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/appbuilder-actions)<a href="https://agentmods.dev/rules/shapediver/appbuildersdk/appbuilder-actions"><img src="https://agentmods.dev/badge/rules/shapediver/appbuildersdk/appbuilder-actions/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/appbuilder-actions"><img src="https://agentmods.dev/badge/rules/shapediver/appbuildersdk/appbuilder-actions.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 | $0.00000 | $0.01367 |
| Opus 5.5 | $0.00000 | $0.00547 |
| Sonnet 5.5 | $0.00000 | $0.00273 |
| Haiku 4.5 | $0.00000 | $0.00137 |
Grade A, and why
appbuilder-actions 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 6d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Builder actions
Table
- One
{ isAction, component?, run?, setup? }entry per action. - Headless
runs live infeatures/appbuilder/model/appBuilderActionCatalog.ts(defaultAppBuilderActionRuns). No UI imports. features/appbuilder/ui/sharedAppBuilderActions.tsspreads those runs and adds shared components, includingexecuteActions.AppBuilderActionFromTypeandrunAppBuilderActionoverlaycomponentContext.actionsby key. Host match wins. A host key with nocomponentand norundoes not fall through.- Toolbar buttons may still call typed
runAppBuilderAction*.tshelpers on click. setupruns when a rendered button owns the action.executeActionscalls it for each nested action, including actions inside a nestedexecuteActions, and passes its own button.setContainerVisibilitysetup registers that button as the 2D anchor position. A later selection opens the panel beside it because the position was stored at render, not on click.- The shared action button records the toolbar sibling list for the click.
executeActionscopies that note onto the run. The visibility run closes the other toolbar anchors when that click will open one, and keeps every anchor the action list names. - A controller update replaces the action list. Setup must run again without clearing a trigger the new setup still owns. Clearing it moves an open panel to the center.
- A direct
setContainerVisibilitybutton clears its 2D trigger on unmount only when the registry still points at that button. Another button may have taken the same anchor. - There are no
useAppBuilderAction*hooks.
Host-only actions
Do not put ar, camera, or fullscreen in the shared table. That imports viewer UI into every host.
- ShapeDiver registers them from
src/AppBuilderRoot.tsx. - iJewel omits the key (no button; a sequence warns), registers
{ isAction }to suppress both, or supplies a nativecomponent+run(WebGi). - A matching host entry with no
runis skipped in sequences. There is no ShapeDiver fallback.
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.
- 6d ago Changed · +4 lines 9205536debae
- 7d ago First seen · 77 lines · 0 tokens per session scan A d50114cec3cd
appbuilder-actions is a cursor rule published in the GitHub repository shapediver/AppBuilderSdk (15 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,367 tokens. 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 2026-10-15.
Other cursor rules, from other repositories
windsurfrules
Create detailed components with these requirements.
state-management
Use the following stack. Do not introduce or recommend Redux or React Context for shared/global state.
backend
Backend development rules for TT Studio - AI model management backend.
tanstack-start-guide
TanStack Start best practices emphasizing client-first architecture, type safety, and modern React patterns.
tanstack-react-router_routing
TanStack Router: Routing.
new-component
Workflow for creating new React components.