git-branch-hygiene

git-branch-hygiene is a skill for Claude Code, Codex from rsenna/rs-agent-plugin. It costs 79 tokens per session (1,920 once invoked), scanned A, original, MIT.

A repository task that examines open Dependabot pull requests and places each into a clear status, such as safe to merge, needs testing, or outdated.

In plain words
What is it for?
It is for reviewing, merging, rebasing, or closing Dependabot pull requests after the user approves the action.
Why use it?
It gives dependency updates an evidence-based review instead of relying only on status checks or GitHub's mergeable flag.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths.

Good fit It is for reviewing, merging, rebasing, or closing Dependabot pull requests after the user approves the action.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rsenna/rs-agent-plugin/git-branch-hygiene
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 rsenna/rs-agent-plugin --skill git-branch-hygiene
Clone the repo
git clone --depth 1 https://github.com/rsenna/rs-agent-plugin

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 git-branch-hygiene

README.md
[![agentmods](https://agentmods.dev/badge/skills/rsenna/rs-agent-plugin/git-branch-hygiene/github.svg)](https://agentmods.dev/skills/rsenna/rs-agent-plugin/git-branch-hygiene)
Your own site
<a href="https://agentmods.dev/skills/rsenna/rs-agent-plugin/git-branch-hygiene"><img src="https://agentmods.dev/badge/skills/rsenna/rs-agent-plugin/git-branch-hygiene/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 git-branch-hygiene

Your own site · 80×15
<a href="https://agentmods.dev/skills/rsenna/rs-agent-plugin/git-branch-hygiene"><img src="https://agentmods.dev/badge/skills/rsenna/rs-agent-plugin/git-branch-hygiene.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,920 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 $0.00079 $0.01920
Opus 5.5 $0.00032 $0.00768
Sonnet 5.5 $0.00016 $0.00384
Haiku 4.5 $0.00008 $0.00192

Measured 1mo ago against content hash 208a1944d82a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

git-branch-hygiene 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 1mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (audit.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/git-branch-hygiene/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Branch Hygiene

The pull-request-process skill's cleanup step only removes the one worktree/branch a task just finished with — and only when explicitly run, right after a PR merges. In practice that step gets skipped constantly (session ends before merge, user moves on, a new session starts cold), so local branches and pr.sh start worktrees pile up silently across many sessions. This skill is the periodic sweep that catches all of that at once, for the whole repo — not a replacement for pull-request-process's per-task cleanup, a backstop for when it didn't happen.

Core principle

Classify everything before touching anything. A branch merged via a squash or true-merge PR is NOT an ancestor of main by git's own ancestry check — relying on git branch --merged alone silently mis-classifies those as unmerged. Always cross-check against the forge's actual PR state (gh pr list --head <branch>) when available, and only fall back to the ancestor check for branches with no PR record at all.

Never delete on inference. A branch with real commits and no PR record might be abandoned scratch work — or it might be someone's still-relevant draft that never got pushed. A worktree with uncommitted files is never safe to force-remove, no matter how old it looks. Every ambiguous case gets surfaced to the user; only clearly-merged branches get deleted without individual confirmation (and even then, as one batch confirmation showing the full list — see Step 3).

Step 1: Run the audit

audit.sh is a sibling of whatever directory this SKILL.md was loaded from — resolve it there rather than assuming a fixed install root (e.g. ~/.claude/skills/git-branch-hygiene/audit.sh, ~/.agents/skills/git-branch-hygiene/audit.sh, or a project-local .agents/skills/git-branch-hygiene/audit.sh, depending on how this skill was installed).

A=<this-skill's-own-directory>/audit.sh
"$A" [base-branch]

Read-only — fetches origin (no --prune, so it never deletes remote-tracking refs), then classifies every local branch and its worktree (if any) into four buckets:

Read the full file on GitHub · 147 lines

Files

What ships with it

1 file 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. 1mo ago First seen · 147 lines · 79 tokens per session scan A 208a1944d82a

Subscribe to this mod's changes

git-branch-hygiene is a skill published in the GitHub repository rsenna/rs-agent-plugin (2 stars, last pushed 2d ago), licensed MIT. It adds 79 tokens to every session and 1,920 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 2026-09-15.