agentmods.dev

claude-craft

claude-craft is a plugin for Claude Code from TheBeardedBearSAS/claude-craft. Its manifest loads nothing; the 56 skills, 94 commands, 47 agents, 5 hooks it bundles cost 3,902 tokens per session together, scanned A, original, MIT.

A team framework for Claude Code that supports several technology stacks, sprint planning, browser checks, and a Kanban board. It is aimed at technical leads introducing Claude Code to a development team.

In plain words
What is it for?
Use it to organize sprints, track work on a Kanban board, and run browser-based quality checks across stacks such as React, Symfony, Flutter, Angular, Laravel, Vue, Python, PHP, and C#.
Why use it?
It gives a team a shared way to plan work, build software, and check websites in a browser. This reduces the need to assemble separate processes for each technology stack.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest. Also seen: mentions Claude Code.

not rated 105repo 4d ago A scan tokens not measured original MIT

Good fit Use it to organize sprints, track work on a Kanban board, and run browser-based quality checks across stacks such as React, Symfony, Flutter, Angular, Laravel, Vue, Python, PHP, and C#.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add TheBeardedBearSAS/claude-craft/plugin install claude-craft
View source ↗ TheBeardedBearSAS/claude-craft
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.

Clone the repo
git clone --depth 1 https://github.com/TheBeardedBearSAS/claude-craft

Made for: Claude Code.

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 claude-craft

README.md
[![agentmods](https://agentmods.dev/badge/plugins/thebeardedbearsas/claude-craft/claude-craft.svg)](https://agentmods.dev/plugins/thebeardedbearsas/claude-craft/claude-craft)
Your own site
<a href="https://agentmods.dev/plugins/thebeardedbearsas/claude-craft/claude-craft"><img src="https://agentmods.dev/badge/plugins/thebeardedbearsas/claude-craft/claude-craft.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 56 skills, 94 commands, 47 agents, 5 hooks cost 3,902 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

claude-craft 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 7d 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-plugin/plugin.json · 41 lines

What it actually says

{
  "$schema": "https://claude.ai/schemas/plugin.json",
  "name": "claude-craft",
  "displayName": "Claude Craft",
  "version": "8.22.0",
  "description": "Multi-stack framework for Claude Code teams: 12 stacks, BMAD v6 sprint workflow, browser QA automation, and Kanban — for tech leads adopting Claude Code with their team.",
  "author": {
    "name": "Flavien Métivier",
    "email": "[email protected]",
    "url": "https://the-bearded-bear.com"
  },
  "repository": "https://github.com/TheBeardedBearSAS/claude-craft",
  "homepage": "https://the-bearded-bear.com/claude-craft",
  "license": "MIT",
  "keywords": [
    "framework",
    "multi-stack",
    "bmad",
    "sprint",
    "qa-automation",
    "tech-leads",
    "ddd",
    "clean-architecture",
    "tdd",
    "claude-code",
    "symfony",
    "react",
    "flutter",
    "angular",
    "laravel",
    "vuejs",
    "vite",
    "vercel",
    "react-native",
    "csharp",
    "python",
    "php",
    "paperclip"
  ]
}
Contents

What it installs

The manifest is a name and a version. 56 skills, 94 commands, 47 agents, 5 hooks travel with it, and installing the plugin installs all of them — 3,902 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 41 lines scan A e617cd501f47

Subscribe to this mod's changes

claude-craft is a plugin published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 4d 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 2026-08-30.

Browser automationClaude CodeProject managementagentsai-toolsbmadclean-architectureddd
Related

Other plugins, from other repositories

planning

Pre-implementation planning pipeline: chart a too-big, foggy effort as a decision map, diverge on candidate approaches, lock product intent and the engineering contract, route resolved domain language to the domain-driven-design glossary steward, explore the design space, stress-test adversarially, and produce a…

melodic-software/claude-code-plugins · not measured

playwright

Live E2E browser automation via Microsoft's @playwright/cli — named sessions, accessibility-ref snapshots, click/fill by ref, screenshots, console and network capture, mocking, tracing, video, and auth state, with artifacts written to disk so only paths enter context, plus a vendored upstream baseline and maintainer…

melodic-software/claude-code-plugins · not measured

firecrawl

Web scraping, search, crawling, and file parsing through the firecrawl-cli binary with a write-to-disk-then-Read pattern that keeps large results out of context — a user-facing wrapper skill, a lazy-install setup skill, and a separate gated maintainer update skill tracking the upstream CLI and skill source.

melodic-software/claude-code-plugins · not measured

LUXOR Specialized Tools

Specialized developer tools including Playwright, Linear, asyncio patterns, unix-goto, and Pydantic.

manutej/luxor-claude-marketplace · not measured

uitkit-automation

Browser automation, Playwright, SaaS scaffolding, spec-to-repo generation, IoT, embedded systems, game dev, and office document automation.

UitbreidenOS/UitKit · not measured

nextjs

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

vercel/next.js · not measured