Search tools, AI agents, MCP servers
Submit a tool

Search iThub

Search tools, categories and collections. Type at least two characters.

Explore all tools
↑ ↓ to explore resultsEnter to open · Esc to close

Claude Forge

Claude Code bundle of agents, slash commands, skills, hooks and rules with an adversarial review loop

AI Skills & PluginsOpen sourcev4.1.0

Claude Forge at a glance

Pricing
Open source
License
Open source
Version
v4.1.0August 25, 2026
Language
Shell
Tool type
Plugin
Data location
Files live in the local clone and ~/.claude; hook logs stay in ~/.claude/work-log. Prompts go through the user's Claude Code setup, and optional MCP servers and some skills call third-party services.
Works with
claude code
Maker
sangrokjung
Founded
2026

What is Claude Forge?

Claude Forge is an MIT-licensed bundle of agents, slash commands, skills, hooks, rules and MCP server settings for Claude Code, Anthropic's terminal coding assistant. It is maintained by Sangrok Jung, credited in the README to QJC (Quantum Jump Club), and hosted at sangrokjung/claude-forge on GitHub. The project describes itself as oh-my-zsh for Claude Code: one installation adds a prepared set of specialist subagents, workflow commands and background checks to the ~/.claude directory that Claude Code reads. The repository was created in February 2026 and v1.0.0 was released on February 24, 2026.

On the main branch (last commit September 3, 2026) the repository contains 16 agent definitions, 35 command files, 33 skill folders, 22 hook scripts plus 9 opt-in .example hooks, 14 rule files and a default MCP configuration with four servers. These match the counts in the README and the plugin manifest. The GitHub repository description still cites 32 skills and 21 safety hooks, the totals from v4.0, and the onboarding site, an interactive setup walkthrough in 13 languages, shows the same earlier figures.

The release marked Latest on GitHub is v4.1.0 of August 25, 2026, which added the harness-diet skill for measuring and reducing always-loaded context. Version 4.0.0 of August 19, 2026 introduced the adversarial verification loop, in which a second agent that did not write a change and never sees the first agent's reasoning has to approve it, together with a reliability pack, a debugging escalation chain, task-grade routing and Korean prose guardrails. The README and plugin.json on main declare version 4.3.0: 4.2.0 added a session-time-report hook and 4.3.0 lets it read Codex rollout logs, but neither version has a Git tag or a GitHub release. Upgrade notes are in MIGRATION.md.

There are two installation paths. The Claude Code plugin marketplace route adds the commands and part of the skills. The full install runs install.sh on macOS, Linux and WSL or install.ps1 on Windows; it links or copies the bundle's folders into ~/.claude and replaces the user's ~/.claude/settings.json with the project's own file, so it changes the existing Claude Code configuration, including permissions and hooks. According to INSTALL.md there is no uninstall command yet. The full install requires Claude Code 2.1.110 or later plus node, jq and git.

Claude Forge is a set of Markdown, JSON and shell files rather than a separate application or service; model usage goes through the user's own Claude Code setup. Several agents and skills target specific stacks, such as TypeScript builds, PostgreSQL and Supabase reviews and Playwright tests, and three skills deal with Korean text. The README states that the v4.0 reliability hooks were built and verified on macOS only. Other Claude Code extensions on iThub include Superpowers, Waza and Ponytail.

