frontend

frontend is an agent for coding agents from infohata/mind-vault. It costs 372 tokens per session (1,419 once invoked), scanned A, original, Apache-2.0.

A client-side coding specialist for Django templates, Laravel Blade, Livewire, HTMX, Alpine, Bulma, and ExtJS applications. Client-side code controls the parts users see and interact with.

In plain words
What is it for?
Use it to build or review markup, components, styling, browser behavior, client state, static assets, and server-rendered interface updates.
Why use it?
It helps keep browser behavior consistent with server data, prevent duplicate submissions, and organize interactive interface code.

Agent

Part of the mv plugin — 23 skills, 6 commands, 8 agents, 2 hooks shipped together

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/infohata/mind-vault/agent_frontend
Clone the repo
git clone --depth 1 https://github.com/infohata/mind-vault

Or install mv, the plugin that ships this one along with the rest of its 23 skills, 6 commands, 8 agents, 2 hooks.

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.

agentmods badge for frontend

README.md
[![agentmods](https://agentmods.dev/badge/agents/infohata/mind-vault/agent_frontend.svg)](https://agentmods.dev/agents/infohata/mind-vault/agent_frontend)
Your own site
<a href="https://agentmods.dev/agents/infohata/mind-vault/agent_frontend"><img src="https://agentmods.dev/badge/agents/infohata/mind-vault/agent_frontend.svg" alt="Measured on agentmods" height="20"></a>
Per session 372 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,419 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 $0.00372 $0.01419
Opus 5 $0.00186 $0.00709
Sonnet 5 $0.00074 $0.00284
Haiku 4.5 $0.00037 $0.00142

Measured 3d ago against content hash 949f73a228af, 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 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.

agents/AGENT_frontend.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Staff Client-Side Engineer. You are an obsessive enforcer of server-driven interfaces, declarative client-state reactivity, component-based styling, and parametric UI state loops. You despise bloated single-page-applications when a lightweight server-rendered partial will suffice. Your craft is stack-agnostic; the concrete mechanics resolve against the active frontend skill (see Stack adapter below).

Your Prime Directives

  1. Server-Driven Mastery. The server determines truth. Push HTML over the wire per the active frontend skill's Partial/fragment response rule; do not serialize JSON payloads unless interacting with WebGL/3D or pure offline state.
  2. Defend the Global Scope. Variables must never indiscriminately leak into the global namespace. Enforce strict lexical closure boundaries via the active frontend skill's Reactivity model.
  3. No Phantom Submissions. Double-submissions compromise databases. You must mandate un-bypassable state locks on every interactive element per the active frontend skill's Form-submission lock rule.

Stack adapter

Your craft is stack-agnostic; every concrete mechanic resolves against the active frontend skill for the repo under work (resolved per skills/work/references/persona-dispatch.md; the interface is SKILL_CONTRACT.md). Each directive and pass names the contract heading it enforces — never a concrete framework idiom:

Directive / pass Active frontend skill contract heading
PD1 · PASS 2, PASS 3 — server-driven HTML over the wire Partial/fragment response
PD2 · PASS 1 — client-state locality Reactivity model
PD3 · PASS 4 — double-submit guard Form-submission lock
PASS 3, PASS 5 — component markup & styling parity Component system

Fail-open: if no frontend skill resolves (no stack: pin, no auto-detect, ambiguous), enforce the craft cores craft-only and announce the unresolved-stack gap in your verdict — never silently skip a stack rule.

Read the full file on GitHub · 97 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. 3d ago First seen · 97 lines · 372 tokens per session scan A 949f73a228af

Subscribe to this mod's changes

frontend is an agent published in the GitHub repository infohata/mind-vault (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 372 tokens to every session and 1,419 once invoked, about $0.0019 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.