agentmods.dev

mindforge-en

mindforge-en is a plugin for Claude Code from ProjAnvil/MindForge. Its manifest loads nothing; the 19 skills, 9 agents it bundles cost 1,451 tokens per session together, scanned A, original, MIT.

An English-language collection of coding agents and skills for code review, frontend and backend development, mobile apps, architecture, testing, and product management. It is intended to be paired with a style-rules plugin for controlled writing.

In plain words
What is it for?
Use it when a project needs focused help with frontend, backend, mobile, architecture, testing, reviews, or product work.
Why use it?
It provides several specialist roles and reusable instructions instead of treating every development task the same way.

Plugin for Claude Code

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

not rated 3repo yesterday A scan tokens not measured original MIT

Good fit Use it when a project needs focused help with frontend, backend, mobile, architecture, testing, reviews, or product work.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add ProjAnvil/MindForge
/plugin install mindforge-en
View source ↗ ProjAnvil/MindForge
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/ProjAnvil/MindForge

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 mindforge-en

README.md
[![agentmods](https://agentmods.dev/badge/plugins/projanvil/mindforge/mindforge-en/github.svg)](https://agentmods.dev/plugins/projanvil/mindforge/mindforge-en)
Your own site
<a href="https://agentmods.dev/plugins/projanvil/mindforge/mindforge-en"><img src="https://agentmods.dev/badge/plugins/projanvil/mindforge/mindforge-en/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mindforge-en

Your own site · 80×15
<a href="https://agentmods.dev/plugins/projanvil/mindforge/mindforge-en"><img src="https://agentmods.dev/badge/plugins/projanvil/mindforge/mindforge-en.svg" alt="Reviewed on agentmods" width="80" 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 19 skills, 9 agents cost 1,451 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

mindforge-en 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 today.

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/mindforge-en/.claude-plugin/plugin.json · 9 lines

What it actually says

{
  "name": "mindforge-en",
  "description": "MindForge agents and skills (English): 9 subagents and 18 skills covering code review, frontend/backend/mobile engineering, architecture, testing, and product management. Pair with style-rules@mindforge for the controlled-writing hook.",
  "version": "0.8.1",
  "author": {
    "name": "MindForge"
  }
}
Contents

What it installs

The manifest is a name and a version. 19 skills, 9 agents travel with it, and installing the plugin installs all of them — 1,451 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. today First seen · 9 lines scan A fa5ad7c91b67

Subscribe to this mod's changes

mindforge-en is a plugin published in the GitHub repository ProjAnvil/MindForge (3 stars, last pushed yesterday), 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 2026-10-17.

Building agentsai-agentsanthropicclaudemcpmodel-context-protocol
Related

Other plugins, from other repositories

octen

Real-time web search, broad multi-angle research, news, and URL extraction through Octen's hosted MCP server, plus image and video search in invite-only Beta. Authorizes over OAuth on first use — nothing to install and no API key to paste.

Octen-Team/octen-mcp · not measured

claude-omakase

Omakase-style skill discovery for Claude Code: the chef observes your work, finds matching skills in a federated catalog, and installs them after your approval. Bundles the Skill Suggester MCP server, the omakase-chef behavior skill, and three proactive hooks.

gyuch-an02/claude-omakase · not measured

slack-mcp

Multi-workspace Slack MCP server with draft+confirm safety, vault auto-export, and triple-mode auth (xoxc/xoxp/xoxb).

adelaidasofia/slack-mcp · not measured

unblockingapi

Give Claude a real browser: fetch bot-protected and JavaScript-heavy pages through UnblockingAPI, with structured JSON for any site a published template covers. Replaces the built-in web fetch.

unblockingapi/mcp · not measured

substack-mcp

FastMCP server for Substack: publish Notes and posts, pull analytics, manage drafts, bridge Obsidian vault drafts to Substack, and generate visual cards with pluggable image generators.

adelaidasofia/substack-mcp · not measured

hive

Collective browser automation intelligence. Share and discover reliable methods for web interactions across the Claude agent network.

Brainrot-Creations/claude-plugins · not measured