brancher-cleanup

brancher-cleanup is a skill for Claude Code from ProxiBlue/pb-hypernode-mcp. It costs 42 tokens per session (2,213 once invoked), scanned A, original, Apache-2.0.

A workflow for finding and deleting old Hypernode Brancher preview copies. These copies keep counting wall-clock minutes even when nobody is using them.

In plain words
What is it for?
Use it to identify nodes older than a chosen age, report their usage, and delete stale previews.
Why use it?
It helps prevent forgotten temporary environments from continuing to consume the application's Brancher minutes.

Skill for Claude Code

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

Part of the pb-hypernode-mcp plugin — 4 skills, 1 MCP server shipped together

Good fit Use it to identify nodes older than a chosen age, report their usage, and delete stale previews.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/proxiblue/pb-hypernode-mcp/brancher-cleanup
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 ProxiBlue/pb-hypernode-mcp --skill brancher-cleanup
Clone the repo
git clone --depth 1 https://github.com/ProxiBlue/pb-hypernode-mcp

Made for: Claude Code.

Or install pb-hypernode-mcp, the plugin that ships this one along with the rest of its 4 skills, 1 MCP server.

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 brancher-cleanup

README.md
[![agentmods](https://agentmods.dev/badge/skills/proxiblue/pb-hypernode-mcp/brancher-cleanup.svg)](https://agentmods.dev/skills/proxiblue/pb-hypernode-mcp/brancher-cleanup)
Your own site
<a href="https://agentmods.dev/skills/proxiblue/pb-hypernode-mcp/brancher-cleanup"><img src="https://agentmods.dev/badge/skills/proxiblue/pb-hypernode-mcp/brancher-cleanup.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,213 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 $0.00042 $0.02213
Opus 5 $0.00021 $0.01107
Sonnet 5 $0.00008 $0.00443
Haiku 4.5 $0.00004 $0.00221

Measured 7d ago against content hash bb0d95f47244, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

brancher-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 7d 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/brancher-cleanup/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brancher Cleanup

Brancher nodes bill wall-clock minutes from creation regardless of whether anyone is actively using them — an idle node still burns the app's Brancher minute allowance. This skill finds nodes that have been alive past a configurable age threshold and removes them, safely.

Age threshold

Default: 240 minutes (4 hours) — the sample threshold used in Hypernode's own Brancher documentation. It is only a starting point:

  • Ask the user for a threshold if they haven't given one, but default to 240 minutes if they have no preference.
  • A shorter threshold (e.g. 60 minutes) is appropriate for a team that spins up short-lived preview nodes throughout the day and forgets to close them.
  • A longer threshold (e.g. 480 minutes / 8 hours) is appropriate if nodes routinely stay open across a working day for review.

The actual "is this node past the threshold" decision is NOT prose — it is the pure function flag_stale_nodes(nodes, threshold_minutes) in src/pb_hypernode_mcp/cleanup_logic.py (unit-tested in tests/test_cleanup_logic.py). Conceptually: a node is flagged when its minutes value is >= threshold_minutes. When calling the MCP tools below, apply that same >= rule when deciding what to show the user as "flagged".

Flow

  1. Identify which Hypernode/app. If the user's request doesn't say which app to target, call brancher_apps first and show the configured list — never guess an appname. If exactly one app is configured, it's fine to proceed with it; just tell the user which one you're using rather than asking a pointless confirmation question. Only after this, move to step 2.

  2. List. Call brancher_list with the app name. Each node returned has name, host, and minutes (wall-clock minutes alive, not idle-aware).

  3. Report full list with minutes. Show the user every active node and its minutes value, so they can see the cost being avoided by cleanup — not just the flagged subset.

  4. Flag. Apply the age-threshold rule (minutes >= threshold_minutes, same logic as flag_stale_nodes) to the list from step 2.

Read the full file on GitHub · 178 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. 7d ago First seen · 178 lines · 42 tokens per session scan A bb0d95f47244

Subscribe to this mod's changes

brancher-cleanup is a skill published in the GitHub repository ProxiBlue/pb-hypernode-mcp (0 stars, last pushed 11d ago), licensed Apache-2.0. It adds 42 tokens to every session and 2,213 once invoked, about $0.0002 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 skills, from other repositories

gke-compute-classes

Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…

google/skills · 83 tokens

gke-reliability

Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).

google/skills · 73 tokens

gke-workload-security

Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…

google/skills · 181 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens

azure-mgmt-botservice-dotnet

Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".

microsoft/skills · 78 tokens

cloud-architect

Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…

Jeffallan/claude-skills · 71 tokens