PR babysit (watch & drive to green)

PR babysit (watch & drive to green) is a skill for Claude Code, Codex from AuraVixStudio/caelo. It costs 36 tokens per session (385 once invoked), scanned A, original, Apache-2.0.

A workflow for monitoring a GitHub pull request, which is a proposed set of code changes, until its automated checks pass and review comments are handled.

In plain words
What is it for?
Use it to inspect pull-request checks, mergeability, and review comments, then delegate fixes and recheck the result. It requires GitHub access through its MCP server or the gh command-line tool.
Why use it?
It removes the need to repeatedly check CI results and coordinate fixes manually.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to inspect pull-request checks, mergeability, and review comments, then delegate fixes and recheck the result. It requires GitHub access through its MCP server or the gh command-line tool.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/auravixstudio/caelo/pr-babysit
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.

Any agent
npx skills add AuraVixStudio/caelo --skill pr-babysit
Clone the repo
git clone --depth 1 https://github.com/AuraVixStudio/caelo

Made for: Claude Code, Codex.

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.

agentmods badge for PR babysit (watch & drive to green)

README.md
[![agentmods](https://agentmods.dev/badge/skills/auravixstudio/caelo/pr-babysit.svg)](https://agentmods.dev/skills/auravixstudio/caelo/pr-babysit)
Your own site
<a href="https://agentmods.dev/skills/auravixstudio/caelo/pr-babysit"><img src="https://agentmods.dev/badge/skills/auravixstudio/caelo/pr-babysit.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 385 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.00385
Opus 5 $0.00018 $0.00192
Sonnet 5 $0.00007 $0.00077
Haiku 4.5 $0.00004 $0.00038

Measured 8d ago against content hash 630f53e47705, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

PR babysit (watch & drive to green) 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 8d 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.

caelo_core/skills/builtin/pr-babysit/SKILL.md · 34 lines

What it actually says

PR babysit (watch & drive to green)

Use this to shepherd a pull request to a mergeable state: monitor checks and review comments, and delegate fixes as needed.

Dependency: this skill needs read access to the PR — either the GitHub MCP server enabled, or the gh CLI available to the tester/run_command tool. If neither is configured, tell the user and stop.

Loop

  1. Fetch status. Get the PR's CI checks, mergeability, and review comments via the GitHub MCP tools, or gh pr view <n> --json ... / gh pr checks <n> through run_command.
  2. Triage.
    • CI failing -> delegate a tester (or implementer) to reproduce, diagnose, and fix.
    • Changes requested in review -> delegate an implementer to address each comment.
    • Green + approved -> you are done.
  3. Re-check. After fixes are merged in, fetch status again.
  4. Repeat steps 1–3 until the PR is green and approved, or you hit the round limit.
  5. Summarize. Report the final PR state and what was changed.

Notes

  • Do not merge or close the PR yourself — surface the green/approved state and let the user merge.
  • Keep polling bounded (respect the round/turn limits); report progress between rounds.
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.

  1. 8d ago First seen · 34 lines · 36 tokens per session scan A 630f53e47705

Subscribe to this mod's changes

PR babysit (watch & drive to green) is a skill published in the GitHub repository AuraVixStudio/caelo (24 stars, last pushed 26d ago), licensed Apache-2.0. It adds 36 tokens to every session and 385 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

error-collection

A structured record of confirmed engineering mistakes, their root causes, and checks that prevent them from returning. It uses evidence from real application behavior, not just successful builds.

lfyxhappy/lfcode · 30 tokens

contract-test-engineer

Use when the user asks to verify compatibility between an API provider and consumer, SDK and service, event producer and consumer, schema versions, or serialized data. Define and test the shared contract, including failures and compatibility rules, before changing either side.

lfyxhappy/lfcode · 54 tokens

e2e-test-engineer

Use when the user asks to create, improve, review, or repair end-to-end tests for a meaningful user workflow across the UI, runtime, backend, or installed application. Validate the real workflow at the highest useful boundary while keeping environments, accounts, and test data controlled.

lfyxhappy/lfcode · 62 tokens

flaky-test-triage

Use when a test passes and fails intermittently, behaves differently by order, machine, runtime, timing, or retry, or when the user asks to reduce test flakiness. Gather repeatable evidence, isolate nondeterminism, and repair the causal dependency without weakening test intent.

lfyxhappy/lfcode · 63 tokens

git-release-manager

Use when the user explicitly asks to prepare, tag, publish, push, or audit a Git release. Inspect branch, worktree, version metadata, changelog, tests, and release artifacts first, obtain confirmation for irreversible release actions, and record a recovery path.

lfyxhappy/lfcode · 57 tokens

integration-test-engineer

Use when the user asks to create, improve, review, or repair integration tests across modules, services, storage, queues, filesystems, or framework adapters. Exercise a real integration boundary with controlled dependencies, lifecycle cleanup, and evidence that the components work together.

lfyxhappy/lfcode · 57 tokens