openusage-preview-launch

A development rule for the local OpenUsage menu-bar app that requires stopping, rebuilding, launching, and checking the fresh development version after relevant changes.

In plain words
What is it for?
Use it when changing the app, restarting or verifying it, or finishing work that should be checked in the running menu-bar app.
Why use it?
It prevents you from viewing an old running build and mistaking it for the version you just changed.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/robinebers/openusage/openusage-preview-launch
Clone the repo
git clone --depth 1 https://github.com/robinebers/openusage

Made for: Cursor.

Per session 209 This file is loaded in full into every session.
When invoked 209 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00209 $0.00209
Opus 5 $0.00105 $0.00105
Sonnet 5 $0.00042 $0.00042
Haiku 4.5 $0.00021 $0.00021

Measured yesterday against content hash 8fe0b3ceeac6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

openusage-preview-launch 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 yesterday.

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.

.cursor/rules/openusage-preview-launch.mdc · 26 lines

What it actually says

OpenUsage Dev Launch Workflow

Always kill any running OpenUsage instance and build/launch a fresh local dev build when:

  • You change app UI, widgets, providers, or anything that affects the running binary
  • The user asks to run, restart, or verify the app
  • You finish a task where the user should see the result in the menu bar app

Do not leave an old process running and assume a rebuild is enough.

Use the project script:

./script/build_and_run.sh verify

This script stops the existing process, builds the app, stages and signs a bundle under dist/, launches it in place (nothing is installed to /Applications), and verifies the process is running. The dev build uses its own bundle id and ships no update feed, so it never disturbs a released OpenUsage and never checks for updates.

Changes

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.

  1. yesterday First seen · 26 lines · 209 tokens per session scan A 8fe0b3ceeac6

Subscribe to this mod's changes

openusage-preview-launch is a cursor rule published in the GitHub repository robinebers/openusage (3,954 stars, last pushed 3d ago), licensed MIT. It adds 209 tokens to every session, about $0.0010 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 2026-08-30.