v4.0.0 (August 2026) — Leads with the adversarial verification loop: every behavioral change is checked by a fresh, independent reviewer (
adversarial-reviewer) that did not write the code and does not see the maker's reasoning — maker≠checker until the checker issuesAPPROVE. This is not theoretical: building v4.0 itself, the loop caught three real defects in the maintainer's own PRs (#58, #61) — a CI parity guard that passed on its own regression, the same guard's fix carrying an identical hole one level down, and a dependency ceiling that silently pinned a year-old release. Full worked example with the actual envelopes:docs/VERIFICATION-LOOP.md. Also ships a reliability pack (unattended API-error auto-resume, session relay across/compact, doom-loop + edit-time verify hooks, an opt-in pre-commit secret guard, and the sharedlibs/hook-guard.shthey build on — wiring guide:docs/RELIABILITY.md), a debugging escalation chain (systematic-debugger→rca-debugger→escalation-fixer), task-grade routing (/workflow-classifysizes work S/M/L/XL and routes documentation + verification depth accordingly), and Korean prose quality guardrails (translation-ese/AI-idiom avoidance at generation time, not just cleanup). 16 agents, 35 commands, 32 skills, 21 hooks, 14 rules. See MIGRATION.md.v3.1.1 (hotfix, August 2026) — Fixes plugin install failing to load entirely (
Hook load failed: expected record, received undefined). If/plugin install claude-forgeshowed✘ failed to loadand none of the skills, agents or commands appeared, upgrade to 3.1.1. Also restores Windowsinstall.ps1parity (statusLine andscripts/were never copied). See #52, #57, #50.
v3.1.0 released (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 - 32 saved procedures (skills) it follows automatically
- 21 safety checks (hooks) that run silently in the background every time it touches your code — including an unattended API-error auto-resume and a doom-loop guard
- 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.
✨ Why bother?
| Without Claude Forge | With Claude Forge |
|---|---|
| Claude Code writes code, but you have to remind it about tests, security, and docs every time | Automated pipeline: plan → test → review → verify → ship, all connected |
| No safety net — Claude can run dangerous commands or leak secrets by accident | 6-layer hook system blocks risky actions before they happen |
| One AI doing everything alone | 16 specialist agents working in parallel (planner, architect, security reviewer, adversarial reviewer…) |
| Hours assembling your own config | 5-minute install, everything pre-wired |
| Updates require manual copy-paste | git pull — done |
📥 Install in Minutes
Option A — Claude Code Plugin (quick start, partial features)
Open a Claude Code session and run two commands:
/plugin marketplace add sangrokjung/claude-forge
/plugin install claude-forge
This gets you commands and most skills right away. Agents, hooks, rules, and MCP connections need Option B.
Update later: /plugin update claude-forge
Option B — Full Install (recommended, everything included)
One line in your terminal:
curl -fsSL https://raw.githubusercontent.com/sangrokjung/claude-forge/main/install.sh | bash
Or if you prefer to clone first:
git clone --recurse-submodules https://github.com/sangrokjung/claude-forge.git
cd claude-forge
./install.sh # fresh install
# or
./install.sh --upgrade # safe migration from v2.1
Windows users: Run .\install.ps1 in PowerShell as Administrator.
Which option should I pick?
| What you get | Option A (/plugin install) |
Option B (./install.sh) |
|---|---|---|
| Commands (35 shortcuts) | ✅ | ✅ |
| Skills (32 saved procedures) | ⚠️ partial | ✅ |
| Agents (16 specialists) | ❌ | ✅ |
| Hooks (21 safety checks) | ❌ | ✅ |
| Rules (14 behavior guidelines) | ❌ | ✅ |
| MCP connections (4 tools) | ❌ | ✅ |
Recommendation: Use Option B unless you only need a taste of commands and skills.
If Claude Forge helps you, a star on GitHub helps others find it.
📦 What's Inside
Here is everything bundled in Claude Forge, explained in plain language:
| What | Count | Plain English |
|---|---|---|
| Agents (specialist colleagues) | 16 | Each one is an AI focused on a single job — planner, architect, security checker, test guide, database expert, adversarial reviewer, and more. Claude calls the right one automatically. |
| Commands (shortcut buttons) | 35 | Type /plan and Claude creates a full implementation plan. Type /tdd and it writes tests first, then code. All 35 are pre-built shortcuts for common developer tasks. |
| Skills (saved procedures) | 32 | Step-by-step playbooks Claude follows automatically — like a recipe it has memorized. loop-forge turns any repetitive task into a reusable slash command in seconds; review-loop runs the maker≠checker verification cycle. |
| Hooks (silent safety checks) | 21 built-in + 9 opt-in examples | These run before and after every action Claude takes. They block leaked passwords, dangerous database commands, and unsafe remote scripts — and, new in v4.0, they auto-resume a session after a retryable API error and nudge you when you're stuck editing the same file. Covers 21 lifecycle events. |
| Rules (behavior guidelines) | 14 | Written instructions Claude reads at the start of every session — coding style, security principles, git workflow conventions, when the verification loop is mandatory, and more. |
| MCP connections (external tools) | 4 | Browser automation (Playwright), live library docs (context7), web page reader (jina-reader), and Chrome DevTools for performance audits. |
Deep Analysis Agents (use the most capable model)
| Agent | What it does |
|---|---|
| planner | Creates detailed implementation plans for complex features. Waits for your sign-off be |