Borrowing it
Nothing to install: this file belongs to jleechanorg/agent-orchestrator-ts. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jleechanorg/agent-orchestrator-ts/main/.claude/commands/babysit.mdgit clone --depth 1 https://github.com/jleechanorg/agent-orchestrator-tsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/jleechanorg/agent-orchestrator-ts/babysit)<a href="https://agentmods.dev/commands/jleechanorg/agent-orchestrator-ts/babysit"><img src="https://agentmods.dev/badge/commands/jleechanorg/agent-orchestrator-ts/babysit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/jleechanorg/agent-orchestrator-ts/babysit"><img src="https://agentmods.dev/badge/commands/jleechanorg/agent-orchestrator-ts/babysit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00029 | $0.00452 |
| Opus 5.5 | $0.00012 | $0.00181 |
| Sonnet 5.5 | $0.00006 | $0.00090 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
babysit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/babysit — Bring all PRs to green
Invoke the babysit skill protocol:
- Survey: List all open PRs with
gh pr list --state open - Classify: Sort into merge-ready / needs-fix / blocked / stale
- Dispatch: Spawn parallel AO workers for all independent needs-fix PRs
- Monitor: Collect results, push fixes, re-survey
See .claude/skills/babysit/SKILL.md for full protocol.
Arguments
/babysit— Full survey + dispatch/babysit --status— Survey only, no dispatch (just report classification)/babysit --fix N— Deep-dive on specific PR N (after survey)/babysit --driver N— DRIVER mode: take ownership of PR N, iterate until ALL gates pass (CI green + CR APPROVED). Does not exit until done or explicitly blocked.
DRIVER mode contract
When a babysit-spawned AO worker is in DRIVER mode for PR N, it MUST:
- Fix all outstanding issues in one batch — read ALL CR comments and ALL CI failures BEFORE making any edits. Fix everything in a single commit. Never push after fixing one item and wait for CI to find the next.
- Iterate until actually fixed — after each push, wait for CI + CR to settle, then re-survey. If new issues surface, fix all of them again in one batch. Repeat until all 6 green gates pass.
- Never exit with "attempted" — "I tried X" is not done. The worker exits only when: (a) 6-green confirmed, or (b) blocked on a genuine external dependency (merge conflict with another PR, external service outage, explicit user instruction to stop).
- Report blockers explicitly — if blocked, post: "BLOCKED: — needs: ". Never silent exit.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 32 lines · 29 tokens per session scan A 8697d48dea4f
babysit is a command published in the GitHub repository jleechanorg/agent-orchestrator-ts (8 stars, last pushed 3d ago), licensed MIT. It adds 29 tokens to every session and 452 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-02.
Other commands, from other repositories
speckit.spex.submit
Push and create PR for team review, with optional watch mode for CI monitoring.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
release-tag
Create and push a version tag after a release PR has been merged.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
code-review
Code review for branch changes. Analyzes git diff between branches with multi-level depth (low/medium/high). Matches changes against task description. Returns structured report with severity levels and verdict.