insforge-mcp CLAUDE.md

insforge-mcp CLAUDE.md is an instructions file for coding agents from InsForge/insforge-mcp. It costs 1,204 tokens per session, scanned A, original, Apache-2.0.

Instructions for publishing the Insforge MCP package to npm, the registry used to distribute JavaScript packages. They describe separate development and production release processes.

In plain words
What is it for?
Building the package, publishing development or production releases, updating its version, and pushing release tags to Git.
Why use it?
They help maintainers publish test and stable versions using the appropriate tags and version changes.

Instructions file

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/insforge/insforge-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/InsForge/insforge-mcp

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 insforge-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/insforge/insforge-mcp/claude-md.svg)](https://agentmods.dev/instructions/insforge/insforge-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/insforge/insforge-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/insforge/insforge-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,204 This file is loaded in full into every session.
When invoked 1,204 The same file — it is already loaded in full.
Security scan A 0 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 $0.01204 $0.01204
Opus 5 $0.00602 $0.00602
Sonnet 5 $0.00241 $0.00241
Haiku 4.5 $0.00120 $0.00120

Measured 3d ago against content hash 40025d3458b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

insforge-mcp CLAUDE.md 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 3d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

CLAUDE.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Insforge MCP Publishing Guide

Package Information

  • Package Name: @insforge/mcp
  • Current Version: Check package.json
  • Registry: npm (public)

🚨 IMPORTANT: Two Publishing Workflows

1. DEV Publishing (For Testing)

Use this for internal team testing WITHOUT affecting production users.

# 1. Build the package
npm run build

# 2. Publish to dev tag
npm publish --tag dev --access public

Result: Team can install with npm install -g @insforge/mcp@dev

2. PRODUCTION Publishing (Stable Release)

Use this when dev version is tested and ready for all users.

# 1. Build the package
npm run build

# 2. Bump version (choose one)
npm version patch  # 1.1.2 -> 1.1.3 (bug fixes)
npm version minor  # 1.1.2 -> 1.2.0 (new features)
npm version major  # 1.1.2 -> 2.0.0 (breaking changes)

# 3. Publish to latest tag (production)
npm publish --access public

# 4. Push version commit and tag to git
git push && git push --tags

Result: Everyone installs with npm install -g @insforge/mcp

Version Conventions

Dev Versions (Testing)

  • Use pre-release versions: 1.1.3-dev.1, 1.1.3-dev.2, etc.
  • Publish with --tag dev
  • Example workflow:
    npm version 1.1.3-dev.1
    npm publish --tag dev --access public
    

Production Versions (Stable)

  • Use semantic versioning: 1.2.3
  • Publish without tag (defaults to latest)
  • Always increment from the last production version, NOT from dev versions

npm Tag System

Think of tags like Git branches:

  • latest tag = Production (what users get by default)
  • dev tag = Development (opt-in testing)

They coexist in the same package!

@insforge/mcp
├── latest → 1.1.2 (production)
└── dev    → 1.1.3-dev.2 (testing)

Integration with Installer

The @insforge/install package has a --dev flag:

# Install production version
npx @insforge/install --client cursor --env API_KEY=key

# Install dev version
npx @insforge/install --client cursor --env API_KEY=key --dev

Read the full file on GitHub · 169 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. 3d ago First seen · 169 lines · 1,204 tokens per session scan A 40025d3458b8

Subscribe to this mod's changes

insforge-mcp CLAUDE.md is an instructions file published in the GitHub repository InsForge/insforge-mcp (35 stars, last pushed 15d ago), licensed Apache-2.0. It adds 1,204 tokens to every session, about $0.0060 per session on Opus 5. 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.