forge-plugin CLAUDE.md

forge-plugin CLAUDE.md is an instructions file for coding agents from nxtg-ai/forge-plugin. It costs 3,599 tokens per session, scanned D, original, MIT.

Repository-specific instructions for the Forge Claude Code plugin. The plugin uses Markdown files for commands, agents, skills, and hooks, plus a small governance server.

In plain words
What is it for?
Finding plugin components, checking its command and skill structure, installing its server dependencies when needed, and starting the governance MCP server.
Why use it?
It explains the plugin's layout and setup so edits go in the right place and the governance server can be run correctly.

Instructions file

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

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 instructions/nxtg-ai/forge-plugin/claude-md
Clone the repo
git clone --depth 1 https://github.com/nxtg-ai/forge-plugin

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 forge-plugin CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nxtg-ai/forge-plugin/claude-md.svg)](https://agentmods.dev/instructions/nxtg-ai/forge-plugin/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nxtg-ai/forge-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/nxtg-ai/forge-plugin/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,599 This file is loaded in full into every session.
When invoked 3,599 The same file — it is already loaded in full.
Security scan D 4 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 $0.03599 $0.03599
Opus 5 $0.01800 $0.01800
Sonnet 5 $0.00720 $0.00720
Haiku 4.5 $0.00360 $0.00360

Measured 4d ago against content hash 14dd03baeade, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

forge-plugin CLAUDE.md scanned grade D with 4 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

| **PreToolUse (Bash)** | `security-command-guard.sh` | **BLOCKS** dangerous commands: `rm -rf /`, `chmod 777`, `curl\|sh`, fork bombs, force push to main |

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

| **PreToolUse (Bash)** | `security-command-guard.sh` | **BLOCKS** dangerous commands: `rm -rf /`, `chmod 777`, `curl\|sh`, fork bombs, force push to main |

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| **PreToolUse (Bash)** | `security-command-guard.sh` | **BLOCKS** dangerous commands: `rm -rf /`, `chmod 777`, `curl\|sh`, fork bombs, force push to main |

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

| **PreToolUse (Write/Edit)** | `security-injection-guard.sh` | **BLOCKS** `eval()`, `os.system()`, `subprocess(shell=True)`, `child_process.exec()` |
CLAUDE.md · 282 lines

How it starts

The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Forge Plugin

Claude Code plugin for AI-powered development governance. Pure markdown — no build step. Commands, agents, skills, and hooks are loaded by Claude Code at runtime.

Quick Reference

# No build step. All content is markdown loaded by Claude Code.

# MCP server (auto-installs deps on first run)
cd plugins/nxtg-forge/servers/governance-mcp
npm install   # only if node_modules missing
node index.mjs

# Plugin lives at: plugins/nxtg-forge/
# Installed by Claude Code via: claude plugin marketplace add nxtg-ai/forge-plugin && claude plugin install nxtg-forge

Plugin Structure

plugins/nxtg-forge/
├── .claude-plugin/
│   └── plugin.json           # Manifest (name, version, description)
├── .mcp.json                 # MCP server config (governance-mcp via stdio)
├── commands/                 # 23 slash commands (*.md)
├── agents/                   # 23 agent definitions (*.md)
├── skills/                   # 27 skill directories (*/SKILL.md)
├── hooks/                    # 6 governance hooks (bash scripts)
│   ├── hooks.json            # Hook trigger definitions
│   └── scripts/lib.sh        # Shared utilities
└── servers/
    └── governance-mcp/       # Node.js MCP server (index.mjs, 8 tools)
        ├── package.json      # @nxtg-forge/governance-mcp v3.5.1
        ├── index.mjs         # 835 lines, ES module
        └── start.sh          # Auto-install launcher

Components

21 Slash Commands

Category Commands
Governance /forge:init, /forge:status, /forge:status-enhanced, /forge:gap-analysis, /forge:compliance, /forge:command-center
Feature Dev /forge:feature, /forge:spec, /forge:agent-assign, /forge:integrate
Quality /forge:test, /forge:deploy, /forge:optimize, /forge:update
State /forge:checkpoint, /forge:restore, /forge:report
Docs /forge:docs-status, /forge:docs-update, /forge:docs-audit
Dashboard /forge:dashboard

Read the full file on GitHub · 282 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. 4d ago First seen · 282 lines · 3,599 tokens per session scan D 14dd03baeade

Subscribe to this mod's changes

forge-plugin CLAUDE.md is an instructions file published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed today), licensed MIT. It adds 3,599 tokens to every session, about $0.0180 per session on Opus 5. A static security scan graded it D with 4 findings (asks for root, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories