A workflow skill that watches a pull request, a proposed code change submitted for review, until configured checks and feedback show it is ready. It can also follow configured steps for merging and cleanup.

It is for monitoring pull requests, handling review feedback through the review-response workflow, rerunning required checks, and optionally merging or closing out the work.

It removes the need to repeatedly check review comments, continuous-integration checks, and the pull request's final status by hand.

babysit — Skill for Claude Code and Codex by sandsower: A workflow skill that watches a pull request, a…

Install

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.

agentmods

npx agentmods add skills/sandsower/beislid/babysit

Any agent

npx skills add sandsower/beislid --skill babysit

Clone the repo

git clone --depth 1 https://github.com/sandsower/beislid

Made for: Claude Code, Codex.

Or install beislid, the plugin that ships this one along with the rest of its 22 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sandsower/beislid/babysit.svg)](https://agentmods.dev/skills/sandsower/beislid/babysit)

Your own site

<a href="https://agentmods.dev/skills/sandsower/beislid/babysit"><img src="https://agentmods.dev/badge/skills/sandsower/beislid/babysit.svg" alt="Measured on agentmods" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,034 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00062	$0.02034
Opus 5	$0.00031	$0.01017
Sonnet 5	$0.00012	$0.00407
Haiku 4.5	$0.00006	$0.00203

Measured 4d ago against content hash 3b437962923e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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.

skills/babysit/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Babysit

Babysit the current pull request until configured live evidence says it is green, then perform the configured closeout path when policy allows it.

This is an outer-loop workflow. It does not replace review-response; it repeatedly uses review-response for feedback handling, configured gates for proof before push, and optional host persistence for wait/recheck cycles.

Persistence model

babysit can run directly in any host. Goal/persistence support is optional, not a hard requirement.

In Claude Code, users may manually wrap babysit in /goal for cross-wait persistence.
In Pi, bundled /babysit starts a Beislið-owned babysit runtime with loop state and completion tools. It does not depend on pi-goal or invoke slash commands from another extension.
Without persistence, perform the current audit/feedback/gate step. If the PR is not terminal green or blocked by turn end, stop with evidence and the next recheck/action.

Inputs

Use, in order:

invocation args such as stop when green, merge, don't merge, skip memento, skip retro, or skip cleanup
.beislid/workflow.md
current branch PR metadata from configured PR host tooling when available
configured pr_review_source and pr_review_update
configured gates, scopes, or gate sets
configured babysit closeout policy
optional review_policy AgenticReviewer risk/opt-in policy

Configuration

Optional workflow block:

goal:
  token_budget: 50k
loop:
  use_review_response: true
  run_configured_gates_before_push: true
  wait_interval_seconds: 60
  timeout_minutes: 60
closeout:
  merge:
    mode: ask # off | ask | auto
    method: squash # squash | merge | rebase | repo-default
    delete_branch: true
  memento:
    mode: ask # off | ask | auto
  retro:
    mode: ask # off | ask | auto
    apply_findings: ask # off | ask | auto
  cleanup:
    mode: ask # off | ask | auto; follows merge.mode when unset

Defaults when absent: no goal budget, use review-response, run configured gates before pushes, merge/memento/retro off, and cleanup following merge.mode. Invocation args override config for this run.

Read the full file on GitHub · 118 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

4d ago First seen · 118 lines · 62 tokens per session scan A 3b437962923e

Subscribe to this mod's changes

babysit is a skill published in the GitHub repository sandsower/beislid (10 stars, last pushed 5d ago), licensed MIT. It adds 62 tokens to every session and 2,034 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 2026-08-31.

Code review Git and workflow

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens