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 linked-model-checkgit 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/linked-model-check)<a href="https://agentmods.dev/skills/utopia5327/claude-plugin-for-revit-bim/linked-model-check"><img src="https://agentmods.dev/badge/skills/utopia5327/claude-plugin-for-revit-bim/linked-model-check/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/linked-model-check"><img src="https://agentmods.dev/badge/skills/utopia5327/claude-plugin-for-revit-bim/linked-model-check.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 | $0.00152 | $0.01965 |
| Opus 5 | $0.00076 | $0.00983 |
| Sonnet 5 | $0.00030 | $0.00393 |
| Haiku 4.5 | $0.00015 | $0.00197 |
Grade A, and why
linked-model-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Linked Model Health Check
Audit linked files and coordination status for:
"$ARGUMENTS"
Approach
Default to a comprehensive read-only report covering:
- All RVT links (loaded, unloaded, missing, not found)
- All CAD imports/links (DWG, DXF, DGN)
- Coordinate system status (shared coordinates, survey point)
- Linked model bounding boxes (detect obvious coordinate outliers)
Script: Comprehensive linked file report (read-only)
import clr
clr.AddReference('RevitServices')
from RevitServices.Persistence import DocumentManager
clr.AddReference('RevitAPI')
from Autodesk.Revit.DB import *
import csv, os
doc = DocumentManager.Instance.CurrentDBDocument
MM_TO_FT = 1.0 / 304.8
def ft_to_mm(ft_val):
return round(ft_val * 304.8, 1)
try:
report = {}
# ── 1. RVT Links ──────────────────────────────────────────────────────────
rvt_link_types = list(FilteredElementCollector(doc)
.OfClass(RevitLinkType).ToElements())
rvt_link_instances = list(FilteredElementCollector(doc)
.OfClass(RevitLinkInstance).ToElements())
rvt_report = []
for lt in rvt_link_types:
load_state = lt.GetLinkedFileStatus()
path_info = lt.GetExternalFileReference()
path_str = ""
try:
path_str = ModelPathUtils.ConvertModelPathToUserVisiblePath(
path_info.GetAbsolutePath())
except Exception:
path_str = "Path unavailable"
# Find matching instances
instances = [li for li in rvt_link_instances
if li.GetTypeId() == lt.Id]
for inst in instances:
xform = inst.GetTransform()
origin = xform.Origin
link_doc = inst.GetLinkDocument()
entry = {
"Name": lt.Name,
"Status": str(load_state),
"Path": path_str,
"Instance Count": len(instances),
"Origin X (mm)": ft_to_mm(origin.X),
"Origin Y (mm)": ft_to_mm(origin.Y),
"Origin Z (mm)": ft_to_mm(origin.Z),
"Is Identity": xform.IsIdentity,
"Linked Doc": link_doc.Title if link_doc else "NOT LOADED",
}
# Coordinate warning
if abs(origin.X) > 328 or abs(origin.Y) > 328: # > 100m offset
entry["WARNING"] = "Link origin > 100m from project origin — check shared coordinates"
else:
entry["WARNING"] = ""
rvt_report.append(entry)
# If no instances (type exists but not placed)
for lt in rvt_link_types:
instances = [li for li in rvt_link_instances if li.GetTypeId() == lt.Id]
if not instances:
rvt_report.append({
"Name": lt.Name,
"Status": str(lt.GetLinkedFileStatus()),
"Path": "Type exists but not placed as instance",
"WARNING": "No instance placed in model"
})
report["RVT Links"] = rvt_report
# ── 2. CAD Links & Imports ────────────────────────────────────────────────
cad_items = list(FilteredElementCollector(doc)
.OfClass(ImportInstance).ToElements())
cad_report = []
for ci in cad_items:
try:
cat_name = ci.Category.Name if ci.Category else "Unknown"
is_linked = ci.IsLinked
xform = ci.GetTransform()
origin = xform.Origin
entry = {
"Category": cat_name,
"Is Linked": is_linked,
"Origin X (mm)": ft_to_mm(origin.X),
"Origin Y (mm)": ft_to_mm(origin.Y),
"Origin Z (mm)": ft_to_mm(origin.Z),
}
try:
ext_ref = ci.GetExternalFileReference()
entry["Path"] = ModelPathUtils.ConvertModelPathToUserVisiblePath(
ext_ref.GetAbsolutePath())
except Exception:
entry["Path"] = "Embedded / no path"
cad_report.append(entry)
except Exception:
pass
report["CAD Links/Imports"] = cad_report
# ── 3. Coordinate summary ─────────────────────────────────────────────────
# Project Base Point and Survey Point
base_pts = list(FilteredElementCollector(doc)
.OfClass(BasePoint)
.ToElements())
coord_info = []
for bp in base_pts:
try:
is_survey = bp.IsShared
pos = bp.Position
coord_info.append({
"Type": "Survey Point" if is_survey else "Project Base Point",
"X (mm)": ft_to_mm(pos.X),
"Y (mm)": ft_to_mm(pos.Y),
"Z (mm)": ft_to_mm(pos.Z),
})
except Exception:
pass
report["Coordinate Points"] = coord_info
# ── 4. Summary ───────────────────────────────────────────────────────────
loaded = sum(1 for r in rvt_report
if "LinkedFileStatus_Loaded" in str(r.get("Status", "")))
unloaded = sum(1 for r in rvt_report
if "LinkedFileStatus_Loaded" not in str(r.get("Status", ""))
and r.get("Status"))
warnings = sum(1 for r in rvt_report if r.get("WARNING"))
report["Summary"] = {
"Total RVT Links": len(rvt_link_types),
"Instances placed": len(rvt_link_instances),
"Loaded": loaded,
"Unloaded/Missing": unloaded,
"Coordinate Warnings": warnings,
"CAD Items": len(cad_items),
}
OUT = report
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.
- 9d ago First seen · 247 lines · 152 tokens per session scan A 4f02bb0e5e26
linked-model-check is a skill published in the GitHub repository Utopia5327/claude-plugin-for-revit-bim (6 stars, last pushed 6mo ago), licensed MIT. It adds 152 tokens to every session and 1,965 once invoked, about $0.0008 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…