Key capabilities

  • Sixteen agent definitions The agents/ folder holds planner, architect, code-reviewer, security-reviewer, tdd-guide and database-reviewer, which the README assigns to the most capable model, plus build-error-resolver, e2e-runner, refactor-cleaner, doc-updater and verify-agent on a faster model. Version 4.0 added adversarial-reviewer, skeptical-auditor, systematic-debugger, rca-debugger and escalation-fixer. The frontmatter follows a v2 schema documented in reference/agent-schema.json.
  • Adversarial verification loop The adversarial-reviewer agent runs in a fresh context with read-only tools (Read, Grep, Glob, Bash) and returns exactly one verdict: APPROVE, REQUEST_CHANGES or UNVERIFIED. The bundled rule treats a behavioural change as done only after APPROVE for the current revision; any later edit voids it, and changes touching authentication, payments, secrets or destructive data need two separate checker lanes. A worked example is in VERIFICATION-LOOP.md.
  • Thirty-five slash commands Commands cover the core workflow (/plan, /tdd, /code-review, /handoff-verify, /commit-push-pr, /auto), exploration, testing, documentation sync, project setup, Git worktrees and maintenance such as /forge-update and /show-setup. /guide starts an interactive tour for first-time users.
  • Thirty-three skills Skills include review-loop, loop-forge for turning a repetitive task into a guarded slash command, harness-diet, relay for handing a session across /compact, security-pipeline, team-orchestrator and session-wrap. Eight former commands moved to skills/ in v3.0, and install.sh --upgrade creates compatibility links for them, which the README says are kept until April 1, 2027.
  • Security hooks output-secret-filter.sh checks tool output for API keys, tokens and passwords, remote-command-guard.sh blocks curl and wget pipes, and db-guard.sh targets DROP, TRUNCATE and DELETE without WHERE. security-auto-trigger.sh reacts to file edits and rate-limiter.sh limits MCP calls; the README figure shows these, with a cost guard for expensive MCP calls, as six security layers.
  • Reliability hooks Added in v4.0, api-error-auto-resume.sh schedules an unattended resume after a retryable API error, loop-detection.sh reacts to repeated edits of the same file and auto-verify-fix.sh runs a quick check after edits to TypeScript, JavaScript or Python files. A snapshot and restore pair carries the relay pointer across context compaction. The wiring is described in RELIABILITY.md.
  • End-of-session time report On main, session-time-report.sh records each session at SessionEnd and prints the end time, duration and prompt, tool and file-change counts at the next SessionStart. It reads only the transcript with python3, appends to ~/.claude/work-log/session-times.jsonl with mode 600, can be turned off with FORGE_SESSION_TIME_REPORT=0, and also parses Codex rollout logs, although Codex wiring is added by hand.
  • Utility hooks and opt-in examples Further hooks suggest documentation sync and session wrap-up, check for a newer Claude Forge release at session start, remind about code quality after edits, warn about costly MCP calls and log work to ~/.claude/work-log. Nine .example files cover events such as SubagentStart, TaskCreated and WorktreeCreate and are activated by renaming them and registering them in settings.
  • Fourteen rule files The rules/ folder defines coding style, security, testing, Git workflow, verification, adversarial review, task-grade routing, API error recovery and Korean writing quality, among others. Rules are read at the start of every session, and the harness-diet skill measures how much always-loaded context they and CLAUDE.md occupy.
  • Default MCP servers mcp-servers.json lists Playwright, Context7, Jina Reader and Chrome DevTools, each started through npx with a pinned version such as chrome-devtools-mcp@0.23.0. Memory, Exa, GitHub, fetch and other servers moved to mcp-servers.optional.json in v3.0.
  • Bundled settings.json The shipped settings allow tools such as Bash(*), Read(*), Write(*) and Edit(*), and list 56 deny patterns, among them WebFetch, recursive deletes, sudo, force pushes to main or master and piped remote scripts. They also enable the experimental agent teams variable, set a status line command and register the hooks. A settings.local.json template holds personal overrides.
  • Status line The installer initializes the cc-chips Git submodule and copies a custom engine.sh and theme files over it. The status line shows model detection, the session ID and cache statistics.
  • Full install on macOS, Linux and WSL install.sh checks for node, jq and git, offers to move an existing ~/.claude to ~/.claude.backup.<timestamp>, then replaces ten folders such as agents, hooks and skills plus settings.json in ~/.claude with symlinks to the clone. It writes .forge-meta.json and appends the aliases cc and ccr to ~/.zshrc or ~/.bashrc. --dry-run previews the changes and --upgrade keeps the existing directory.
  • Windows install install.ps1 must run in PowerShell as Administrator and copies the files, including settings.json, instead of linking them. Updates on Windows therefore require running the script again after git pull.
  • Plugin marketplace install /plugin marketplace add sangrokjung/claude-forge followed by /plugin install claude-forge adds the commands and most skills without agents, hooks, rules or MCP servers, as listed in PLUGIN-VS-INSTALL-SH.md. Version 4.0.0 fixed a hook load error that had made the plugin fail to load.
  • Optional extras in the installer After linking, install.sh asks before installing MCP servers, before adding external skills (Superpowers, Humanizer, UI/UX Pro Max and Find Skills through npx skills add -g) and before installing the Work Tracker, which logs Claude Code usage locally.
  • Updates and removal Symlinked installs update with git pull, and /forge-update pulls the latest version. INSTALL.md states that there is no --uninstall flag: the links in ~/.claude are removed by hand, and the backup folder exists only after a fresh interactive install, not after --upgrade or a piped curl | bash run. An uninstall script is proposed in an open pull request.

