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 commands/demolinator/revit-mcp-plugin/design-buildinggit clone --depth 1 https://github.com/Demolinator/revit-mcp-pluginWrote 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/commands/demolinator/revit-mcp-plugin/design-building)<a href="https://agentmods.dev/commands/demolinator/revit-mcp-plugin/design-building"><img src="https://agentmods.dev/badge/commands/demolinator/revit-mcp-plugin/design-building.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 5.1 | $0.00007 | $0.01013 |
| Opus 5 | $0.00003 | $0.00507 |
| Sonnet 5 | $0.00001 | $0.00203 |
| Haiku 4.5 | $0.00001 | $0.00101 |
Grade A, and why
design-building 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 5d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guide the user through designing a complete building in Revit. This is an interactive, multi-step workflow.
Phase 1: Understand the Brief
Ask the user what they want to build. Gather:
- Building type (residential, commercial, institutional, mixed-use)
- Approximate footprint dimensions (length x width in meters)
- Number of floors
- Key spaces needed (rooms, lobbies, corridors)
- Any style or material preferences
If the user provided a description via $ARGUMENTS, use that as the starting brief. Ask only for missing details.
Phase 2: Verify Revit Connection
Call get_revit_status to confirm Revit is connected and a project is open. If it fails, tell the user to open Revit with pyRevit loaded and a project open.
Phase 3: Query Available Types
Call list_families and list_family_categories to discover available types for:
- Walls (exterior and interior types)
- Structural columns
- Doors and windows
- Floors and roofs
Present a summary of available types to the user. Let them choose or recommend defaults.
Phase 4: Create Elements in Sequence
Follow the building design sequence strictly:
- Levels — Define floor-to-floor heights using
create_level - Grids — Establish the structural grid using
create_grid - Columns — Place at grid intersections using
place_family - Beams — Connect columns using
create_structural_framing - Exterior walls — Trace the building perimeter using
create_line_based_element - Interior walls — Partition rooms using
create_line_based_element - Doors — Place on walls using
place_family - Windows — Place on exterior walls using
place_family - Floors — Create floor slabs using
create_surface_based_element - Roof — Create roof using
create_surface_based_element
After each major step, tell the user what was created and ask if they want adjustments before continuing.
Phase 5: Documentation
- Call
create_dimensionsto add key dimensions - Call
tag_wallsto add wall tags - Call
create_scheduleto create element schedules (wall, door, window) - Call
create_sheetto create drawing sheets - Call
export_documentto export views to PDF or PNG - Call
color_splashto visualize element categories
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.
- 5d ago First seen · 75 lines · 7 tokens per session scan A e757050ed242
design-building is a command published in the GitHub repository Demolinator/revit-mcp-plugin (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 7 tokens to every session and 1,013 once invoked, about $0.0000 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.