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 skills/yankieldbc2/codex-skills-library/generative-ui-contractsnpx skills add YankielDBC2/codex-skills-library --skill generative-ui-contractsgit clone --depth 1 https://github.com/YankielDBC2/codex-skills-libraryWrote 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/skills/yankieldbc2/codex-skills-library/generative-ui-contracts)<a href="https://agentmods.dev/skills/yankieldbc2/codex-skills-library/generative-ui-contracts"><img src="https://agentmods.dev/badge/skills/yankieldbc2/codex-skills-library/generative-ui-contracts.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 5.1 | $0.00036 | $0.00382 |
| Opus 5 | $0.00018 | $0.00191 |
| Sonnet 5 | $0.00007 | $0.00076 |
| Haiku 4.5 | $0.00004 | $0.00038 |
Grade A, and why
generative-ui-contracts 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.
What it actually says
Generative UI Contracts
Goal
Keep AI-generated UI safe, typed, renderable, and maintainable by constraining output through schemas and approved components.
When to use
Use when an AI agent creates UI, selects components, generates layout JSON, manipulates product pages, or returns actions/components that the frontend renders.
Workflow
- Do not let the model output arbitrary HTML, code, or unsafe component trees for direct execution.
- Define allowed components, props, variants, actions, and data schemas before rendering model output.
- Validate model output server-side or at the boundary before passing it to UI renderers.
- Separate assistant reasoning, user-facing messages, typed actions, and UI payloads.
- Add fallback states for invalid, incomplete, or unsupported model output.
- Keep generated UI deterministic enough to debug, test, and audit.
- Log safe metadata and avoid storing secrets, payment data, or sensitive content in UI payloads.
Quality bar
- Add or update schema/unit tests when practical.
- Run typecheck and relevant frontend/backend validation.
- Test invalid payload behavior or document why it was not tested.
Validation
- Generated UI is constrained by explicit contracts.
- Frontend only renders known components with validated props.
- Failures are recoverable and visible to developers without exposing internals to users.
Final response
- Summarize contracts added, validation boundary, and unsupported cases.
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 · 51 lines · 36 tokens per session scan A 822099ea5f60
generative-ui-contracts is a skill published in the GitHub repository YankielDBC2/codex-skills-library (10 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 382 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 2026-08-31.
Other skills, from other repositories
openbot-data-access
Governs how the OpenBot browser app reads and writes server data — every request goes through client in app/src/lib/client.ts, every read is a queryOptions factory in app/src/lib/ /queries.ts, every write is a mutationOptions factory in app/src/lib/ /mutations.ts, and components consume them through…
openbot-screen-layout
The default layout for every OpenBot configuration screen — PageShell and its prose/wide widths, PageSection and PageRows, Item row composition, the settings-row pattern where a summary and a chevron open a dialog, and the size and variant vocabulary. This is what a new screen looks like unless an instruction says…
frontend-slides
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
a2ui-generation
Design and generate A2UI updateComponents and updateDataModel payloads for three modes (DTO component, non-DTO component, non-DTO page). Use when asked to create or refine A2UI cards, components, or pages from DTO/JSON/business data, generate Python transformer code for DTO-driven components, iterate on existing A2UI…
vera-language
Write programs in the Vera programming language. Use when asked to write, edit, debug, or review Vera code (.vera files). Vera is a statically typed, purely functional language with algebraic effects, mandatory contracts, and typed slot references (@T.n) instead of variable names.
writer-documents
Use when creating, opening, or editing LibreOffice Writer ODT documents, or DOCX documents only when Microsoft Word compatibility is explicitly required.