onchainai: Skill for Codex

.agents/skills/onchainai-ui-workflow/SKILL.md

onchainai-ui-workflow is a skill for Codex from Coinyak/onchainai. It costs 60 tokens per session (1,220 once invoked), scanned A, original, MIT.

A project-specific workflow for changing or reviewing the OnchainAI web interface, built with Next.js, Tailwind CSS, and related web code. It defines the project's visual, responsive, accessibility, and deployment rules.

In plain words
What is it for?
Use it when editing OnchainAI pages or components, checking mobile layouts, polishing styles, reviewing screenshots, or running browser checks.
Why use it?
It keeps interface changes consistent with the project's design documents and prevents UI additions that conflict with its security and product boundaries.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: reads .claude/ paths; installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is Coinyak/onchainai's own configuration. It tells Codex how to work on onchainai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything onchainai configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./scripts/dev-watch.sh.

Reuse

Borrowing it

Nothing to install: this file belongs to Coinyak/onchainai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Coinyak/onchainai/main/.agents/skills/onchainai-ui-workflow/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Coinyak/onchainai

Made for: Codex.

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.

agentmods badge for onchainai-ui-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/coinyak/onchainai/onchainai-ui-workflow/github.svg)](https://agentmods.dev/skills/coinyak/onchainai/onchainai-ui-workflow)
Your own site
<a href="https://agentmods.dev/skills/coinyak/onchainai/onchainai-ui-workflow"><img src="https://agentmods.dev/badge/skills/coinyak/onchainai/onchainai-ui-workflow/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.

agentmods 80×15 button for onchainai-ui-workflow

Your own site · 80×15
<a href="https://agentmods.dev/skills/coinyak/onchainai/onchainai-ui-workflow"><img src="https://agentmods.dev/badge/skills/coinyak/onchainai/onchainai-ui-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,220 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00060 $0.01220
Opus 5 $0.00030 $0.00610
Sonnet 5 $0.00012 $0.00244
Haiku 4.5 $0.00006 $0.00122

Measured 10d ago against content hash d920527aee73, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

onchainai-ui-workflow scanned grade A with 1 finding 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 10d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

This is the preferred agent path because it does a coherent API + Next.js release build, restarts both servers, verifies bundle timestamps, runs curl/browser/auth smoke, and captures desktop/mobile screenshots.
.agents/skills/onchainai-ui-workflow/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OnchainAI UI Workflow

Use this repo-specific workflow for UI work before reaching for generic frontend advice. OnchainAI already has strong design and deploy rules; the job is to preserve them while making small, visible improvements.

Source Priority

Read these first for any UI change:

  1. AGENTS.md
  2. DESIGN.md
  3. docs/UI_UX_DESIGN.md
  4. docs/BUILD_DEPLOY_RULES.md

Then inspect the affected frontend/ component, page, CSS, and script files. Do not infer UI intent from screenshots alone when a design doc covers the surface.

Design Invariants

  • UI text is English.
  • No emoji in UI text.
  • Use lucide-style SVG line icons or existing icon/logo patterns.
  • Keep the calm light theme: neutral surfaces, orange only for primary interaction/focus, no crypto-gradient styling.
  • Preserve information density without cramped mobile layouts.
  • Body text on mobile must stay readable; touch targets should be at least 44px.
  • Cards stay at 8px radius or less unless the existing design document says otherwise.
  • Do not introduce x402 payment execution, custody, wallet, facilitator, or fund-moving UI. x402 belongs to metadata, attribution, and trust signals only.

Workflow

0. Preserve Existing Behavior

Before editing, identify the existing behavior that must survive the change:

  • Navigation and auth controls.
  • Sidebar collapse/expand behavior and saved state.
  • Search, filters, sorting, pagination/load more, and selected tool behavior.
  • Modal open/close, keyboard dismissal, and focusable controls.
  • Existing data-testid selectors used by smoke scripts.

Do not remove or rename these behaviors as part of a visual fix unless the user explicitly asks and the smoke scripts/docs are updated.

1. Frame The Change

Write down:

  • Target route or component.
  • User task it supports.
  • Viewports that matter, usually 1280x900 and 375x812.
  • Whether this is a layout, responsive, accessibility, component-boundary, or visual-polish issue.

If the issue is vague, use web-design-guidelines or visual-qa after capturing screenshots.

Read the full file on GitHub · 137 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 10d ago First seen · 137 lines · 60 tokens per session scan A d920527aee73

Subscribe to this mod's changes

onchainai-ui-workflow is a skill published in the GitHub repository Coinyak/onchainai (1 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,220 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.