brancher-prototype

brancher-prototype is a skill for Claude Code, Codex from ProxiBlue/pb-hypernode-mcp. It costs 74 tokens per session (4,510 once invoked), scanned A, original, Apache-2.0.

A fast prototyping workflow on a temporary Hypernode Brancher copy of a Magento site. It records the work and turns the resulting code changes into a GitHub scoping ticket before the copy is deleted.

In plain words
What is it for?
Use it to try rough ideas, capture notes and changes, create a follow-up scope ticket, and remove the disposable preview.
Why use it?
It gives teams a place to test an idea quickly while preserving what was learned after the temporary environment is gone.

Skill for Claude CodeCodex

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

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.

agentmods
npx agentmods add skills/proxiblue/pb-hypernode-mcp/brancher-prototype
Any agent
npx skills add ProxiBlue/pb-hypernode-mcp --skill brancher-prototype
Clone the repo
git clone --depth 1 https://github.com/ProxiBlue/pb-hypernode-mcp

Made for: Claude Code, Codex.

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-prototype

README.md
[![agentmods](https://agentmods.dev/badge/skills/proxiblue/pb-hypernode-mcp/brancher-prototype.svg)](https://agentmods.dev/skills/proxiblue/pb-hypernode-mcp/brancher-prototype)
Your own site
<a href="https://agentmods.dev/skills/proxiblue/pb-hypernode-mcp/brancher-prototype"><img src="https://agentmods.dev/badge/skills/proxiblue/pb-hypernode-mcp/brancher-prototype.svg" alt="Measured on agentmods" 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 4,510 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00074 $0.04510
Opus 5 $0.00037 $0.02255
Sonnet 5 $0.00015 $0.00902
Haiku 4.5 $0.00007 $0.00451

Measured 3d ago against content hash 488795e8a091, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brancher-prototype 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 3d 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-prototype/SKILL.md · 324 lines

How it starts

The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brancher Prototype

A throwaway idea-testing loop that trades code quality for speed on a single disposable Brancher node, then converts whatever was learned into a persistent GitHub scoping ticket before the node disappears. This skill reuses brancher-preview's spin-up step and its build-command logic — it does not duplicate the create -> wait -> sanitize sequence, and it does not replace brancher-cleanup's deletion mechanics. What it adds on top: a ground-rules statement for working fast and dirty ON THE NODE ONLY, a notes-first iteration discipline so ideas survive the node, and a harvest step that turns the node's git diff into a ticket via src/pb_hypernode_mcp/prototype_logic.py's tested functions.

Prototype-mode ground rules

Prototype mode suspends this project's normal TDD workflow, coding standards, and plan-orchestration pipeline — but only for code written on the disposable -eph node, never for this repo's own source. Standards resume immediately for anything that graduates out of a prototype (via a real plan/task, not by copy-pasting the hack as-is).

  • Write the smallest hack that demonstrates the idea. Skip tests, skip declare(strict_types=1) discipline, skip PSR-12, skip DI-over-rewrite — none of that matters for code that is going to be destroyed with the node.
  • All edits happen on-node, via brancher_exec heredocs (preferred, since the command and its result are both visible in the session transcript) or brancher_put for pushing a whole file up. Never edit the local repo to test a prototype idea — the local checkout is not disposable, and any edit there would show up as unexplained dirt in the harvest step's local git status check below.
  • Be honest about what "prototype mode suspends standards" actually means: this is a prompt-level convention, not an enforced sandbox boundary. Nothing stops an AI session from writing production-grade code on the node anyway, and nothing stops a careless edit from touching the local repo instead of the node — there is no mechanism here that makes either mistake structurally impossible, only prose asking you not to make it (the same honesty brancher-spinup extends to its own sanitization guardrails: sanitization commands are enforced by the underlying tool, but this skill's "hack fast, hack on-node only" convention is not).
  • brancher_put paths must contain no shell metacharacters. Both local_path and remote_path are known injection sinks if either string is built from untrusted input — always pass a plain literal path, never something assembled by string-concatenating user-supplied text.
  • Prefer hacking under app/code or app/design. Anything touched under GIT_EXCLUDED_PATHS (vendor, generated, var, pub/static, pub/media, node_modules) will not appear in the harvest diff — the harvest step only lists those paths as changed (detect_excluded_path_changes()), it never diffs their content. If a hack under one of those paths is worth keeping, describe what it actually did in PROTOTYPE_NOTES.md in enough detail that the ticket reader could reconstruct it, because the diff alone will not show it.

Read the full file on GitHub · 324 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. 3d ago First seen · 324 lines · 74 tokens per session scan A 488795e8a091

Subscribe to this mod's changes

brancher-prototype is a skill published in the GitHub repository ProxiBlue/pb-hypernode-mcp (0 stars, last pushed 7d ago), licensed Apache-2.0. It adds 74 tokens to every session and 4,510 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 skills, from other repositories

nemoclaw-contributor-implement-issue

Implement an accepted NemoClaw GitHub issue in the current checkout. Use when a user asks to pick up an issue for implementation, implement or fix a named issue, or add the issue's tests. Confirm accepted scope, deliver the smallest independently valuable capability slice, and record validation and remaining gates…

NVIDIA/NemoClaw · 134 tokens

amazon-reviews-api-skill

This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…

browser-act/skills · 124 tokens

amazon-competitor-analyzer

Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.

browser-act/skills · 48 tokens

weekly-report

Structure and data sources for the weekly inventory report. Load this when the task is "weekly report", "Monday report", or "summarize inventory status".

anthropics/cwc-workshops · 35 tokens

shopify-functions

Shopify Functions allow developers to customize the backend logic that powers parts of Shopify. Available APIs: Discount, Cart and Checkout Validation, Cart Transform, Pickup Point Delivery Option Generator, Delivery Customization, Fulfillment Constraints, Local Pickup Delivery Option Generator, Order Routing Location…

Shopify/Shopify-AI-Toolkit · 61 tokens

asc-subscription-localization

Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.

rorkai/app-store-connect-cli-skills · 60 tokens