Claude Forge
oh-my-zsh for Claude Code — 16 agents, 35 commands, 33 skills, 22 hooks + 9 examples (21 events), 14 rules, 4 MCP (minimal: playwright, context7, jina-reader, [email protected]). Adversarial verification loop (maker≠checker), unattended API-error auto-resume, session relay, and Korean prose quality guardrails. One-line install: curl -fsSL https://raw.githubusercontent.com/…
- Type
- Plugin
- Repository
- sangrokjung/claude-forge
- GitHub stars
- 843
- License
- MIT
- Repo last updated
- Sep 3, 2026
- Source file
- .claude-plugin/plugin.json
- Version
- 4.3.0
- Author
- Sangrok Jung
What Claude Forge is
Claude Forge is a plugin published in the sangrokjung/claude-forge repository on GitHub, which has about 843 stars. The repository describes itself as: “oh-my-zsh for Claude Code — 16 agents, 35 commands, 32 skills, 21 safety hooks in one install. v4.0 adds an adversarial review loop: a second agent that never sees the first one's reasoning. MIT.”
A plugin is a package that bundles skills, slash commands, subagents, hooks, and MCP connectors so they install together. Plugins are plain files with a manifest at .claude-plugin/plugin.json, and they work in both Claude Code and Claude Cowork.
Installing Claude Forge adds everything it ships in one step. Connectors inside a plugin still need to be connected separately, and hooks and subagents only run in Cowork and Claude Code, not in regular chat.
How to install Claude Forge
Claude Code
- Add the repository as a plugin marketplace: claude plugin marketplace add sangrokjung/claude-forge
- Install the plugin: claude plugin install claude-forge@<marketplace-name>, using the marketplace name from the repository's .claude-plugin/marketplace.json.
- Restart the session if the new skills or commands don't appear straight away.
Claude Cowork
- Open Customize → Plugins and choose Add marketplace.
- Enter sangrokjung/claude-forge (the owner/repo shorthand works for GitHub).
- Find Claude Forge in the list, click Install, then connect any connectors it needs from its Connectors tab.
New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.
Inside the source file
An excerpt from .claude-plugin/plugin.json, shared under the repository's MIT license. Read the full file on GitHub.
⚡ New here? Walk through setup in 60 seconds →
English · 한국어 · 中文 · setup guide in 13 languages
oh-my-zsh for Claude Code — one install, full professional kit
What is it? • Why bother? • Install • What's inside • How to use • Architecture • FAQ • 한국어
> v4.3.0 (September 2026, latest) — session-time-report now reads Codex too. Same hook, same report; it detects whether a transcript is a Claude Code transcript or a Codex rollout log and counts either. Wiring for Codex is two entries you add to ~/.codex/hooks.json (how). > > v4.2.0 (September 2026) — Adds session-time-report (22nd hook): measures each session as it closes and tells you at your next start what time it ended, how long it actually ran, and how much you got through. Resume-aware, so a session you picked back up days later reports that sitting rather than a bogus 400-hour total. > > v4.1.0 (August 2026) — Adds harness-diet (33rd skill): measure your always-loaded context (CLAUDE.md + rules) and shrink it back under budget without losing governance. > > v4.0.0 (August 2026) — Introduces the adversarial verification loop: every behavioral change is checked by a second, independent agent that did not write the code and never sees the first agent's reasoning — maker≠checker until it issues APPROVE. Building v4.0 itself, the loop caught three real defects in the maintainer's own PRs (#58, #61); worked example: docs/VERIFICATION-LOOP.md. Also ships a reliability pack (API-error auto-resume, session relay across /compact, doom-loop guard — docs/RELIABILITY.md), a debugging escalation chain, task-grade routing, and Korean prose quality guardrails. Details: What's New in v4.0 · MIGRATION.md. > > If /plugin install claude-forge ever showed ✘ failed to load (Hook load failed: expected record, received undefined), that bug is fixed as of v4.0.0 — see #52, #57.
> v3.1.0 (June 2026) — Adds loop-forge (turn a repetitive task into a reusable, self-guarding slash command) and a full beginner-friendly rewrite of this README with diagrams. Built on v3.0.2 (LLM-readable install) and v3.0.1 (Anthropic 2026 standard alignment: Hooks 21+ events, Subagent frontmatter v2, Skills/Commands hybrid policy, 4-server MCP minimum). See MIGRATION.md.
