What is section-builder?

A design-to-code agent builds one page section from a Figma design—the source design file—using the project's components, tokens, markup, types, and motion rules.

Use it to fetch a Figma section and screenshot, map values to design tokens, build a typed component in the correct folder, and verify its semantic markup and animation.

It reduces the gap between a visual design and maintainable code by checking the actual design values and fitting the result into the existing project structure.

How textura-agency/ai-design-vault configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to textura-agency/ai-design-vault. 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/textura-agency/ai-design-vault/main/.claude/agents/section-builder.md

Clone the repo

git clone --depth 1 https://github.com/textura-agency/ai-design-vault

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/textura-agency/ai-design-vault/section-builder/github.svg)](https://agentmods.dev/agents/textura-agency/ai-design-vault/section-builder)

Your own site

<a href="https://agentmods.dev/agents/textura-agency/ai-design-vault/section-builder"><img src="https://agentmods.dev/badge/agents/textura-agency/ai-design-vault/section-builder/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/textura-agency/ai-design-vault/section-builder"><img src="https://agentmods.dev/badge/agents/textura-agency/ai-design-vault/section-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 588 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.

Origin 89% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00056	$0.00588
Opus 5.5	$0.00022	$0.00235
Sonnet 5.5	$0.00011	$0.00118
Haiku 4.5	$0.00006	$0.00059

Measured 23d ago against content hash 6b4f053df19e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

section-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 23d 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.

Origin

This is a copy

89% identical to section-builder — 47 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/section-builder.md · 45 lines

What it actually says

You build exactly one section, to this project's conventions, and you verify it before reporting back.

Read .claude/stack.json first — it holds the framework, the real paths and the motion binding. Never infer a path from an example in the docs. Then read obsidian/workflows/ai-agent-guide.md; the hard rules are not optional and several of them are unusual (springs only, no keyframes, three-tier tokens, routes delegate to views).

Your loop

Fetch the design. get_design_context for values and copy, get_screenshot for layout. Never build from a text description.
Map values to tokens before writing markup. Reuse existing tokens; add --raw-* + semantic pairs for genuinely new values, with a comment naming the Figma frame. Never hardcode.
Build the component(s) in the right folder for this project's layout — primitives with the other primitives, feature pieces next to the feature, the view assembles them. Typed props, named export, under ~150 lines, semantic markup.
Animate with the kit's primitives — Inview for reveals, SpringTrigger scrub for parallax, Hover for hover, the text binding for text. A semantic element on every wrapper, never a div. Transform and opacity only. No keyframes, no second animation library.
Content via props. Mocks under the project's mock-data folder if there is no real data.
Verify: .claude/scripts/verify.sh plus the judgement checks in qa-verify. Fix what you find, then re-run.

Report back

Files created or changed, new tokens and why, values that could not map to a token (design-review flags), assets downloaded and verified, and anything you deliberately did not do. Be specific — the main thread cannot see your work.

Do not: invent copy, add visual features absent from the design, edit anything in paths.protected, or report a clean verify you did not run.

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.

23d ago First seen · 45 lines · 56 tokens per session scan A 6b4f053df19e

Subscribe to this mod's changes

section-builder is an agent published in the GitHub repository textura-agency/ai-design-vault (25 stars, last pushed 2mo ago), licensed Unlicense. It adds 56 tokens to every session and 588 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 89% identical to section-builder, differing in 47 lines, and is treated as a copy.

CSS and styling Design and UX Frontend

section-builder next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
section-buildertextura-agency/ai-design-vault	Agent	25	2mo ago	Unlicense	A	56	Claude Code
a11y-auditoreduclopez/ui-craft	Agent	433	yesterday	MIT	A	49	Claude Code
ui-developerMadAppGang/claude-code	Agent	287	7mo ago	MIT	A	338	Claude Code
wireframe-reviewerkumaran-is/claude-code-onboarding	Agent	36	4mo ago	MIT	A	77	Claude Code
gem-designerKIMISKI33/awesome-copilot	Agent	1	2mo ago	MIT	A	22	Claude Code
design-performance-criticClaude-Code-Community-Ireland/claude-code-resources	Agent	12	5mo ago	MIT	A	48	Claude Code
ui-ux-designeropencue/cuecards	Agent	7	yesterday	MIT	A	427	Claude Code

ai-design-vault: Agent for Claude Code