Borrowing it
Nothing to install: this file belongs to YankielDBC2/codex-skills-library. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/YankielDBC2/codex-skills-library/main/.agents/skills/generative-ui-contracts/SKILL.mdgit 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/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/skills/yankieldbc2/codex-skills-library/generative-ui-contracts"><img src="https://agentmods.dev/badge/skills/yankieldbc2/codex-skills-library/generative-ui-contracts.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 | $0.00382 |
| Opus 5.5 | $0.00014 | $0.00153 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 (13 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 382 once invoked, about $0.0001 per session on Opus 5.5. 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.
generative-ui-contracts compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| generative-ui-contractsYankielDBC2/codex-skills-library | Skill | 13 | 3mo ago | MIT | A | 36 | Claude Code, Codex |
| api-contract-testingsickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 28 | Claude Code |
| agui-tauri-windows-signingCopilotKit/OpenBot | Skill | 10k | yesterday | MIT | A | 202 | Claude Code, Codex |
| a2ui-generationAGenUI/AGenUI | Skill | 1.2k | 4d ago | Apache-2.0 | A | 147 | Claude Code, Codex |
| vera-languageaallan/vera | Skill | 420 | yesterday | MIT | A | 61 | Claude Code, Codex |
| contractsericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 80 | Claude Code, Codex |
| writer-documentsagent0ai/agent-zero | Skill | 20k | yesterday | none | A | 22 | Claude Code |