web-dev

A web-development workflow that connects user research, design review, frontend implementation, and screenshot comparison.

In plain words
What is it for?
Use it to research users, review designs, implement mockups on any web technology, and check pages with browser tests and visual comparisons.
Why use it?
It helps teams catch differences between an approved design and the built website, including issues found through testing and accessibility review.

Plugin 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.

Claude Code
/plugin marketplace add endorphin-ai/hasbrains-agent-kit
agentmods
npx agentmods add plugins/endorphin-ai/hasbrains-agent-kit/web-dev
Clone the repo
git clone --depth 1 https://github.com/endorphin-ai/hasbrains-agent-kit

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

web-dev 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 yesterday.

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.

web-dev/.claude-plugin/plugin.json · 10 lines

What it actually says

{
  "name": "web-dev",
  "version": "1.2.0",
  "description": "Multi-agent web dev pipeline — UX research and design critique around the build, plus the designer ↔ frontend contract: freeze approved mockups into a canonical oracle, port them 1:1 on any stack, and verify with screenshot-based design-diff gates.",
  "author": { "name": "Andrew Novykov", "url": "https://github.com/andrewnovykov" },
  "repository": "https://github.com/endorphin-ai/hasbrains-agent-kit",
  "license": "MIT",
  "keywords": ["claude-code", "web-development", "ux-research", "design-review", "accessibility", "playwright", "visual-regression", "design-to-code", "e2e-testing"]
}
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. yesterday First seen · 10 lines scan A e13e8eb75960

Subscribe to this mod's changes

web-dev is a plugin published in the GitHub repository endorphin-ai/hasbrains-agent-kit (4 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Related

Other plugins, from other repositories

ops

Structured non-code project management for Claude Code: planning, execution, knowledge persistence, and autonomous work loops for research, strategy, and content projects. 9 skills, 5 agents, 7 commands.

OdinMB/ops-workflow · not measured

vp-beads

Sprint workflow automation: backlog grooming, retrospectives, upstream vendor tracking, cross-project synergy tracking, swarm wave orchestration, vendor sync, and bilateral sibling reconciliation for projects using beads and Basic Memory.

voxpelli/claude-beads · not measured

erpaval

ERPAVal — autonomous software development workflow for Claude Code. Comprehensive standalone bundle: the erpaval workflow plus 10 vendored companion skills (product-discovery, research, ultraplan, tech-stack-builder, product-strategy, working-backwards, customer-research, meta-prompt-optimizer, product-design-shared…

theagenticguy/erpaval · not measured

compound-selfcheck

PostToolUse soft-prompt: when a Write/Edit/MultiEdit/NotebookEdit produces > 100 LOC or > 5KB, emits a stderr reminder to ingest the change into a knowledge base (Compound Engineering, not one-shot). Audit-logs [COMPOUND-CHECK] entries to .harness/hook-trace.log for real-trigger vs performance distinction. Soft-prompt.

mr-shaper/keel-harness · not measured

soleur

Soleur plugin marketplace. Provides the Soleur AI organization plugin for Claude Code.

jikig-ai/soleur · not measured

claude-hangar

Production-grade Claude Code environment with 42 skills, 22 agents, 31 hooks, and 9 framework stacks — optimized for Claude Code v2.1.116.

claude-hangar/claude-hangar · not measured