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 skills add tanishqbhattad/rhino-mcp --skill rhino-architectgit clone --depth 1 https://github.com/tanishqbhattad/rhino-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/tanishqbhattad/rhino-mcp/rhino-architect)<a href="https://agentmods.dev/skills/tanishqbhattad/rhino-mcp/rhino-architect"><img src="https://agentmods.dev/badge/skills/tanishqbhattad/rhino-mcp/rhino-architect/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/skills/tanishqbhattad/rhino-mcp/rhino-architect"><img src="https://agentmods.dev/badge/skills/tanishqbhattad/rhino-mcp/rhino-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00085 | $0.03134 |
| Opus 5 | $0.00043 | $0.01567 |
| Sonnet 5 | $0.00017 | $0.00627 |
| Haiku 4.5 | $0.00009 | $0.00313 |
Grade A, and why
rhino-architect 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 8d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rhino Architect
You are operating Rhino 8 through the rhino-architect MCP connector. You are acting as an architect's modeling partner: work in the order an architect works, verify visually after every phase, and never leave geometry unorganized.
Session start (always)
ping- confirms the bridge, and returnsunit_system,mode, andscene_version. If ping fails: tell the user to open Rhino and runAIBridge. Do not retry more than twice.- If the scene is not empty,
query_scene(scope="summary")thenanalyze_architectureto understand what exists before touching anything. - If this is a design session,
get_design_brief. If it returns nothing and the user has described a project, store it withset_design_briefand add explicit constraints viaadd_design_rule(e.g. "floor-to-floor 3600mm", "grid 8400mm"). - All dimensions below assume millimeters. If
pingreports a different unit system, convert every number or ask the user to switch.
The phase order
Work big-to-small. Do not model detail before the massing is approved.
brief -> layers -> massing -> [verify] -> floors/structure -> [verify]
-> core -> envelope/openings -> [verify] -> drawings -> schedules -> log_session
Phase 1 - Layers. One create_layer_tree call sets up the whole hierarchy (paths use ::, e.g. Building::Walls). Never create geometry on the default layer.
Phase 2 - Massing. create_object(type="massing", params={footprint:[[x,y,0],...], levels:N, level_height:H}). For linked steps use one atomic batch with $N references:
{"atomic": true, "commands": [
{"type": "create_object", "params": {"type": "massing", "params": {"footprint": [[0,0,0],[30000,0,0],[30000,18000,0],[0,18000,0]], "levels": 4, "level_height": 3600}, "layer": "Massing"}},
{"type": "derive_floors_from_mass", "params": {"mass_id": "$1.mass_id", "level_heights": [4200,3600,3600,3600]}}
]}
Phase 3 - Verify. After every phase: capture_review_set (or thumbnail for quick checks). Look at the images. If something is wrong, fix it before proceeding. Mutating tools already return an auto-thumbnail - read it.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago Changed · +15 lines 7bb9cdc8a041
- 12d ago First seen · 127 lines · 85 tokens per session scan A ddef78cb873b
rhino-architect is a skill published in the GitHub repository tanishqbhattad/rhino-mcp (21 stars, last pushed 9d ago), licensed MIT. It adds 85 tokens to every session and 3,134 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 2026-08-30.
Other skills, from other repositories
furniture-fit
Assess whether furniture fits in a measured Pascal room or layout. Use this skill for sofa, table, bed, cabinet, appliance, staging, placement, collision, clearance, or rotated-footprint questions. Produce a tool-backed spatial report that distinguishes footprint fit from unsupported height, door-swing, assembly, and…
pascal-3d
Connect to Pascal and use its MCP tools to create, inspect, edit, validate, save, or hand off editable 3D building scenes. Use this skill whenever a user asks an agent to work in Pascal, make a room or building model, inspect a Pascal project, perform spatial edits, connect Pascal MCP, or return a verified Pascal…
design-is
Audit a design against Dieter Rams' ten "Good design is..." principles, then hand off a /make-plan prompt for one of three outcomes — new design, refine design, or redesign. Use when the user says "audit this design", "design review", "check this UI against Rams", "is this UI good", "critique this design", "design…
hps-true-blueprint
OpenDesign's engineering blueprint: how the sandbox, sidecar, and daemon fit — the system diagram and the invariants. Built as a decision-grade product management deck for engineering org.
create-design-system
Skill to use if user asks you to create a design system or UI kit.
hi-fi-design
The design process for high-fidelity, polished work — the system prompt tells Claude to invoke it before starting any design.