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 rules/jasperhartong/sketchup-code/sketchup-bridgegit clone --depth 1 https://github.com/jasperhartong/sketchup-codeWrote 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/rules/jasperhartong/sketchup-code/sketchup-bridge)<a href="https://agentmods.dev/rules/jasperhartong/sketchup-code/sketchup-bridge"><img src="https://agentmods.dev/badge/rules/jasperhartong/sketchup-code/sketchup-bridge.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 | $0.01726 | $0.01726 |
| Opus 5 | $0.00863 | $0.00863 |
| Sonnet 5 | $0.00345 | $0.00345 |
| Haiku 4.5 | $0.00173 | $0.00173 |
Grade A, and why
sketchup-bridge 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SketchUp Bridge – Agent-Driven Iteration
When running or iterating on SketchUp Ruby code, always use the bridge. Do not ask the user to paste code into the SketchUp Ruby Console.
When you need to run code inside SketchUp and see results (e.g. test Timmerman::SkeletonDimensions.run, .clear, or any SketchUp Ruby):
-
Ensure the listener is running in SketchUp
Option A (plugin — preferred): Installdist/timmerman_sketchup_bridge-1.0.0.rbz, set the bridge directory to this project'ssketchup_bridge/folder via Extensions → SketchUp Bridge → Set Bridge Directory…, then click Start Listener. The listener persists across sessions.
Option B (manual): Paste once in the Ruby Console:
load File.join('<path-to-this-repo>', 'sketchup_bridge', 'listener.rb') -
Write the code to run
Editsketchup_bridge/command.rb. The default loadscore.rbdirectly and calls run/clear:core = File.expand_path('../plugins/timmerman_skeleton_dimensions/core.rb', __dir__) load core Timmerman::SkeletonDimensions.debug_mode = true Timmerman::SkeletonDimensions.clear Timmerman::SkeletonDimensions.run "OK"The algorithm lives in
plugins/timmerman_skeleton_dimensions/core.rb— edit that file, then re-run the bridge to test it. -
Run and wait for result
Execute:ruby sketchup_bridge/run_and_wait.rb
The script touchescommand.rbso the listener runs it, then waits forresults/result.txtwritten this run. It only succeeds when SketchUp actually runs the command (so you never get stale output). If the listener is not running, it times out and fails. -
Use the output
stdout/stderr from the command are in the printed result. Parse it to decide the next edit and repeat. -
Programmatic screenshots (optional)
Load the utils helper incommand.rband calltake_screenshot:load File.expand_path('utils.rb', __dir__) SketchupBridgeUtils.take_screenshot # timestamped PNG in results/ SketchupBridgeUtils.take_screenshot(name: "after_fix") # results/after_fix.pngThe image is saved under
sketchup_bridge/results/. Seesketchup_bridge/utils.rbfor options (width, height, antialias). -
If the bridge is not connected
When the listener is not running in SketchUp (or the IDE was not opened with the correct port),run_and_wait.rbwill fail after a short timeout and print a clear "BRIDGE NOT CONNECTED" message. Report that to the user: tell them the bridge could not reach SketchUp and they need to start the listener in SketchUp (Extensions → SketchUp Bridge → Start Listener, or load the listener from the Ruby Console) and set the bridge directory, then rerun.
Do not ask the user to paste code into the Ruby Console for iteration; use the bridge (edit command.rb → run run_and_wait.rb → read output).
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 · 100 lines · 1,726 tokens per session scan A 1fe18fd0b36f
sketchup-bridge is a cursor rule published in the GitHub repository jasperhartong/sketchup-code (5 stars, last pushed 3mo ago), licensed MIT. It adds 1,726 tokens to every session, about $0.0086 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 cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.