Where Claude Forge fits

Feature work from plan to pull request

The README's main pipeline is /plan, /tdd, /code-review, /handoff-verify and /commit-push-pr. The plan step waits for approval before code is written, the TDD step writes failing tests first, the verify step runs build, tests and lint in a fresh session, and the last step commits, pushes and opens a pull request. /auto runs the same chain from a short description, for example /auto login page.

Independent review of behavioural changes

The review-loop skill dispatches adversarial-reviewer against the goal, the diff and the execution evidence. REQUEST_CHANGES leads to fixes and a new reviewer instance rather than the same one, UNVERIFIED is retried with another checker, and only APPROVE for the current revision ends the loop. skeptical-auditor separately re-runs steps that another agent reported as passing and compares the real exit codes.

Bug fixing and debugging escalation

For bugs the README lists /explore, /tdd, /verify-loop, /quick-commit and /sync, where /verify-loop retries build, lint and tests up to three times with automatic fixes. Harder failures move from systematic-debugger to rca-debugger and then to escalation-fixer, each step taking over only when the previous one could not close the case.

Security reviews

The documented security sequence is /security-review, which applies CWE Top 25 and STRIDE threat modelling, followed by the stride-analysis-patterns and security-compliance skills for SOC 2, ISO 27001, GDPR and HIPAA checks. In the background, the security hooks filter secrets from output and block piped remote scripts and destructive SQL during the session.

Parallel agent teams

/orchestrate and the team-orchestrator skill split work across Claude Code agent teams in a hub-and-spoke layout with file ownership and phases, using the experimental agent teams setting enabled in the bundled settings.json. /worktree-start and /worktree-cleanup create and remove Git worktrees for parallel branches, and /commit-push-pr closes the work.

Long and unattended sessions

The reliability pack targets sessions that run for hours: the relay skill writes a baton file before /compact and the hooks restore it afterwards, the auto-resume hook restarts a session after a retryable API error under fixed limits, and the loop detector nudges a rethink after repeated edits of one file. The session time report then summarises duration and activity at the next start. Recurring chores can be turned into reusable commands with loop-forge and skill-factory.

Install

git clone --recurse-submodules https://github.com/sangrokjung/claude-forge.git && cd claude-forge && ./install.sh

Reviews of Claude Forge

No reviews yet

Be the first to share your experience with Claude Forge.

Loading review form…

Found Claude Forge useful? Upvote it todayYour vote helps other IT teams find it in the daily ranking.

Similar to Claude Forge

Compare:Claude Forge vs SuperpowersClaude Forge vs WazaClaude Forge vs Ponytail

  1. SuperpowersComposable skills that guide coding agents through design, planning, testing, and code review.AI Skills & Plugins4 views
  2. WWazaEight engineering skills for Claude Code, Codex and CursorAI Skills & Plugins3 views
  3. PonytailRuleset and plugin that makes AI coding agents reuse code and write the smallest complete changeAI Skills & Plugins3 views
  4. AI Job SearchA Claude Code workflow for evaluating jobs, tailoring CVs and preparing interviewsAI Skills & Plugins24 views
  5. agent-browserBrowser automation skills and a native CLI for AI agents.AI Skills & Plugins18 views
  6. Ffacebook-skillsAI agent skills for drafting, reviewing and planning Facebook Page content with approval before publishing.AI Skills & Plugins4 views
  7. CBClaude BlogClaude Blog researches, drafts and reviews blog posts inside Claude Code.AI Skills & Plugins3 views
  8. EECCECC adds reusable skills, specialized agents, memory, and verification workflows to AI coding tools.AI Skills & Plugins33 views