Borrowing it
Nothing to install: this file belongs to zekiriabd/SDD-Pro. 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/zekiriabd/SDD-Pro/main/.claude/commands/sdd-reverse-ui.mdgit clone --depth 1 https://github.com/zekiriabd/SDD-ProWrote 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/commands/zekiriabd/sdd-pro/sdd-reverse-ui)<a href="https://agentmods.dev/commands/zekiriabd/sdd-pro/sdd-reverse-ui"><img src="https://agentmods.dev/badge/commands/zekiriabd/sdd-pro/sdd-reverse-ui.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 | $0.00066 | $0.00865 |
| Opus 5 | $0.00033 | $0.00432 |
| Sonnet 5 | $0.00013 | $0.00173 |
| Haiku 4.5 | $0.00007 | $0.00086 |
Grade A, and why
sdd-reverse-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 3d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sdd-reverse-ui {U-N} [--json]
Rôle
Lancer la Phase 4 : traduire les templates legacy d'une unité U-N en mockups HTML sémantiques préservant la structure visuelle (sans clonage pixel-perfect).
Args
| Arg | Type | Description |
|---|---|---|
{U-N} |
string requis | Identifiant U-N stable, doit avoir une FEAT Phase 3 déjà produite |
--json |
flag | Émet rapport extraction en JSON |
Pré-conditions
- Phase 1 + Phase 3 préalables pour cette unité :
workspace/old/{P}/.sys/inventory.jsoncontientunits[id={U-N}]inventory.json._featAllocations[{U-N}]renseigné → résolutionnfigéeworkspace/feats/{n}-{FeatName}.mdexiste (sinon → ERROR[REVERSE_NO_SOURCE])
- Les
units[U-N].evidenceFilescontiennent au moins 1 fichier UI (.aspx,.ascx,.cshtml,.jsp,.blade.php,.html,.dfm,.frm,.xaml). Sinon → SKIP silencieux (unité backend-only sans UI). (.xamlajouté 2026-06-10 — audit M12 : WPF supporté en Phase 1 mais SKIPpé en silence en Phase 4.)
Actions
- Spawn unique
Agent(reverse-ui-extractor)avec args ={U-N} - L'agent suit STEP 1 à 5 documenté dans
.sdd/agents/reverse-ui-extractor.md - Délégation scripts déterministes :
css_palette_extractor+ui_template_parser - Génération 1-5 fichiers HTML par unité (selon écrans détectés)
- Émission ligne chat finale
[REVERSE] {U-N} → {M} écran(s) UI. (75%)
Sortie
workspace/ui/
├── {n}-1-{Name}.html (écran principal)
├── {n}-2-{Name}.html (modale / wizard step 2 / écran secondaire, si applicable)
└── ...
Format : HTML5 sémantique pur (pas de framework UI inline). Mapping vers Radzen/Vuetify/shadcn fait par dev-frontend lors de /sdd-full {n}.
Voie d'usage standard
Phase 4 est optionnelle. Elle s'invoque après Phase 3 :
/sdd-reverse-inventory MyLegacy
/sdd-reverse U-3 # Phase 3 → FEAT 7-Login.md
/sdd-reverse-ui U-3 # Phase 4 → workspace/ui/7-1-Login.html
Skip cohérent : si le Tech Lead préfère que dev-frontend regénère l'UI from scratch via le mapping FEAT-only (sans mockup HTML), ne pas lancer cette phase. La FEAT seule reste valide pour /sdd-full.
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.
- 3d ago First seen · 64 lines · 66 tokens per session scan A d61ab52de7fa
sdd-reverse-ui is a command published in the GitHub repository zekiriabd/SDD-Pro (191 stars, last pushed 4d ago), licensed Apache-2.0. It adds 66 tokens to every session and 865 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 2026-09-03.
Other commands, from other repositories
sddesign
Full spec-driven pipeline — walks brief → tokens → shape (spec) → craft (build) → converge → ship in one guided run. Writes .ui-craft/spec.md. Run when starting a net-new surface from scratch.
seed-create-component
A command for creating a new SEED Design component, including its source specification, recipes, React implementation, documentation, examples, and optional headless layer.
craft
One-shot build pipeline for a complete surface from an outcome recipe — inputs (or defaults) → composition → theme → build order → acceptance bar. Use when the user asks for a whole surface ("build me a dashboard", "I need a landing page") and expects a shippable result, not component-level help.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
spec-screenshot
Analyze website screenshots and generate detailed implementation specs.