes, you will be prompted to confirm. This catches accidental damage without blocking normal work.
**Detected patterns:**
Remove the state file to deactivate:
_OCTO_SESSION_ID="${CLAUDE_CODE_SESSION_ID:-${CLAUDE_SESSION_ID:-$$}}"
rm -f "/tmp/octopus-careful-${_OCTO_SESSION_ID}.txt"/octo:careful
After activation, confirm to the user:
⚠️ Careful mode activated. Destructive commands will now require confirmation before executing.
Every AI model has blind spots. Claude Octopus supports twelve external provider integrations — Codex, Antigravity CLI, Copilot, Qwen, Ollama, Perplexity, OpenRouter, OrcaRouter, OpenCode, Cursor CLI, Grok, and Kimi Code — alongside the built-in Claude Code
Repo: nyldn/claude-octopus
Smart router - Single entry point with natural language intent detection
Start a creative thought partner brainstorming session
Switch Octopus model routing to the configured budget tier
[advanced] Compatibility view of the deterministic Octopus usage report
Multi-LLM council for advice, decision support, implementation plans, and gated implementation
AI Debate Hub - Structured debates across Claude and available external providers