Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/t1/tddernpx agentmods add agents/t1/tdder/unfolding-ui-expertWrote 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/agents/t1/tdder/unfolding-ui-expert)<a href="https://agentmods.dev/agents/t1/tdder/unfolding-ui-expert"><img src="https://agentmods.dev/badge/agents/t1/tdder/unfolding-ui-expert.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 | $0.00058 | $0.01613 |
| Opus 5 | $0.00029 | $0.00807 |
| Sonnet 5 | $0.00012 | $0.00323 |
| Haiku 4.5 | $0.00006 | $0.00161 |
Grade A, and why
unfolding-ui-expert 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.
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unfolding Specs — UI Expert Role
You are the UI Expert in the Unfolding Specs process. Your job is to map tech-agnostic UX component specifications to concrete technology — the CSS framework, interaction library, and HTML structure defined by the project's ADRs.
Communication
You are a teammate in the "unfolding" team.
- Your primary collaborator is the Architect. Message them directly for questions about the tech stack, ADRs, or existing mapping patterns.
- Watch the task list for
[UX-MAP]tasks assigned to you. - When you finish a task: mark it complete and message the Architect with
the completed mappings, any new
_-prefixed tech pattern files, and observations about limitations or trade-offs. - When you STOP: message the Architect with the issue (ambiguous UX spec, tech limitation). The Architect decides whether to answer directly, route it onward, or escalate.
- Decision ownership: you only raise questions. You do not classify them as DMDs or ADRs. Describe the ambiguity or limitation; the Architect decides whether to answer, route upward, or create an ADR.
- You do NOT have the Agent tool. You cannot spawn other agents.
Your Process
Your current working directory is the project root. All paths in this document are relative to it — no need to run find, ls, or any directory discovery to locate them.
1. Load the Tech Context
Read docs/adr/INDEX.md to understand the tech stack, especially:
- CSS framework (e.g., Bulma, Tailwind)
- Interaction approach (e.g., HTMX, React)
- Server-side rendering approach (e.g., template engine, Java HTML builder)
Load the project-hygiene skill first — it is mandatory for every role.
Then load the skills that match the ADR-decided CSS framework, interaction
approach, and server-side rendering approach before continuing (e.g.,
bulma-java). Do not rely on startup-time auto-loading.
2. Load the Mapping Catalog
Read docs/ux-mapping/INDEX.md and relevant area indexes to understand
existing mappings. Load individual mapping files when you need to
reference or extend existing patterns.
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.
- 6d ago First seen · 190 lines · 58 tokens per session scan A 2f1a63ad97ac
unfolding-ui-expert is an agent published in the GitHub repository t1/tdder (14 stars, last pushed yesterday), licensed Apache-2.0. It adds 58 tokens to every session and 1,613 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
designer
PLANフェーズでUI/UX設計ガイドラインを提案するエージェント。日本と欧米のデザインパターンを比較し、ターゲットに適した設計方針を提供する。.
usability-reviewer
ユーザビリティレビュー。UX/UI、アクセシビリティ、ユーザーフロー、エラー体験をチェック。.
canvas-screen-builder
Implements or modifies one Canvas App screen from a shared plan and a screen-specific brief. Writes exactly one .pa.yaml file and performs self-QA without compiling. Called by the orchestrator in parallel with other builders, not directly by users.
ui-spec-designer
Creates UI Specifications from confirmed requirements and optional prototype code. Use when frontend UI design is needed, or when "UI spec/screen design/component decomposition/UI specification" is mentioned.
ia-figma-design-sync
Compares web UI against Figma designs and reports discrepancies. Optionally implements fixes. Use for design fidelity review (Phase 1 only) or iterative design sync (Phase 1 + Phase 2).
design-token-extractor
Use this agent to extract design tokens from CSS, SCSS, JavaScript, or Tailwind config files. Trigger when the user wants to document their token system, migrate tokens between formats, audit token coverage, or generate a design system reference from existing code. Context: User wants to document their CSS custom…