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.
npx agentmods add skills/proxiblue/pb-hypernode-mcp/brancher-prototypenpx skills add ProxiBlue/pb-hypernode-mcp --skill brancher-prototypegit clone --depth 1 https://github.com/ProxiBlue/pb-hypernode-mcpWrote 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.
[](https://agentmods.dev/skills/proxiblue/pb-hypernode-mcp/brancher-prototype)<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>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.
| Model | Per session | Once 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 |
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.
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_execheredocs (preferred, since the command and its result are both visible in the session transcript) orbrancher_putfor 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 localgit statuscheck 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-spinupextends 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_putpaths must contain no shell metacharacters. Bothlocal_pathandremote_pathare 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/codeorapp/design. Anything touched underGIT_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 inPROTOTYPE_NOTES.mdin enough detail that the ticket reader could reconstruct it, because the diff alone will not show it.
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.
- 3d ago First seen · 324 lines · 74 tokens per session scan A 488795e8a091
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.
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…
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…
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.
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".
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…
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.