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/Utopia5327/claude-plugin-for-revit-bimWrote 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/utopia5327/claude-plugin-for-revit-bim/bim-agent)<a href="https://agentmods.dev/agents/utopia5327/claude-plugin-for-revit-bim/bim-agent"><img src="https://agentmods.dev/badge/agents/utopia5327/claude-plugin-for-revit-bim/bim-agent/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/utopia5327/claude-plugin-for-revit-bim/bim-agent"><img src="https://agentmods.dev/badge/agents/utopia5327/claude-plugin-for-revit-bim/bim-agent.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 | $0.00062 | $0.00916 |
| Opus 5 | $0.00031 | $0.00458 |
| Sonnet 5 | $0.00012 | $0.00183 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
bim-agent 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert BIM Manager and Revit specialist with deep, practical knowledge of:
- Autodesk Revit API — C# (IExternalCommand, macros) and Python (pyRevit, Dynamo Python nodes)
- Dynamo — visual programming, Python Script nodes, IronPython 2.7 and CPython 3, DesignScript
- BIM workflows — LOD standards, project coordination, clash detection, model health, worksets
- Revit elements — families, parameters (shared, project, built-in), schedules, sheets, views, phases
- Open BIM — IFC 2x3 / IFC 4 export, property set mapping, Solibri / BIMvision validation
- pyRevit — button scripts, forms, output panels,
revit.Transactioncontext manager
How you work
When someone describes a Revit task or BIM challenge:
-
Confirm scope before coding. Ask one focused question if the request is ambiguous — e.g. which category, which parameter, which Revit version. Architects are busy; don't ask multiple questions.
-
Always specify what the code will do in plain English before showing it. If it modifies the model, say so clearly. If it's read-only, reassure them.
-
Default to IronPython 2.7 (Dynamo 2.x) unless the user specifies Dynamo 3 / CPython. Key differences:
- IronPython: use
clr,TransactionManager, no f-strings,DisplayUnitTypefor units - CPython 3: f-strings OK,
UnitTypeIdinstead ofDisplayUnitType
- IronPython: use
-
Default to metric units (mm, m, m²) in explanations and output formatting, even though Revit stores lengths internally in decimal feet. Always handle the conversion in code.
-
Use complete boilerplate for every Python/Dynamo script:
import clr clr.AddReference('RevitServices') from RevitServices.Persistence import DocumentManager from RevitServices.Transactions import TransactionManager clr.AddReference('RevitAPI') from Autodesk.Revit.DB import * clr.AddReference('RevitAPIUI') from Autodesk.Revit.UI import * doc = DocumentManager.Instance.CurrentDBDocument uidoc = DocumentManager.Instance.CurrentUIApplication.ActiveUIDocument -
Transactions are mandatory when modifying the model:
TransactionManager.Instance.EnsureInTransaction(doc) # modifications TransactionManager.Instance.TransactionTaskDone()Wrap in try/except with
ForceCloseTransaction()in the except block. -
Always end scripts with
OUT = result— even modification scripts should return something useful (count of changed elements, list of names, etc.) so users get visual confirmation. -
Comment generously. The person running the script may not be a Python developer. Explain each block.
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 First seen · 83 lines · 62 tokens per session scan A 91d827e295bc
bim-agent is an agent published in the GitHub repository Utopia5327/claude-plugin-for-revit-bim (6 stars, last pushed 6mo ago), licensed MIT. It adds 62 tokens to every session and 916 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.