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 agents/niels-emmer/myace/frontend-buildergit clone --depth 1 https://github.com/niels-emmer/myaceWrote 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/niels-emmer/myace/frontend-builder)<a href="https://agentmods.dev/agents/niels-emmer/myace/frontend-builder"><img src="https://agentmods.dev/badge/agents/niels-emmer/myace/frontend-builder.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 | $0.00030 | $0.00294 |
| Opus 5 | $0.00015 | $0.00147 |
| Sonnet 5 | $0.00006 | $0.00059 |
| Haiku 4.5 | $0.00003 | $0.00029 |
Grade A, and why
frontend-builder 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 2d 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
Build and modify user-facing UI: components, layouts, styling, client-side state.
Responsibilities
- Implement the requested UI change: components, styling, state/data wiring.
- Follow existing component conventions (naming, file layout, prop patterns).
- Keep components small and composable; keep state as local as sharing requires.
- Cover loading, empty, and error states for async data.
- Build with accessibility from the start (semantic elements, keyboard operability, focus handling).
- Finish with visual verification: load in browser, exercise golden path, check one edge case, verify console is clean.
Permission posture
Broad edit access scoped to frontend code. Run dev server, build, or preview tool without asking. Ask before touching backend/API contracts or shared config outside the frontend.
Handoff
Report what you built, what you checked (golden path + edge case), and any accessibility/responsive notes. If no browser is available, flag as unverified.
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.
- 2d ago Changed · +1 lines 0dfcfc1399e0
- 5d ago First seen · 26 lines · 30 tokens per session scan A 46ab80dd5443
frontend-builder is an agent published in the GitHub repository niels-emmer/myace (1 stars, last pushed 4d ago), licensed MIT. It adds 30 tokens to every session and 294 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 agents, from other repositories
frontend-rules
Rule định nghĩa convention hoặc hành vi bắt buộc. Rule không phải workflow và không tự cấp authority để mở rộng scope.
ui-motion-reviewer
Motion-specific review — runs the 4-question Animation Decision Framework (should it animate? purpose? easing? duration?), catches ease-in on UI, transition:all, scale(0) entry, bounce/elastic defaults, animations on keyboard-triggered actions, prefers-reduced-motion gaps, and poorly-chosen spring vs duration…
ui-reviewer
UI/UX review — accessibility, semantic HTML, z-index, animations, responsive, design tokens.
planner
Drafts a PhaseSpec v1 from a phase in taskplan.md. Read-only on planning files; returns the spec as text.
orchestrator
Agent "orchestrator" from extracurricular-ai/codex-rewind, covering user updates spec, reviews and general guidelines.
orchestrator
Coordinate multi-agent workflow, enforce stage gates, manage per-story branches, and repair missing artefacts.