agentmods.dev

nxtg-forge

nxtg-forge is a plugin for Claude Code from nxtg-ai/forge-plugin. Its manifest loads nothing; the 27 skills, 24 commands, 33 agents it bundles cost 14,318 tokens per session together, scanned A, original, MIT.

A Claude Code plugin for managing AI-assisted software development with multiple agents, commands, skills, security checks, test auditing, drift detection, and shared memory. Claude Code is a coding assistant that works in a code repository.

In plain words
What is it for?
Use it to coordinate coding agents, check security and tests, detect changes from expected project behavior, and share context across development tasks.
Why use it?
It brings development rules, security checks, testing review, and shared project context into one setup. This can help teams keep AI-generated work aligned with their engineering standards.

Plugin for Claude Code

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

not rated 6repo changed 4d ago A scan tokens not measured original MIT

Good fit Use it to coordinate coding agents, check security and tests, detect changes from expected project behavior, and share context across development tasks.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add nxtg-ai/forge-plugin
/plugin install nxtg-forge
View source ↗ nxtg-ai/forge-plugin forge.nxtg.ai
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/nxtg-ai/forge-plugin

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 nxtg-forge

README.md
[![agentmods](https://agentmods.dev/badge/plugins/nxtg-ai/forge-plugin/nxtg-forge/github.svg)](https://agentmods.dev/plugins/nxtg-ai/forge-plugin/nxtg-forge)
Your own site
<a href="https://agentmods.dev/plugins/nxtg-ai/forge-plugin/nxtg-forge"><img src="https://agentmods.dev/badge/plugins/nxtg-ai/forge-plugin/nxtg-forge/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 nxtg-forge

Your own site · 80×15
<a href="https://agentmods.dev/plugins/nxtg-ai/forge-plugin/nxtg-forge"><img src="https://agentmods.dev/badge/plugins/nxtg-ai/forge-plugin/nxtg-forge.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 27 skills, 24 commands, 33 agents cost 14,318 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

nxtg-forge 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 4d 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/nxtg-forge/.claude-plugin/plugin.json · 24 lines

What it actually says

{
  "$schema": "https://claude.ai/schemas/plugin.json",
  "name": "nxtg-forge",
  "displayName": "NXTG Forge",
  "version": "3.14.0",
  "description": "Governance-native AI development \u2014 33 agents, 24 commands, 27 skills, 27 hooks (4 blocking security guards, an opt-in enforced-task test guard and Stop gate, a Stop check on required command output, and Semgrep scanning), drift detection (needs a configured model), an optional CRUCIBLE test-review prompt, and shared memory for Claude Code (alpha)",
  "defaultEnabled": true,
  "author": {
    "name": "NXTG AI",
    "email": "[email protected]",
    "url": "https://github.com/nxtg-ai"
  },
  "repository": "https://github.com/nxtg-ai/forge-plugin",
  "license": "MIT",
  "keywords": [
    "governance",
    "quality",
    "testing",
    "agents",
    "orchestration",
    "devops"
  ]
}
Contents

What it installs

The manifest is a name and a version. 27 skills, 24 commands, 33 agents travel with it, and installing the plugin installs all of them — 14,318 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. 4d ago Changed 883b65a98df9
  2. 5d ago Changed 45f344e062df
  3. 10d ago Changed 7a614592af71
  4. 11d ago Changed 2f8490fab858
  5. 1mo ago First seen · 24 lines scan A 6809649a5caf

Subscribe to this mod's changes

nxtg-forge is a plugin published in the GitHub repository nxtg-ai/forge-plugin (6 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 2026-09-03.

Building agentsClaude CodeTestingaiai-agentsai-developmentclaudecoding-assistant
Related

Other plugins, from other repositories

atdd

Acceptance Test Driven Development for Claude Code. Enforces the ATDD methodology: write Given/When/Then specs first, generate a project-specific test pipeline, maintain two test streams (acceptance + unit). Inspired by Robert C. Martin's acceptance test approach from empire-2025.

swingerman/engineer · not measured

crap-analyzer

Analyze recently-changed code for Change Risk Anti-Patterns. Computes CRAP per changed function across TypeScript, JavaScript, Python, Java, Kotlin, Go, Ruby, C#, Rust, and PHP. Auto-discovers how the repo generates coverage and proposes refactors + test stubs.

swingerman/engineer · not measured

don-cheli-sdd

Full SDD (Spec-Driven Development) framework for Claude Code. 72+ slash commands (/dc:), 14 reusable skills, 15 reasoning models, TDD as an iron law, and i18n support (ES/EN/PT). Turn requirements into tested, documented, production-ready code through 7 disciplined lifecycle phases.

doncheli/don-cheli-sdd · not measured

god-prompt-mcp

GodPrompt engineering workflows for task routing, TDD, debugging, verification, and progressive disclosure.

AKzar1el/god-prompt-mcp · not measured

testing-expert

Test strategy and implementation: unit/integration/e2e, TDD, mocking, fixtures, and coverage.

Miaoge-Ge/coding-agent-skills · not measured

macos-sandbox

Smoke-test macOS .app/.pkg in disposable Tart VMs via the macbox CLI or MCP.

robzilla1738/roberts-skills · not measured