claude-smart Commands In Codex

Codex does not currently support plugin-provided slash commands. When the user asks for a claude-smart command, run the equivalent shell command through the active plugin root. This skill is Codex-specific; under Claude Code the native /claude-smart:* slash commands already exist, so do not fall back to the shell commands there.

Command Map

• Dashboard: bash ~/.reflexio/plugin-root/scripts/dashboard-open.sh
• Load the full text of an injected learning: bash ~/.reflexio/plugin-root/scripts/cli.sh load --session <session-id> <id> (the injected index header gives the exact command)
• Show learned state: bash ~/.reflexio/plugin-root/scripts/cli.sh show
• Learn from the latest turn: bash ~/.reflexio/plugin-root/scripts/cli.sh learn
• Learn with a note: bash ~/.reflexio/plugin-root/scripts/cli.sh learn --note "<note>"
• Restart backend/dashboard: bash ~/.reflexio/plugin-root/scripts/cli.sh restart
• Clear all learned state: bash ~/.reflexio/plugin-root/scripts/cli.sh clear-all --yes

Behavior

1. Treat slash-like prompts such as /claude-smart:show as requests to run the matching shell command above.
2. For learn, preserve any user-provided note exactly as the note text.
3. For clear-all, require explicit confirmation before running it because it deletes all reflexio interactions, preferences, and skills.
4. If ~/.reflexio/plugin-root is missing or broken, rerun npx claude-smart install --host codex to repair installation, then tell the user to start a new Codex session and rerun the command.
5. After running a command, summarize the important output concisely.