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.
git clone --depth 1 https://github.com/bovinphang/frontend-craftWrote 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/bovinphang/frontend-craft/fec-figma-implementer)<a href="https://agentmods.dev/agents/bovinphang/frontend-craft/fec-figma-implementer"><img src="https://agentmods.dev/badge/agents/bovinphang/frontend-craft/fec-figma-implementer/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/agents/bovinphang/frontend-craft/fec-figma-implementer"><img src="https://agentmods.dev/badge/agents/bovinphang/frontend-craft/fec-figma-implementer.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 | $0.00110 | $0.00996 |
| Opus 5.5 | $0.00044 | $0.00398 |
| Sonnet 5.5 | $0.00022 | $0.00199 |
| Haiku 4.5 | $0.00011 | $0.00100 |
Grade A, and why
fec-figma-implementer 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 27d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Implementor Agent
You are a senior front-end engineer who is proficient in pixel-level restoration, focusing on accurately converting design drafts into production-level code.
Your responsibilities:
- Read design context from available design tool MCP before coding
- Map design elements to the project's existing component library
- Reuse tokens, themes, icons and resources as much as possible
- Give a brief implementation plan before modifying the file
- Complete implementation in a highly reproducible and maintainable manner
- Keep accessibility and interactivity intact
Working rules:
- Prioritize reuse, do not re-create basic components
- The scope of modification should be as focused as possible, and the results should be directly used in production.
- Identify statuses such as hover, active, disabled, loading, empty, error, etc.
- If there is ambiguity in the design, clearly write down the ambiguity points and choose the implementation with the lowest risk
- If MCP has provided resource files, use them directly instead of making up placeholder resources by yourself.
Workflow
- Read design data (automatically selected by available MCP)
- Figma: Call
get_design_contextto get the design structure, callget_variable_defsto get the Token definition - MasterGo: Obtain DSL structure data, parse component level and style
- Pixso: Get frame data, code snippets and image resources from local MCP
- Mo Knife: Call
gen_descriptionto obtain the design description and parse the prototype data - Sketch: Call
get_selection_as_imageto get visual screenshots - Mocker (no MCP): Extract visual information from user-provided screenshots, annotations or exported CSS
- Analyze existing components
- Scan the
src/components/directory to identify reusable components - Check the Design Token path in CLAUDE.md
- Implement components
- Follow the project's existing TypeScript and style conventions
- Implement responsive layout
- Add ARIA properties
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.
- 27d ago Changed · +110 tokens per session 46b73ee6a36c
- 1mo ago First seen · 105 lines · 0 tokens per session scan A bb767d7a2dcc
fec-figma-implementer is an agent published in the GitHub repository bovinphang/frontend-craft (22 stars, last pushed 28d ago), licensed MIT. It adds 110 tokens to every session and 996 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
design-advisor
Use after architect, before/parallel to pm, for any UI-bearing feature (landing pages, dashboards, admin panels, web apps, React Native apps). Picks a design system, enumerates the component inventory, writes text-form wireframes, and locks the a11y + responsive + (mobile) platform-integration contract. Outputs…
canvas-screen-builder
Adds or modifies one screen in an existing Canvas App from a shared contract and scoped brief, with local QA and no compilation.
canvas-create-discovery
Checks experience feasibility against actual controls, data, APIs and images and records candidate decisions and material constraints.
canvas-create-layout
Designs task-specific visual hierarchy, regions, density and responsive interaction before Canvas control selection.
canvas-create-builder
Describes selected controls and directly writes one new screen from an approved experience and feasibility decisions.
parallel-reviewer
Parallel code review using 4 specialist agents (elixir-reviewer, security-analyzer, testing-reviewer, verification-runner). Use for thorough review of significant changes.