A React runtime that reads structured metadata and turns it into web interface elements. It renders pages and widgets from a shared specification, passes context such as a record or user, and chooses components from a registry.

Use it to build the rendering engine for server-driven interfaces in applications such as Next.js or Vite, including pages, regions, and registered widgets.

It lets an application describe interface structure as data instead of hard-coding every page, while keeping layouts, widgets, and data definitions aligned.

engine — Command for GitHub Copilot by objectstack-ai/objectstack

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.

Clone the repo

git clone --depth 1 https://github.com/objectstack-ai/objectstack

Made for: GitHub Copilot.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/objectstack-ai/objectstack/engine/github.svg)](https://agentmods.dev/commands/objectstack-ai/objectstack/engine)

Your own site

<a href="https://agentmods.dev/commands/objectstack-ai/objectstack/engine"><img src="https://agentmods.dev/badge/commands/objectstack-ai/objectstack/engine/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/objectstack-ai/objectstack/engine"><img src="https://agentmods.dev/badge/commands/objectstack-ai/objectstack/engine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,168 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.02168
Opus 5.5	$0.00000	$0.00867
Sonnet 5.5	$0.00000	$0.00434
Haiku 4.5	$0.00000	$0.00217

Measured today against content hash 9c8d9ffcd9a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

engine 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 today.

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.

ui/.github/prompts/engine.prompt.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⚙️ ObjectStack Runtime Engine Development Context

Role: You are the Core Framework Engineer for ObjectStack. Task: Build the React-based Server-Driven UI (SDUI) Engine that interprets Zod Metadata and renders the UI. Environment: A frontend application (e.g., Next.js, Vite) consuming the @objectstack/spec package.

1. The Trinity of Engines

A complete ObjectUI Runtime consists of three coordinating engines. Each engine consumes specific types from @objectstack/spec.

A. Layout Engine (`<PageRenderer />`)

Responsible for recursive rendering of the UI tree.

Input Protocol: Page (from @objectstack/spec/ui)
- Reference: packages/spec/src/ui/page.zod.ts
Block Protocol: PageComponent (from @objectstack/spec/ui)
- Reference: packages/spec/src/ui/block.zod.ts
Logic:
1. Recursively traverse Page.regions and Region.components.
2. Map component.type (e.g., page:tabs) to the React Component via widgetRegistry.
3. Pass component.properties as Props (Typed as ComponentProps from @objectstack/spec/ui).
4. Inject context (Record ID, User Info) into the component tree.
Key Hook: useComponentResolver(type)

B. Data Engine (`useObjectData()`)

Responsible for data fetching, caching, and state management.

Input Protocol: View / ListView (from @objectstack/spec/ui)
- Reference: packages/spec/src/ui/view.zod.ts
Filter Protocol: FilterCondition (from @objectstack/spec/data)
- Reference: packages/spec/src/data/filter.zod.ts
Library: React Query (TanStack Query) + SWR.
Logic:
1. Convert View.filters and View.sort into ObjectQL Query.
2. Handle isLoading, error, data states.
3. Provide refresh() and mutations (Create/Update/Delete).
Key Hook: useRecord(object, id), useList(object, view)

C. Action Engine (`useAction()`)

Responsible for executing business logic and side effects.

Input Protocol: Action (from @objectstack/spec/ui)
- Reference: packages/spec/src/ui/action.zod.ts
Logic:
1. Pre-check: Evaluate disabled state and permissions.
2. Confirmation: Show Modal if confirmText is present.
3. Execution: Call API / Run Script / Navigate URL.
4. Feedback: Show Toast (Success/Error) and trigger DataEngine.refresh().

Read the full file on GitHub · 229 lines

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.

today First seen · 229 lines · 0 tokens per session scan A 9c8d9ffcd9a2

Subscribe to this mod's changes

engine is a command published in the GitHub repository objectstack-ai/objectstack (75 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,168 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 2026-10-26.

Frontend React fde fde-enablement metadata-driven ontology ontology-driven-development ontology-engineering

plan-feature

Plan a feature from BRD-lite brief or clear intent into PRD (What), decisions, implementation plan, and task slices.

HoangNguyen0403/agent-skills-standard · 0 tokens

retro-learn

Convert delivery findings into skill, eval, workflow, and documentation improvements.

HoangNguyen0403/agent-skills-standard · 0 tokens

prototype-loop

Enter leveraged-prototype focus mode — focus marker plus normal watch/rebuild loop for visual-parity work and batch upstream framework gap-fixes.

Generous-Corp/pulp · 31 tokens

story-and-test

For the component(s) in scope.

epam/ai-dial-ui-kit · 0 tokens

react-build

Fix React build failures (Vite, webpack, Next.js, CRA, Parcel, esbuild, Bun) incrementally — JSX/TSX compile errors, hydration mismatches, server/client component boundary failures, missing types. Invokes the react-build-resolver agent for minimal, surgical fixes.

DekaPrayoga/AurixAgent · 59 tokens

web-design

Design and build a complete website or webapp from a project brief — end-to-end workflow from design to working React/Vite code.

lukaskellerstein/claude-my-marketplace · 26 tokens