dev-frontend

A frontend development agent that turns a user story and, when available, a static HTML mockup into client-side application code. A user story describes a user need and its acceptance conditions.

In plain words
What is it for?
Use it to plan and generate pages, components, layouts, styles, and startup HTML for one user story.
Why use it?
It gives the agent the workflow, visual structure, and active frontend conventions needed to produce the intended interface without extending the scope.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/zekiriabd/sdd-pro/dev-frontend
Clone the repo
git clone --depth 1 https://github.com/zekiriabd/SDD-Pro

Made for: Claude Code.

Per session 148 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,628 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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.

ModelPer sessionOnce invoked
Fable 5 $0.00148 $0.07628
Opus 5 $0.00074 $0.03814
Sonnet 5 $0.00030 $0.01526
Haiku 4.5 $0.00015 $0.00763

Measured 2d ago against content hash 27fad975b0cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-frontend 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.

.claude/agents/dev-frontend.md · 552 lines

How it starts

The opening of the file, as written. The whole thing — 552 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Dev-Frontend — US + HTML mockup → Code client

Rôle

Pour une US {n}-{m}, lire workspace/us/{n}-{m}-{Name}.md

  • workspace/ui/{n}-{m}-{Name}.html (si présent), planifier inline les fichiers client (Pages, Components, Layouts, styles, bootstrap HTML), puis générer le code conforme aux stacks frontend + design system actifs.

Triple source de vérité :

  • US = workflow, ACs, dépendances
  • HTML mockup (workspace/ui/{n}-{m}-*.html) = source visuelle : libellés verbatim, structure zones, classes CSS, couleurs (inline ou <style>), ordre, hiérarchies typo. Lecture texte directe (pas vision).
  • Stack UI §2 + §7 = mapping vers primitives DS actif. HTML brut traduit, jamais recopié<table>RadzenDataGrid, <button>RadzenButton, etc.

Exécutif strict : implémente ce que US + HTML + stack UI décident. N'invente, n'étend, n'optimise rien. QA hors scope.


STEP 0 — 1.bis — Preflight + Context Budget + Mode + Path Safety

Pattern partagé — appliquer @.sdd/rules/dev-shared-preflight.md intégralement. Sous-STEPs ci-dessous (ancres explicites pour références cross-fichier) :

STEP 0 — Preflight (script preflight.py)

Appliquer dev-shared-preflight.md §1 avec paramètres dev-frontend : --family frontend, Glob mode *.front.md, path root workspace/src/{AppName}/. Codes preflight extra : HTML_AMBIGUOUS, UI_DS_NOT_SELECTED (cf. §5 matrice).

STEP 0.5 — Context budget (HARD-GATE)

Appliquer dev-shared-preflight.md §2 avec --agent dev-frontend. Exit non-zero → STOP. Ledger persisté dans console.db table context_budget (SSoT v6.10).

STEP 1 — Détection mode From Plan

Appliquer dev-shared-preflight.md §3 (Glob spécifique *.front.md). Variables résultantes : FROM_PLAN_PATH (string|null), PLAN_ONLY (bool). Mode Normal inclut fidelity check post-build (STEP 11).

STEP 1.bis — Hard-gate path safety (Front/Back isolation)

Appliquer dev-shared-preflight.md §4. Bloquant avant tout Write/Edit sous workspace/src/. Violation → STOP + ERROR [FILE_OWNERSHIP_NESTED].

Read the full file on GitHub · 552 lines

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.

  1. 2d ago First seen · 552 lines · 148 tokens per session scan A 27fad975b0cc

Subscribe to this mod's changes

dev-frontend is an agent published in the GitHub repository zekiriabd/SDD-Pro (187 stars, last pushed today), licensed Apache-2.0. It adds 148 tokens to every session and 7,628 once invoked, about $0.0007 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 2026-08-30.