Borrowing it
Nothing to install: this file belongs to sifter-ai/sifter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sifter-ai/sifter/main/.agents/skills/sdd-ui/SKILL.mdgit clone --depth 1 https://github.com/sifter-ai/sifterWrote 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/skills/sifter-ai/sifter/sdd-ui)<a href="https://agentmods.dev/skills/sifter-ai/sifter/sdd-ui"><img src="https://agentmods.dev/badge/skills/sifter-ai/sifter/sdd-ui/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/skills/sifter-ai/sifter/sdd-ui"><img src="https://agentmods.dev/badge/skills/sifter-ai/sifter/sdd-ui.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 | $0.00035 | $0.00891 |
| Opus 5.5 | $0.00014 | $0.00356 |
| Sonnet 5.5 | $0.00007 | $0.00178 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
sdd-ui 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 2mo 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDD UI — Visual Component Editor
Purpose
Use this workflow when implementing a React component from a screenshot reference in an SDD project. The split-panel editor shows the spec screenshot on the left and the live component on the right, so you can iterate visually until they match.
Prerequisites
sddCLI installed globally- Playwright MCP configured in Claude Code settings
- e.g.
@playwright/mcpor@executeautomation/playwright-mcp - If not configured, inform the user and stop — visual feedback won't work without it
- e.g.
Workflow
Step 1 — Read the spec
Read the SDD feature file to understand what the component should look like and do. Look for any screenshot paths referenced in the feature doc.
Step 2 — Launch the editor
# Single screenshot — detached (recommended when run by an agent)
sdd ui launch-editor LoginForm \
--screenshot product/features/auth/login.png \
--detach
# Multiple screenshots (e.g. desktop + mobile)
sdd ui launch-editor LoginForm \
--screenshot product/features/auth/login-desktop.png \
--screenshot product/features/auth/login-mobile.png \
--detach
The command will:
- Scaffold
code/components/LoginForm.tsxif it doesn't exist - Print the exact component file path to edit
- Start the editor at
http://localhost:5174
With --detach the process runs in background and the terminal is immediately free.
Without --detach it runs in foreground (use Ctrl+C to stop).
With multiple screenshots, the left panel shows a tab per screenshot. With a single screenshot, no tab bar is shown.
Step 3 — Implement the component
Edit the file printed by sdd ui launch-editor (e.g. code/components/LoginForm.tsx).
Write a React component that matches the screenshot. Use standard HTML/CSS or inline styles — no external UI library unless the project already uses one.
Vite HMR will update the right panel automatically on every save.
Step 4 — Visual check with Playwright
After each save, screenshot the live preview and compare it with the spec:
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.
- 2mo ago First seen · 114 lines · 35 tokens per session scan A b0032a9fee00
sdd-ui is a skill published in the GitHub repository sifter-ai/sifter (54 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 891 once invoked, about $0.0001 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.
sdd-ui compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sdd-uisifter-ai/sifter | Skill | 54 | 1mo ago | MIT | A | 35 | Claude Code |
| chakra-ui-builderchakra-ui/chakra-ui | Skill | 41k | yesterday | MIT | A | 214 | Claude Code, Codex |
| tamagui-v6-configtamagui/tamagui | Skill | 14k | today | MIT | A | 0 | Claude Code, Codex |
| tamagui-theme-generatortamagui/tamagui | Skill | 14k | today | MIT | A | 48 | Claude Code, Codex |
| frontend-ui-dark-tsmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 48 | Claude Code |
| cobejsMengTo/Skills | Skill | 7.3k | yesterday | MIT | A | 31 | Claude Code, Codex |
| vercel-composition-patternscalesthio/OpenMontage | Skill | 77k | 3d ago | AGPL-3.0 | A | 58 | Claude Code, Codex |