Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add OutThisLife/brooklyn-skills --skill babysitgit clone --depth 1 https://github.com/OutThisLife/brooklyn-skillsWrote 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/skills/outthislife/brooklyn-skills/babysit)<a href="https://agentmods.dev/skills/outthislife/brooklyn-skills/babysit"><img src="https://agentmods.dev/badge/skills/outthislife/brooklyn-skills/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/skills/outthislife/brooklyn-skills/babysit"><img src="https://agentmods.dev/badge/skills/outthislife/brooklyn-skills/babysit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00070 | $0.00654 |
| Opus 5 | $0.00035 | $0.00327 |
| Sonnet 5 | $0.00014 | $0.00131 |
| Haiku 4.5 | $0.00007 | $0.00065 |
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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Babysit
Stay on the PR after handoff until it's actually done. Being asked to babysit IS the ask to poll — but report state changes only, no heartbeats, no per-poll narration.
Loop
- Snapshot:
gh pr view <N> --json state,mergeable,mergeStateStatus,reviewDecision,statusCheckRollup,autoMergeRequestplusgh pr checks <N>. - Poll inside bounded shell loops (a single
forwithsleep 30–60between iterations), not one message per check. - React by cause:
- CI never started → kick it:
git commit --allow-empty -m "chore: kick CI" && git push. - Red caused by this branch → fix it (the
pr-readyloop), push, resume watching on the new SHA. - Flake / infra red → rerun the failed jobs; repeat until green. Note the flake in one line with the run link.
- New review threads → handle per
pr-ready(fix or reply, verify resolved via the forge API), resume.
- CI never started → kick it:
- Repeat until done. A push or rerun is progress, not an exit.
Merging
Arm automerge only when the ask says so — "set to automerge", "make CI green", or any mention of merging. A plain "babysit" / "watch it" ends at green with threads resolved: report, don't merge.
CI quirks
gh run rerunrefusing with "already running" → cancel the run first, then rerun.- A cancelled run showing "no checks reported" is pending, not red — wait for it to re-report before calling it either way.
- Rollup gates ("All required checks pass") go red because a leaf did — diagnose the leaf failure, never the gate.
Done when
Re-query the forge — don't trust that a push went green or a rerun stuck. Merged, or every check green with no unresolved threads. Fail closed: any red or open thread means keep watching. Wrap up with the PR/MR link and what the watch consumed — reruns used, kicks, fixes pushed.
Scope
- In: watching an open PR, kicking stalled CI, rerunning flakes, small branch-caused fixes, late review threads.
- Out: opening or refreshing the PR (
pr-update,cpr), full rebase/red-CI overhauls (pr-ready), other people's PRs (pr-triage), merging unasked.
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.
- 10d ago First seen · 63 lines · 70 tokens per session scan A d97496189231
babysit is a skill published in the GitHub repository OutThisLife/brooklyn-skills (191 stars, last pushed 23d ago), licensed MIT. It adds 70 tokens to every session and 654 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other skills, from other repositories
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
atmos-hooks
Atmos hooks: lifecycle events, hook kinds, command/store/git/security hooks, step/steps hooks, when: conditions, scoping and overrides, toolchain integration, --skip-hooks, and Atmos Pro/local output.
atmos-pro
Atmos Pro setup and workflows: settings.pro, GitHub OIDC, affected and inventory uploads, stack locks, pro commit, workflow dispatch, merge queues, and drift detection.
start-temps-cluster
Start (or restart) a local multi-node Temps cluster using Docker-in-Docker — one control plane + 3 worker nodes, each a privileged DinD container running its own dockerd + temps agent, wired with the real multi-host overlay (VXLAN, computecidr allocation) via tools/dev-cluster/ in whichever checkout/worktree you run…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.