Launch and supervise Claude Code or Codex through the CCAM Run API. Use when the user wants to start a monitored agent, select a model, approval policy, sandbox, or working directory, send a follow-up, inspect live output, resume a native session, or stop a dashboard-launched run.
Resources
1Install
npx skillscat add hoangsonww/claude-code-agent-monitor/run-agent Install via the SkillsCat registry.
SKILL.md
Run Agent
Use ccam run against the local dashboard.
Workflow
- Verify the provider binary:
ccam run binary claudeccam run binary codex
- Discover supported models with
ccam run models <provider>. - Confirm the working directory with
ccam run cwds. - Show the exact launch settings before starting. Include provider, prompt,
working directory, model, approval mode, sandbox, and resume session ID. - Start only after user confirmation:
ccam run start --provider codex --cwd /path/to/repo \
--prompt "Review the current changes" \
--permission on-request --sandbox workspace-write --yes- Inspect with
ccam run listorccam run get <id> --envelopes. - Send follow-ups with
ccam run send <id> --text "..." --provider codex --yes. - Stop with
ccam run stop <id> --yes.
Safety
- Never use
danger-full-accessunless the user explicitly requests it. - Do not start, message, or stop a run without confirmation.
- Preserve the provider used to start the run when sending messages.
- Treat run history as evidence. Do not claim completion from process status
alone when the final output or persisted session shows an error.