Best use case
babysitter:resume is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Resume orchestrating an existing babysitter run.
Teams using babysitter:resume should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/resume/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How babysitter:resume Compares
| Feature / Agent | babysitter:resume | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Resume orchestrating an existing babysitter run.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# babysitter:resume
Resume an existing babysitter orchestration run that was paused, interrupted, or left incomplete.
## Workflow
### 1. Find the Run
If a selector is provided, use the session index:
- `recent` -> most recently updated session
- `tag:<tag>` -> latest session tagged with `<tag>`
- `search:<query>` -> latest session matching alias/tag/session id
- `list` -> return indexed sessions
- `name <alias>` -> set alias on most recent session
- `tag +<tag>` / `tag -<tag>` -> add/remove tag on most recent session
If no selector is provided, default to `recent`.
For fallback/manual mode, discover incomplete runs:
```bash
babysitter run:status --runs-dir .a5c/runs --json
```
Look for runs with `status: "waiting"` or `status: "executed"` (not completed/failed). Suggest the most recent incomplete run.
### 2. Resume the Session
```bash
babysitter session:resume \
--session-id "${CODEX_THREAD_ID:-$CODEX_SESSION_ID}" \
--state-dir "$CODEX_PLUGIN_ROOT/skills/babysitter/state" \
--run-id <runId> \
--runs-dir .a5c/runs \
--json
```
### 3. Continue the Iteration Loop
Resume iterating from the current state:
```bash
babysitter run:iterate .a5c/runs/<runId> --json --iteration <n> --plugin-root "$CODEX_PLUGIN_ROOT"
```
Handle pending effects as in `/babysitter:call`:
- Execute agent/node/shell/skill tasks
- Handle breakpoints (interactive or auto-approve)
- Post results via `task:post`
### 4. Completion
When `completionProof` is emitted, return it wrapped in `<promise>PROOF</promise>`.Related Skills
babysitter
Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)
resume
Resume an existing Babysitter run from Codex.
resume-screening
Intelligent resume parsing and candidate screening with bias-reduction capabilities
babysitter:observe
Launch the babysitter observer dashboard for real-time run monitoring.
babysitter:yolo
Start babysitting in non-interactive mode — no user interaction or breakpoints, fully autonomous execution.
babysitter:project-install
Set up a project for babysitting. Research the codebase, build project profile, install tools.
babysitter:user-install
Set up babysitter for yourself. Install deps, build user profile, configure tools.
babysitter-codex
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".
babysitter:model
Set or view model routing policy for plan/execute/review phases.
babysitter:retrospect
Analyze a completed or in-flight run and propose process improvements for future runs.
babysitter:plan
Plan a babysitter workflow without executing it. Focus on creating the best process possible.
babysitter:help
Help and documentation for babysitter commands, processes, skills, agents, and methodologies.