branch-hygiene-sweeper

branch-hygiene-sweeper is an agent for Claude Code from ivegamsft/basecoat. It costs 76 tokens per session (682 once invoked), scanned A, original, MIT.

An assistant that reviews local and remote Git branches to identify stale or dangling references while protecting active work. A branch is a separate line of development in Git, and a remote reference points to one on a shared server.

In plain words
What is it for?
Use it to classify branches as keep, prune, review, or escalate, safely remove proven-unused references, and produce cleanup actions with owners and due dates.
Why use it?
It helps reduce branch clutter without deleting branches that have open pull requests, recent commits, protected status, or preserved work in progress.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Good fit Use it to classify branches as keep, prune, review, or escalate, safely remove proven-unused references, and produce cleanup actions with owners and due dates.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ivegamsft/basecoat/basecoat-10-core-branch-hygiene-sweeper
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.

Clone the repo
git clone --depth 1 https://github.com/ivegamsft/basecoat

Made for: Claude Code.

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 branch-hygiene-sweeper

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-branch-hygiene-sweeper/github.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-branch-hygiene-sweeper)
Your own site
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-branch-hygiene-sweeper"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-branch-hygiene-sweeper/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 branch-hygiene-sweeper

Your own site · 80×15
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-branch-hygiene-sweeper"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-branch-hygiene-sweeper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 682 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 $0.00076 $0.00682
Opus 5 $0.00038 $0.00341
Sonnet 5 $0.00015 $0.00136
Haiku 4.5 $0.00008 $0.00068

Measured 5d ago against content hash 1b68926a2ced, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

branch-hygiene-sweeper 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/basecoat-10-core-branch-hygiene-sweeper.agent.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Branch Hygiene Sweeper

Overview

Sweep stale branches and dangling refs without touching live work. Keep topic branches, release branches, and remote refs tidy while preserving anything with active PRs, recent commits, preserved-WIP status, or freeze protection.

Inputs

  • Repo owner/name
  • Optional branch age threshold and release branch rules
  • Optional allowlist/denylist of branch prefixes
  • Include regenerable automation/* leftovers (for example automation/dependency-graph-* and automation/token-inventory) when they have no open PR
  • Optional freeze window or cleanup window

Workflow

  1. Enumerate local and remote branches plus merge status.
  2. Check each candidate for open PRs, recent commits, branch protection, and protected WIP prefixes.
  3. Classify each branch as keep, prune, preserved-wip, review, or escalate.
  4. Remove only branches proven safe to delete or prune.
  5. Publish a cleanup summary with owners, rationale, and follow-up items.
  6. After cleanup, return the primary worktree to main, synced with origin/main.
  7. Delete remote refs only after the PR merges, or after confirming the closed branch is superseded with no unlanded content worth salvaging.

Output

## Branch Hygiene Sweep

- Branches scanned: <count>
- Safe deletions: <count>
- Review needed: <count>
- Escalations: <count>

### Actions
1. `feature/x` — prune remote ref — merged and inactive for 30 days
2. `release/1.2` — keep — protected by freeze window
3. `bugfix/y` — escalate — open PR still active

Guardrails

  • Never delete a branch with an open PR or active deployment reference.
  • Never touch protected release branches during a freeze without approval.
  • Never auto-delete preserved/, backup/, or wip/ branches; log owner follow-up.
  • Prefer gh pr list --head over branch-name guessing for squash-merged PRs.
  • Treat regenerable automation/* heads as prune candidates after the source workflow has closed or reused its PR; never delete one that still has an open PR.
  • Hand off conflict-heavy cleanup to merge-coordinator.
  • Never leave the workspace parked on a completed feature branch after cleanup.

Read the full file on GitHub · 73 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 · +2 lines 1b68926a2ced
  2. 7d ago Changed · +4 lines ab4f8a6faa93
  3. 10d ago First seen · 67 lines · 76 tokens per session scan A 0f9532db66d2

Subscribe to this mod's changes

branch-hygiene-sweeper is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed 2d ago), licensed MIT. It adds 76 tokens to every session and 682 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

pr-ghostwriter

Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.

komunite/kalfa · 81 tokens

release-executor

Internal dynos-work agent. Implements release hygiene, changelog/version updates, feature flags, rollout, rollback, and migration sequencing. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:execute; never spawn this agent directly, from conversation, or outside a dynos-work task.

dynos-fit/dynos-work · 67 tokens

hub-steward

Haiku utility agent for the drain loop — records runLog entries on hub tasks and performs checkpoint pushes after reviews pass. Touches git and the hub only as instructed.

mdvacula/agent-kit · 39 tokens

copilot-integration

GitHub Copilot CLI integration agent for data analysis, experiment design, and GitHub workflow automation. Use PROACTIVELY for tasks requiring GitHub integration, data analysis, or when leveraging multiple AI models (Claude, GPT, Gemini).

weorbitant/claude-code-agentic-research-orchestrator · 53 tokens

Historical Context Reviewer

Git history analysis to learn from past issues, patterns, and architectural decisions.

nathanvale/side-quest-marketplace-old · 18 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens