ui-driven-spec

ui-driven-spec is a skill for Claude Code, Codex from tamnguyendinh/Anvien. It costs 76 tokens per session (1,095 once invoked), scanned A, original, MIT.

A UI-first development workflow that starts with a working interface, extracts its data and interaction requirements, checks them against the specification, and only then plans backend work. The backend is implemented one module at a time after owner approval.

In plain words
What is it for?
Use it to turn an approved prototype into implementation requirements, align it with the system specification, plan backend modules, and verify each module before continuing.
Why use it?
It exposes missing requirements through the interface before backend code is written and prevents agents from inventing missing details or changing the specification to fit a prototype.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to turn an approved prototype into implementation requirements, align it with the system specification, plan backend modules, and verify each module before continuing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tamnguyendinh/anvien/ui-driven-spec
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.

Any agent
npx skills add tamnguyendinh/Anvien --skill ui-driven-spec
Clone the repo
git clone --depth 1 https://github.com/tamnguyendinh/Anvien

Made for: Claude Code, 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 ui-driven-spec

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/tamnguyendinh/anvien/ui-driven-spec"><img src="https://agentmods.dev/badge/skills/tamnguyendinh/anvien/ui-driven-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,095 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00076 $0.01095
Opus 5 $0.00038 $0.00548
Sonnet 5 $0.00015 $0.00219
Haiku 4.5 $0.00008 $0.00110

Measured 6d ago against content hash 20aa3813495e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ui-driven-spec 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.

internal/aicontext/skills/ui-driven-spec/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI-Driven Spec — FE-First Development Workflow

Core Philosophy

The UI is the user interaction map, not the supreme authority.
The supreme authority remains the Spec and System Architecture.
Human / Architect approval is mandatory before a single line of backend code is written.

  • Traditional flow: Spec → Backend → Frontend (Gaps discovered late, expensive patches).
  • UI-driven flow: UI Prototyping → Contract Extraction → Spec Alignment & Gate → Module-by-Module Backend Implementation & QA.

Iron Laws

  1. Extraction over invention: Contract extraction reads from FE code and mock types without guessing. Missing information must be flagged as [TBD], never self-filled.
  2. Spec judges artifacts, not the reverse: If an artifact conflicts with the Spec, conform the artifact to the Spec. Do not alter the Spec during extraction.
  3. Owner Review Gate is non-negotiable: No backend planning or implementation may begin without explicit owner sign-off. Silence is never approval.
  4. Strict single-module planning: Never plan multiple backend modules concurrently. Plan exactly one module, implement, verify with runtime QA, obtain approval, then proceed to the next module.
  5. Spec is the supreme law: If UI/FE behavior conflicts with Spec requirements, stop and escalate — never arbitrarily decide which side wins.
  6. No uncontracted backend work: Backend never implements anything outside backend-contract-map.md. Do not add unsolicited endpoints.
  7. Real UI verification mandatory: A module is never done without testing with real API integration on the actual UI.

File-to-File Workflow Pipeline

[1] references/ui-prototyping-and-components.md
    │   • Build static HTML prototype (`prototype/`)
    │   • Build FE components with mock types (`src/types/`, `src/mocks/`)
    ▼
[2] references/contract-maps-and-payloads.md
    │   • Extract Data Source Map & API Payload contracts
    │   • Extract UI Slot Map & State Transitions
    │   • Aggregate Backend Contract Map (`docs/backend-contract-map.md`)
    ▼
[3] references/spec-alignment-and-review-gate.md
    │   • Draft / ingest authoritative SPEC (`docs/SPEC.md`)
    │   • Adjudicate and align all contract maps against SPEC
    │   • Package handoff bundle & await Owner Approval
    │
    ▼ ⛔ [MANDATORY OWNER APPROVAL GATE] ⛔
    │
[4] references/module-implementation-and-qa.md
    │   • Plan single module (`Implementation Plan: Module [Name]`)
    │   • Implement backend services & wire live API to FE
    │   • Verify runtime QA on real UI (`docs/qa-log.md`)
    │   • Iterate module-by-module until complete

Read the full file on GitHub · 80 lines

Files

What ships with it

4 files 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. 6d ago First seen · 80 lines · 76 tokens per session scan A 20aa3813495e

Subscribe to this mod's changes

ui-driven-spec is a skill published in the GitHub repository tamnguyendinh/Anvien (9 stars, last pushed 2d ago), licensed MIT. It adds 76 tokens to every session and 1,095 once invoked, about $0.0004 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 2026-09-03.

Related

Other skills, from other repositories

supabase-nextjs

Next.js with Supabase and Drizzle ORM.

alinaqi/maggy · 14 tokens

design-patterns

Agents should invoke this skill when choosing patterns, designing traits/interfaces/components, deciding abstraction boundaries, evaluating dependency injection/callbacks, or comparing implementation approaches in Rust, TypeScript/React, or Django/Python.

waybarrios/opencode-power-pack · 46 tokens

fullstack-expert

Expert-level fullstack development guide covering multi-language (TypeScript, Python, Go, Rust), multi-framework (Next.js, FastAPI, Gin, Axum), API design, microservices, DevOps, and system design / Panduan fullstack tingkat ahli mencakup multi-bahasa (TypeScript, Python, Go, Rust), multi-framework (Next.js, FastAPI…

roedyrustam/vibes-plug · 101 tokens

spa-orchestrator

Orchestrates Single-Page Application (SPA) architecture, integrating frontend state management with API-driven backends / Mengorkestrasi arsitektur Single-Page Application (SPA), mengintegrasikan state management frontend dengan backend berbasis API.

roedyrustam/vibes-plug · 53 tokens

multiple-entry-points

Expert guide for designing and implementing Multiple Entry Points architecture in web applications / Panduan ahli untuk merancang dan mengimplementasikan arsitektur Multiple Entry Points pada aplikasi web.

roedyrustam/vibes-plug · 39 tokens

client-scripts

Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.

serac-labs/serac · 45 tokens