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 Utopia5327/claude-plugin-for-revit-bim --skill clash-detectiongit 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/skills/utopia5327/claude-plugin-for-revit-bim/clash-detection)<a href="https://agentmods.dev/skills/utopia5327/claude-plugin-for-revit-bim/clash-detection"><img src="https://agentmods.dev/badge/skills/utopia5327/claude-plugin-for-revit-bim/clash-detection/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/utopia5327/claude-plugin-for-revit-bim/clash-detection"><img src="https://agentmods.dev/badge/skills/utopia5327/claude-plugin-for-revit-bim/clash-detection.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 | $0.00133 | $0.01319 |
| Opus 5 | $0.00067 | $0.00660 |
| Sonnet 5 | $0.00027 | $0.00264 |
| Haiku 4.5 | $0.00013 | $0.00132 |
Grade A, and why
clash-detection scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clash Detection & Coordination
Perform clash detection for:
"$ARGUMENTS"
Before scripting
Clarify:
- Which two disciplines are you checking? (e.g. structural columns vs MEP ducts)
- How should clashes be reported? (list of IDs, CSV export, isolate in view?)
- Minimum clash volume? Default threshold is very small (1e-6 ft³) to catch all contacts.
Note: for large models, Boolean intersection on every element pair is slow. Recommend running on a specific level or workset, or using Navisworks for production-scale clash detection.
Clash detection script
Read-only — no model modifications.
import clr
clr.AddReference('RevitServices')
from RevitServices.Persistence import DocumentManager
clr.AddReference('RevitAPI')
from Autodesk.Revit.DB import *
doc = DocumentManager.Instance.CurrentDBDocument
# ── Define the two element sets to check ────────────────────────────────────
# Modify these categories for your discipline combination:
set_a = list(FilteredElementCollector(doc)
.OfCategory(BuiltInCategory.OST_StructuralColumns)
.WhereElementIsNotElementType()
.ToElements())
set_b = list(FilteredElementCollector(doc)
.OfCategory(BuiltInCategory.OST_DuctCurves)
.WhereElementIsNotElementType()
.ToElements())
# ── Helper: extract solid geometry from an element ──────────────────────────
def get_solid(element):
opts = Options()
opts.ComputeReferences = False
opts.DetailLevel = ViewDetailLevel.Fine
geo = element.get_Geometry(opts)
if geo is None:
return None
for obj in geo:
if isinstance(obj, Solid) and obj.Volume > 1e-9:
return obj
if isinstance(obj, GeometryInstance):
for sub in obj.GetInstanceGeometry():
if isinstance(sub, Solid) and sub.Volume > 1e-9:
return sub
return None
# ── Run clash detection ──────────────────────────────────────────────────────
clashes = []
try:
for el_a in set_a:
solid_a = get_solid(el_a)
if solid_a is None:
continue
# Get type name once per el_a (minor optimisation)
type_id_a = el_a.GetTypeId()
type_name_a = (doc.GetElement(type_id_a).Name
if type_id_a != ElementId.InvalidElementId else 'N/A')
for el_b in set_b:
solid_b = get_solid(el_b)
if solid_b is None:
continue
try:
intersection = BooleanOperationsUtils.ExecuteBooleanOperation(
solid_a, solid_b, BooleanOperationsType.Intersect)
if intersection and intersection.Volume > 1e-6:
type_id_b = el_b.GetTypeId()
type_name_b = (doc.GetElement(type_id_b).Name
if type_id_b != ElementId.InvalidElementId else 'N/A')
clashes.append({
'Element A ID': el_a.Id.IntegerValue,
'Element A Type': type_name_a,
'Element B ID': el_b.Id.IntegerValue,
'Element B Type': type_name_b,
'Clash Volume (ft3)': round(intersection.Volume, 6),
'Clash Volume (cm3)': round(intersection.Volume * 28316.8, 2),
})
except:
# Boolean operation failed — elements may share a face (contact, not clash)
pass
OUT = [len(clashes), clashes]
except Exception as e:
import traceback
OUT = 'ERROR: ' + str(e) + '\n' + traceback.format_exc()
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.
- 10d ago First seen · 161 lines · 133 tokens per session scan A d70121335261
clash-detection is a skill published in the GitHub repository Utopia5327/claude-plugin-for-revit-bim (6 stars, last pushed 6mo ago), licensed MIT. It adds 133 tokens to every session and 1,319 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…