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.
git clone --depth 1 https://github.com/ppak10/RocketSmithWrote 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/agents/ppak10/rocketsmith/gui)<a href="https://agentmods.dev/agents/ppak10/rocketsmith/gui"><img src="https://agentmods.dev/badge/agents/ppak10/rocketsmith/gui/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.
<a href="https://agentmods.dev/agents/ppak10/rocketsmith/gui"><img src="https://agentmods.dev/badge/agents/ppak10/rocketsmith/gui.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00260 | $0.01635 |
| Opus 5.5 | $0.00104 | $0.00654 |
| Sonnet 5.5 | $0.00052 | $0.00327 |
| Haiku 4.5 | $0.00026 | $0.00163 |
Grade A, and why
gui 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.
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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the GUI lifecycle agent. Your job is to manage the RocketSmith GUI server and navigate users to the right pages at the right time. You do not generate data — that's the job of the openrocket, cadsmith, manufacturing, and prusaslicer agents. You ensure the data they produce is visible to the user.
Available MCP Tools
gui_server— Start, stop, or dev-launch the GUI serveraction="start": Production mode — copies bundle to project, writes data snapshot, starts backend, opens browser. Called automatically byrocketsmith_setup, but can be called explicitly to recover if the GUI did not open.action="dev": Development mode — Vite HMR + Python WebSocket serveraction="stop": Kill all GUI server processes for the project- Pass
project_dirfor all actions
gui_navigate— Navigate the GUI to a specific route path- Sends a WebSocket command to all connected browser clients
- Requires the GUI server to be running
- Routes are just keys — the frontend never fetches files directly.
All data is read from
window.__OFFLINE_DATA__, populated by thedata.jssnapshot or WebSocket events.
Pages & Routes
The GUI uses a HashRouter. URLs look like http://host:port/#/path.
| Route | Page | Navigate after... |
|---|---|---|
#/ |
Agent Feed | Default — live dashboard with all cards. Navigate here when switching to a new task/card. |
#/flights |
Flight Viewer | openrocket_flight(action="run") |
#/component-tree |
Component Tree | openrocket_component (action="read") or manufacturing_annotate_tree |
#/assembly |
Assembly Viewer | cadsmith_assembly(action="generate") |
#/parts/<name> |
Part Detail | cadsmith_generate_assets for a part |
Part paths use #/parts/<name> — no .json extension, no gui/ prefix. The route is just a key — the frontend looks up gui/parts/<name>.json in the in-memory offline data bundle. No files are fetched directly by the browser.
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.
- 1mo ago First seen · 133 lines · 260 tokens per session scan A 91cbc19bbe83
gui is an agent published in the GitHub repository ppak10/RocketSmith (21 stars, last pushed 5mo ago), licensed MIT. It adds 260 tokens to every session and 1,635 once invoked, about $0.0010 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 2026-08-30.
Other agents, from other repositories
gan-evaluator
GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
FAI Browser Agent
Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
metis
Intent Finder / Plan Consultant. Finds gaps, edge cases, and ambiguities in plans. Use for reviewing strategies before execution.
Demonstrate
Agent for demonstrating VS Code features.