pr-nurse

pr-nurse is a skill for Claude Code from mdelapenya/coding-skills. It costs 69 tokens per session (1,226 once invoked), scanned A, original, MIT.

A guide for monitoring and repairing the checks and merge status of the current branch's pull request. It can investigate build failures, bring changes from the main branch into the work, resolve conflicts, and push updates.

In plain words
What is it for?
Use it to check CI, fix build failures, merge the main branch, resolve merge conflicts, and monitor whether the pull request can be merged.
Why use it?
It helps keep a pull request moving when automated checks fail or the branch has fallen behind the main branch. It combines diagnosis with the code and branch operations needed to address the problem.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; positional $N argument.

Part of the coding-skills plugin — 5 skills shipped together

Good fit Use it to check CI, fix build failures, merge the main branch, resolve merge conflicts, and monitor whether the pull request can be merged.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mdelapenya/coding-skills/pr-nurse
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 mdelapenya/coding-skills --skill pr-nurse
Clone the repo
git clone --depth 1 https://github.com/mdelapenya/coding-skills

Made for: Claude Code.

Or install coding-skills, the plugin that ships this one along with the rest of its 5 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 pr-nurse

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/mdelapenya/coding-skills/pr-nurse"><img src="https://agentmods.dev/badge/skills/mdelapenya/coding-skills/pr-nurse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,226 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 $0.00069 $0.01226
Opus 5 $0.00034 $0.00613
Sonnet 5 $0.00014 $0.00245
Haiku 4.5 $0.00007 $0.00123

Measured 8d ago against content hash 272b666fa272, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pr-nurse 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.

skills/pr-nurse/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Nurse

Monitor and fix CI failures and merge conflicts for the current branch's pull request.

NEVER use git push --force or git push --force-with-lease. Always use a regular git push. If a push is rejected, stop and ask the user.

Supported Platforms

This skill supports multiple code hosting platforms. Each platform has its own reference file under references/ with platform-specific commands.

Currently supported:

  • GitHub — see references/github.md
  • GitLab — see references/gitlab.md

Planned:

  • Bitbucket

When invoked, first detect the platform from git remote -v, then load the corresponding reference file for platform-specific commands. If the platform is not yet supported, inform the user and stop.

Context: Worktree Setup

This skill is typically invoked from a git worktree, not the root repository. Understand the two paths:

  • Workspace (current directory): the worktree where you are editing code — pwd
  • Root repo: the main checkout where main branch lives — determined by git worktree list | head -1 | awk '{print $1}'

Always return to the workspace after any operation in the root repo.

Looping

After completing a single run (Steps 1–5), start a /loop 5m /pr-nurse to continuously monitor the PR. This ensures CI re-runs and new merge conflicts are caught automatically.

If the user invokes this skill directly (not already inside a loop), ask:

Want me to keep nursing this PR on a 5-minute loop? [Y/n]:

If confirmed, start the loop. If declined, run once and stop.

Workflow

Step 1: Detect platform and identify the PR

Run git remote -v to detect the platform, then load the corresponding reference file.

Using the platform-specific commands from the loaded reference, identify the current branch's PR and fetch its metadata (number, title, branches, mergeable status, CI status).

If no PR exists for the current branch, stop and inform the user.

Step 2: Check CI status

Inspect the CI status from Step 1. Categorize each check as passing, failing, or pending.

Read the full file on GitHub · 126 lines

Files

What ships with it

2 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.

  1. 8d ago First seen · 126 lines · 69 tokens per session scan A 272b666fa272

Subscribe to this mod's changes

pr-nurse is a skill published in the GitHub repository mdelapenya/coding-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 69 tokens to every session and 1,226 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.