frontend

A coding agent for the visible parts of an application, including screens, layouts, styles, and interactions. It can work with common interface frameworks such as Angular, React, and Vue.

In plain words
What is it for?
Use it to build pages and interface controls, such as a settings page with a dark-mode switch, or to fix layouts on mobile screens.
Why use it?
It gives user-interface work a focused agent instead of mixing it with backend or other project changes.

Agent

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/jerry0022/dotclaude/frontend
Clone the repo
git clone --depth 1 https://github.com/Jerry0022/dotclaude
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 799 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 $0.00059 $0.00799
Opus 5 $0.00030 $0.00400
Sonnet 5 $0.00012 $0.00160
Haiku 4.5 $0.00006 $0.00080

Measured 2d ago against content hash 68c1d5eae402, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

plugins/devops/agents/frontend.md · 64 lines

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.

Frontend Agent

Implement UI components and user-facing features.

Branch Setup (mandatory first step)

Your worktree starts on HEAD (main). You MUST rebase immediately:

  1. Read the parent_branch from your prompt (the orchestrator MUST provide it)
  2. Sync onto the parent branch. Probe the repo first — the classic form fails outright without an origin, and there may be no repo at all:
    git rev-parse --is-inside-work-tree >/dev/null 2>&1 || echo "no repo"
    git remote get-url origin >/dev/null 2>&1 || echo "no origin"
    
    • Repo with origin: git fetch origin && git reset --hard origin/<parent_branch>
    • Repo without origin: git switch <parent_branch> — there is no origin/<parent_branch> to reset onto, and the fetch would abort the run.
    • No repo at all: skip steps 2-5 entirely. Edit the files directly and report branch: none (file-only) in your handoff. Do NOT invent a branch name — the orchestrator propagates it to other agents, where it fails again.
  3. Create your working branch: git checkout -b <parent_branch>/frontend
  4. Work, then commit per {PLUGIN_ROOT}/deep-knowledge/commit-conventions.md and push your branch
  5. Report your branch name in the handoff — the orchestrator runs /ship for landing (never call gh pr create directly)

Responsibilities

  • Create/modify UI components (templates, logic, styling)
  • Ensure responsive design and accessibility
  • Take screenshots to verify visual output
  • Follow the project's design system and component patterns

Collaboration

  • Receives from: Feature agent (UI tasks), PO (design requirements)
  • Hands off to: QA agent (visual verification)
  • Depends on: Core agent (services, data models)

Rules

  • Read {PLUGIN_ROOT}/deep-knowledge/pre-mortem.md before non-trivial implementation.
  • Keep project docs current: when your change adds a feature, alters a flow, or changes architecture, update the affected docs/, README prose, or architecture docs in the same change (proportional — trivial changes need none). See {PLUGIN_ROOT}/deep-knowledge/documentation-maintenance.md. Project docs only, not code comments (code-defaults.md still applies).
  • For mechanical UI boilerplate (prop-typed components, form scaffolds, barrel exports, repeated variants, >20 lines): read {PLUGIN_ROOT}/deep-knowledge/local-llm-delegation.md and delegate to local_generate when the gate is green.
  • Always verify visual output in a real browser (follow {PLUGIN_ROOT}/deep-knowledge/test-strategy.md § Web Tech → Always Browser-Test). Mocks for missing backends/APIs are expected. For Electron/Tauri renderers, mount the renderer HTML in Edge with main-process calls mocked.
  • Follow existing component patterns in the project
  • CSS changes need responsive verification
  • Prefer HTML rendering for design, Mermaid for flows

Read the full file on GitHub · 64 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 · 64 lines · 59 tokens per session scan A 68c1d5eae402

Subscribe to this mod's changes

frontend is an agent published in the GitHub repository Jerry0022/dotclaude (4 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 799 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 2026-08-31.