What is Claude Forge?
Plain English version: Claude Code is an AI coding assistant that lives in your terminal. Out of the box it is capable but bare — like a new employee who knows how to code but has no company procedures, no safety checklists, no templates, and no specialist colleagues to call on.
Claude Forge is the equipment pack for that assistant. One install gives it:
- 16 specialist "colleagues" (agents) it can delegate to — planner, security reviewer, TDD guide, adversarial reviewer, and more
- 35 one-word shortcuts (commands like /plan, /tdd, /code-review) that trigger full workflows
- 33 saved procedures (skills) it follows automatically
- 22 safety checks (hooks) that run silently in the background every time it touches your code — including an unattended API-error auto-resume, a doom-loop guard, and an end-of-session time report
- 14 rule files that define how it should behave
- 4 external tool connections (browser automation, live docs search, and more)
> The oh-my-zsh analogy: oh-my-zsh is a free add-on that turns a plain terminal into a colorful, plugin-packed power tool — without changing what the terminal fundamentally does. Claude Forge does the same thing for Claude Code.
Before you install
- Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
- Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
- Try it in a test project or a copy of your files before pointing it at real work.
- Pin the version you tested, and review changes before updating.
- Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.
FAQ
What is Claude Forge?
Claude Forge is a plugin for Claude Code and Claude Cowork from the sangrokjung/claude-forge repository on GitHub. oh-my-zsh for Claude Code — 16 agents, 35 commands, 33 skills, 22 hooks + 9 examples (21 events), 14 rules, 4 MCP (minimal: playwright, context7, jina-reader, [email protected]). Adversarial verification loop (maker≠checker), unattended API-error auto-resume, session relay, and Korean prose quality guardrails. One-line install: curl -fsSL https://raw.githubusercontent.com/…
How do I install Claude Forge in Claude Code?
Add the repository as a plugin marketplace: claude plugin marketplace add sangrokjung/claude-forge Install the plugin: claude plugin install claude-forge@<marketplace-name>, using the marketplace name from the repository's .claude-plugin/marketplace.json. Restart the session if the new skills or commands don't appear straight away.
Can I use Claude Forge in Claude Cowork?
Open Customize → Plugins and choose Add marketplace. Enter sangrokjung/claude-forge (the owner/repo shorthand works for GitHub). Find Claude Forge in the list, click Install, then connect any connectors it needs from its Connectors tab.
Is Claude Forge safe to install?
It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.
Similar resources
- E2e Runner Use when creating, maintaining, or running E2E tests for critical user journeys (auth, payments, core features), or diagnosing memory leaks, console errors, and network waterfalls in flaky tests. Subagent · sangrokjung/claude-forge
- Database Reviewer Use when writing SQL queries, creating migrations, or troubleshooting database performance in Supabase/PostgreSQL projects. Reviews indexes, RLS policies, schema types, N+1 patterns. Read-only reviewer with EXPLAIN ANALYZE capability. Subagent · sangrokjung/claude-forge
- Business Growth Skills 20 business growth skills: conversion-rate optimization, pricing, referrals, revenue operations, and commercial strategy (deal desk, channel economics, partnerships) Plugin · borghei/Claude-Skills
- Terraform Provider Development Terraform provider development skills for Claude Code, including resources, data sources, actions, and acceptance testing. Plugin · hashicorp/agent-skills
- C Level Skills 7 flagship C-suite advisory skills: CEO, CTO, CFO, CISO, CMO advisors plus board meeting and board deck building. Plugin · borghei/Claude-Skills
- Terraform Module Generation Terraform module generation and refactoring skills for Claude Code, including module design and Terraform Stacks. Plugin · hashicorp/agent-skills
- Compliance Skills 9 flagship compliance skills: ISO 27001, SOC 2, GDPR, EU AI Act, NIS2, DORA, ISO 13485, MDR, FDA. Plugin · borghei/Claude-Skills
- Terraform Code Generation Terraform code generation skills for Claude Code, including HCL generation, style guides, and testing. Plugin · hashicorp/agent-skills