agentmods.dev

swe:babysit-pr

swe:babysit-pr is a skill for Claude Code from ckorhonen/swe-skills. It costs 119 tokens per session (2,292 once invoked), scanned A, original, MIT.

A continuous workflow for monitoring one open pull request. A pull request is a proposed set of code changes submitted for review and automated checks.

In plain words
What is it for?
Use it to watch a pull request, apply small fixes, push updates, handle failed checks, and reach a clear merge-ready or blocked result.
Why use it?
It keeps track of new review comments, requested changes, and CI failures instead of stopping after a single review. It continues until the request is ready to merge, closed, or blocked by needed input.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the swe-skills plugin — 17 skills shipped together

not rated 3repo +1 1mo ago A scan 119 tokens original MIT

Good fit Use it to watch a pull request, apply small fixes, push updates, handle failed checks, and reach a clear merge-ready or blocked result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ckorhonen/swe-skills/babysit-pr
View source ↗ ckorhonen/swe-skills cdd.dev
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 ckorhonen/swe-skills --skill babysit-pr
Clone the repo
git clone --depth 1 https://github.com/ckorhonen/swe-skills

Made for: Claude Code.

Or install swe-skills, the plugin that ships this one along with the rest of its 17 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.

agentmods badge for swe:babysit-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/ckorhonen/swe-skills/babysit-pr/github.svg)](https://agentmods.dev/skills/ckorhonen/swe-skills/babysit-pr)
Your own site
<a href="https://agentmods.dev/skills/ckorhonen/swe-skills/babysit-pr"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/babysit-pr/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.

agentmods 80×15 button for swe:babysit-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/ckorhonen/swe-skills/babysit-pr"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/babysit-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,292 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 $0.00119 $0.02292
Opus 5 $0.00060 $0.01146
Sonnet 5 $0.00024 $0.00458
Haiku 4.5 $0.00012 $0.00229

Measured 11d ago against content hash 438e213c15f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

swe:babysit-pr 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 11d 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-pr/SKILL.md · 301 lines

How it starts

The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SWE PR Babysitting

What This Skill Does

Use this skill to take one open pull request from active review to merge-safe state with minimal manual intervention.

The job is to keep a live watch loop going, absorb new feedback, push fixes, explain disagreements when feedback is invalid, and only stop when one of these terminal states is reached:

  • the PR is ready to merge
  • the PR is merged or closed
  • a blocker requires user or reviewer input

The expected outcome is not a one-shot review. It is an active PR shepherding loop that keeps working until the branch is either safe to merge or explicitly blocked.

When To Use

Use this skill when the user wants to:

  • babysit one open PR until it is merge-ready
  • watch for review comments, change requests, and CI failures continuously
  • apply small follow-up fixes and push them without waiting for manual nudges
  • keep iterating until a reviewer or review bot gives the highest available score
  • end with a clear ready to merge or blocked outcome

Do Not Use

Do not use this skill for:

  • a one-time risk review with no ongoing watch loop
  • post-merge production impact checks
  • repo-wide CI triage without a scoped PR
  • ambiguous product or design decisions that require fresh user direction
  • unrelated worktree cleanup or broad refactors outside the PR

Inputs To Confirm

Confirm or infer:

  • the PR number, URL, or branch to watch
  • the repository scope if the PR target is ambiguous
  • whether the local checkout is clean enough to edit safely
  • whether the agent is allowed to push commits, reply on GitHub, and rerun checks
  • any no-touch files, rollout constraints, or reviewer-specific expectations

If the request is vague, ask only for the missing PR identifier needed to lock onto one PR.

Tooling Stance

Prefer GitHub-native evidence and actions:

  • gh pr view for mergeability, review decision, head branch, and head SHA
  • gh pr checks plus gh run view for CI state and failed logs
  • gh api review and comment endpoints for issue comments, inline comments, reviews, and reactions
  • the local checkout for code changes, validation, commits, and pushes

Read the full file on GitHub · 301 lines

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. 11d ago First seen · 301 lines · 119 tokens per session scan A 438e213c15f9

Subscribe to this mod's changes

swe:babysit-pr is a skill published in the GitHub repository ckorhonen/swe-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 119 tokens to every session and 2,292 once invoked, about $0.0006 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.

Claude CodeCode reviewGit and workflowReleasesagent-skillsclaude-pluginscodex
Related

Other skills, from other repositories

github-automation

GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.

ruvnet/ruflo · 61 tokens

github

GitHub via gh CLI: PRs, issues, reviews, repos, auth.

NousResearch/hermes-agent · 19 tokens

deploy-steward

Mainline deploy steward. Consumes ready PRs, owns a lease on mainline landing, refreshes PR state, updates stale branches, waits for CI and deploy gates, merges or queues one candidate at a time, and opens repair tasks for failures.

SethGammon/Citadel · 56 tokens

github

Full GitHub CLI control — issues, PRs, code reviews, repo management. Uses gh CLI with auth detection, rate limiting, and templates. Triggers on: github, issue, pull request, PR, code review, repo, branch, label, assignee, milestone, release, workflow, actions.

adolfousier/opencrabs · 0 tokens

release

Release gentle-pi through GitHub and npm. Trigger: release, publish, npm publish, GitHub release, version bump.

Gentleman-Programming/gentle-pi · 28 tokens

release-pr-review

Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…

cyanheads/obsidian-mcp-server · 139 tokens