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/shapediver/AppBuilderSdkWrote 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/shapediver/appbuildersdk/browser-diagnosis)<a href="https://agentmods.dev/rules/shapediver/appbuildersdk/browser-diagnosis"><img src="https://agentmods.dev/badge/rules/shapediver/appbuildersdk/browser-diagnosis/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/rules/shapediver/appbuildersdk/browser-diagnosis"><img src="https://agentmods.dev/badge/rules/shapediver/appbuildersdk/browser-diagnosis.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 | $0.00036 | $0.00469 |
| Opus 5 | $0.00018 | $0.00234 |
| Sonnet 5 | $0.00007 | $0.00094 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
browser-diagnosis 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 2d 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.
What it actually says
Browser diagnosis (App Builder)
Dev server and models
pnpm start --port 3000→http://localhost:3000/?slug=<slug>. Slug data inmodelstorage.local.ts.- Platform token expires hourly; run
pnpm run convert-slug-datawhen a session fails to load. - Testing-account models do not whitelist localhost — use the deployed URL.
- Settings/theme:
?g=<file>frompublic/.
Throwaway Playwright
Write drivers as .mjs under test-results/scratch (wiped by e2e; keep copies in the scratchpad). Run from the project directory so @playwright/test resolves. Viewport 1280x720. Use Write/Edit for driver files (Python "\n" escapes have produced literal newlines inside string literals).
In-page (window.SDV)
Object.values(SDV.sessions)[0]—parameters,outputs,customizeSDV.viewports—busyfor idle detectionSDV.EVENTTYPE_INTERACTION+SDV.addListener—SELECT_ON/OFF,HOVER_ON,MULTI_SELECT_*- Node
InteractionData:restrictedManagers,interactionTypes(capability),interactionStates(current)
Count computations with page.on("request") filtered to PUT and /output; diff the body's parameter values against the previous request.
Pulse highlight effects make pixel counting unreliable; use events, parameter values, or public/example-simple-interaction-colors.json for snapshots.
Who committed? (async stacks)
Debounce in handleChange breaks stacks. Temporary console.log("[diag] ...", new Error().stack) in useParameterComponentCommons.handleChange, the custom parameter executor, and batchParameterValueUpdate; capture page.on("console"); then git checkout HEAD -- the instrumented files.
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.
- 2d ago First seen · 33 lines · 36 tokens per session scan A 98d5230ed6a3
browser-diagnosis is a cursor rule published in the GitHub repository shapediver/AppBuilderSdk (16 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 469 once invoked, about $0.0002 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 2026-09-10.
Other cursor rules, from other repositories
slate-patch
Fix Slate v2 bugs in one pass with reproduction, behavior tests, architecture/DX/perf pressure, proactive rearchitecture when the patch is not the cleanest long-term shape, and final autoreview.
mobx-strict-mode
Guidance for enabling MobX strict mode, which requires observable state changes to happen inside actions.
common-fixes
Utility for VAN QA common validation fixes.
autofix
Please use the Playwright MCP to open a browser to the URL I provide, check for any errors, and then automatically fix those errors in my codebase, then continue to iterate until all the errors are gone.
modus-modal-implementation-react
Critical implementation patterns for ModusWcModal in React.
modus-checkbox-value-inversion-react
Critical bug fix for ModusWcCheckbox value property inversion.