claude-context: Skill for Claude Code

.agents/skills/pr-cleanup/SKILL.md

pr-cleanup is a skill for Claude Code, Codex from lbruton/claude-context. It costs 74 tokens per session (2,845 once invoked), scanned A, original, MIT.

A cleanup routine for Git branches and worktrees after a pull request is merged.

In plain words
What is it for?
Use it after merging a pull request to prune remote references, delete merged branches and worktrees, fast-forward main, and report what happened.
Why use it?
It removes stale local copies and references, while checking whether there is uncommitted, unpushed, or unpulled work before updating the main branch.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; positional $N argument; installed under .agents/ (shared by several agents).

This is lbruton/claude-context's own configuration. It tells Claude Code and Codex how to work on claude-context itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-context configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lbruton/claude-context. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lbruton/claude-context/master/.agents/skills/pr-cleanup/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lbruton/claude-context

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-cleanup

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/lbruton/claude-context/pr-cleanup"><img src="https://agentmods.dev/badge/skills/lbruton/claude-context/pr-cleanup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,845 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 $0.00074 $0.02845
Opus 5.5 $0.00030 $0.01138
Sonnet 5.5 $0.00015 $0.00569
Haiku 4.5 $0.00007 $0.00284

Measured 5d ago against content hash 8633f8f00bba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pr-cleanup 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 5d 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.

.agents/skills/pr-cleanup/SKILL.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Cleanup

Post-merge housekeeping. Run this after a PR has been merged to main — before /wrap. It is safe to run even if no PR was merged this session; it will just report that nothing needed cleaning.

Run the entire flow autonomously. The user invoked /pr-cleanup once — that is the permission to clean up merged state. Do NOT ask for permission between steps.


When to run

  • After a PR merged to main this session
  • When git worktree list shows stale worktrees
  • Anytime branches marked [gone] are piling up

If this session had no PR activity and no stale branches, report that briefly and exit. Do not run the full flow unnecessarily.


The Flow

Step 1 — Snapshot current state (parallel)

git fetch --prune --all
git branch -vv                          # shows [gone] branches
git worktree list
git log --oneline @{u}..HEAD 2>/dev/null   # commits ahead of origin
git log --oneline HEAD..@{u} 2>/dev/null   # commits behind origin
gh pr list --author "@me" --state merged \
  --search "merged:>=$(date -v-1d +%Y-%m-%d 2>/dev/null || date -d 'yesterday' +%Y-%m-%d)" \
  --json number,title,headRefName,mergedAt 2>/dev/null

Hold all results in working memory. Do not display yet.

Step 2 — Remove merged worktrees

For each entry in git worktree list (excluding the main worktree):

  1. Check if the worktree's branch appears in git branch -vv output as [gone] — meaning the remote branch has been deleted (i.e., merged and cleaned up by GitHub).
  2. If [gone]:
    • Check for uncommitted changes: git -C <worktree-path> status --short
    • If clean → remove the worktree: git worktree remove <worktree-path> --force
    • If dirty → do NOT remove. Add to warnings: "Worktree <path> has uncommitted changes — left intact. Review manually."
  3. If NOT [gone] (branch still exists on remote) → leave it alone, no warning needed unless it's been open for >7 days (then add a soft note).

Step 3 — Update main WITHOUT switching branches

Read the full file on GitHub · 241 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. 5d ago Changed 8633f8f00bba
  2. 9d ago Changed 34d5bef862ac
  3. 11d ago First seen · 241 lines · 74 tokens per session scan A a642774f49b6

Subscribe to this mod's changes

pr-cleanup is a skill published in the GitHub repository lbruton/claude-context (2 stars, last pushed 5d ago), licensed MIT. It adds 74 tokens to every session and 2,845 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-17.