Menu
Start a babysitter orchestration run. Use this command to start babysitting a complex workflow.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Orchestrate complex, multi-step AI workflows with quality convergence loops, event-sourced state, and human-in-the-loop approval gates. Use when the user wants to babysit a task, orchestrate a workflow, run quality-gated development, resume a previous orchestration run, diagnose run health, plan without executing, set up a project or user profile for babysitter, or assimilate an external methodology. Also use when the user mentions "babysitter", "orchestrate", "babysit", "quality loop", or "convergence loop".
Help and documentation for babysitter commands, processes, skills, agents, and methodologies.
Plan a babysitter workflow without executing it. Focus on creating the best process possible.
Install or refresh a team-pinned babysitter runtime/content setup from lockfile.
Analyze a completed or in-flight run and propose process improvements for future runs.
Drive feature development using Outside-In TDD with Hexagonal Architecture. Design emerges through inline code, in-memory fakes, interface extraction, and deferred I/O. Use when building features, writing tests, or structuring backend services. Triggers on: TDD, outside-in, hexagonal, ports and adapters, emergent design, acceptance test, component test, walking skeleton, in-memory fakes, component, contract test, adapter, fast tests, sub-second feedback. Language-agnostic (Go, Rust, Python, TypeScript, Java, C#).
| name | babysitter:call |
| description | Start a babysitter orchestration run. Use this command to start babysitting a complex workflow. |
| argument-hint | Specific instructions for the run |
Orchestrate .a5c/runs/<runId>/ through iterative execution. Use the babysitter SDK CLI to drive the orchestration loop inside Codex CLI.
Ensure babysitter CLI is available:
npx -y @a5c-ai/babysitter-sdk@0.0.173 version --json
Gather user intent, requirements, goals, and scope. Research the repo structure, search the process library for relevant specializations and methodologies.
Create the process .js file with task definitions. Install @a5c-ai/babysitter-sdk in .a5c/package.json if not present.
When searching for reusable processes, skills, and agents:
.a5c/processesupstream/babysitter/skills/babysit/processupstream/babysitter/skills/babysit/referenceOverride process root with BABYSITTER_PROCESS_LIBRARY_ROOT when needed.
babysitter run:create \
--process-id <id> \
--entry <path>#<export> \
--inputs <inputs-file> \
--prompt "$PROMPT" \
--harness codex \
--session-id "${CODEX_THREAD_ID:-$CODEX_SESSION_ID}" \
--plugin-root "$CODEX_PLUGIN_ROOT" \
--json
babysitter run:iterate .a5c/runs/<runId> --json --iteration <n> --plugin-root "$CODEX_PLUGIN_ROOT"
For each pending task:
Write result value to a separate file, then post via CLI:
babysitter task:post .a5c/runs/<runId> <effectId> \
--status ok \
--value tasks/<effectId>/output.json \
--json
When run:iterate returns status: "completed" with a completionProof, the run is done. Return the proof wrapped in <promise>PROOF</promise> to signal completion.
Read user profile for personalization:
babysitter profile:read --user --json
babysitter profile:read --project --json
| Command | Description |
|---|---|
run:create | Create and bind a new run |
run:iterate | Get next pending tasks |
run:status | Check run state |
task:list --pending | List pending effects |
task:post | Post task result |
session:resume | Resume existing session |
skill:discover | Find available skills/agents |
health --json | SDK health check |