Claude Forge
A Claude Code toolkit that prewires specialist workflows, slash commands, and safety hooks.
- Source repo
- sangrokjung/claude-forge
- Stars
- ★ 839
- Last updated
- 20d ago
- License
- MIT
- Primary language
- Shell
- FA score
- 48/100 · Major gaps
At a glance
- Works with
- Platform-specificClaude Code
- You'll need
- Typical use
- A team building a feature in Claude Code that wants an approved implementation plan from /plan before starting test-first work with /tdd.
- Main limitation
- Its core operation depends on Claude Code; no standalone adapter for ChatGPT, Codex, the OpenAI API, or the Claude API is documented.
- Source review
- 48/100 · Major gaps
What does this agent do, and when should you use it?
Claude Forge is a development-environment extension for Claude Code, delivered through either a plugin install or a fuller local installation. The full install provides 11 specialist agents, 34 slash commands, 26 skills, 15 built-in hooks, 10 rule files, and four default MCP connections. Its installer links repository configuration into ~/.claude/ on macOS and Linux so Claude Code can load the definitions, commands, rules, and hooks; Windows uses copied files instead. The documented primary workflow is /plan → /tdd → /code-review → /handoff-verify → /commit-push-pr. It fits Claude Code users who want a standardized plan-to-verification workflow, rather than teams seeking a standalone, provider-neutral agent API.
The installer connects agents/, commands/, skills/, rules/, hooks/, and MCP configuration to Claude Code. /plan creates an implementation plan and waits for approval; /tdd follows a failing-test, passing-test, refactor cycle; /code-review performs quality and security checks; and /handoff-verify runs build, test, and lint verification. Its agent definitions include planner, architect, security-reviewer, tdd-guide, database-reviewer, e2e-runner, and verify-agent. Built-in hooks run around Bash commands, database commands, file edits, and MCP use, including remote-command-guard.sh, db-guard.sh, and output-secret-filter.sh. The default MCP servers are playwright, context7, jina-reader, and chrome-devtools.
- A team building a feature in Claude Code that wants an approved implementation plan from /plan before starting test-first work with /tdd.
- A TypeScript maintainer who needs /build-fix or build-error-resolver to address build errors with minimal surrounding changes.
- An engineer preparing a release who wants /security-review and security-reviewer to check OWASP Top 10 issues, injection risks, and leaked secrets.
- A web developer who needs /e2e and e2e-runner to generate and run Playwright end-to-end tests.
- A team that wants a separate verification step to run build, tests, and lint through /handoff-verify before handoff.
- A Claude Code user repeating the same operation who wants /loop-forge to turn it into a reusable slash command with automatic verification and a hardstop.
How do you install or deploy this agent?
Prerequisite: Claude Code; the README badges Claude Code >=2.1.110. For the quick, partial plugin installation, run these inside a Claude Code session:
/plugin marketplace add sangrokjung/claude-forge
/plugin install claude-forgeThis provides commands and most skills; agents, hooks, rules, and MCP connections require the full install. On macOS/Linux, run:
curl -fsSL https://raw.githubusercontent.com/sangrokjung/claude-forge/main/install.sh | bashAlternatively, run git clone --recurse-submodules https://github.com/sangrokjung/claude-forge.git, enter the directory, and run ./install.sh. On Windows, run .\install.ps1 in PowerShell as Administrator. The supplied material does not document additional credentials.
How do you use this agent?
After a full install, start with /guide for an interactive tour. For a feature workflow, run /plan → /tdd → /code-review → /handoff-verify → /commit-push-pr; /auto login page is a documented example of starting an automated plan-to-PR flow. On macOS/Linux, run git pull in the claude-forge repository to update linked configuration; on Windows, rerun install.ps1 after pulling. To override settings without editing tracked files, copy setup/settings.local.template.json to ~/.claude/settings.local.json and edit it.
What are this agent's strengths and limitations?
- The full install bundles agents, commands, skills, rules, hooks, and four MCP connections as one prewired configuration rather than a single workflow.
- It documents a connected workflow spanning planning, test-first development, review, fresh-context verification, and commit/PR creation.
- Its hooks target unsafe remote pipelines, destructive SQL, secret leakage in output, and MCP usage, with additional opt-in lifecycle examples.
- macOS/Linux symlinks into ~/.claude/, allowing repository updates to take effect after git pull without reinstalling.
- Its core operation depends on Claude Code; no standalone adapter for ChatGPT, Codex, the OpenAI API, or the Claude API is documented.
- Plugin installation is intentionally incomplete: agents, hooks, rules, and MCP connections require the full installer.
- The default tool set includes Playwright, Context7, Jina Reader, and Chrome DevTools, so using those integrations requires network access and an MCP-capable environment.
- Windows uses file copies instead of symlinks, requiring install.ps1 to be rerun after each git pull.
How does this agent compare with similar options?
Against a basic .claude/ setup, Claude Forge supplies preconfigured specialist agents, commands, skills, hooks, and MCP connections. Against installing individual plugins, it positions /plan, /tdd, /code-review, /handoff-verify, and /commit-push-pr as a connected workflow.
Key facts side by side with the most closely related agents.
| Agent | Source review | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|
| Claude Forge This agent | 48 · Major gaps | ★ 839 | 20d ago | Shell | Claude Code |
| Claude Code Slash Commands | 36 · Major gaps | ★ 2.6k | 11mo ago | — | Claude Code |
| OrchestKit AI Development Toolkit | 86 · Good | ★ 278 | 3d ago | TypeScript | Claude Code |
| Agent Skills — Production-Grade Engineering Skills for AI Agents | 71 · Some gaps | ★ 99k | 1d ago | JavaScript | Codex · Claude Code · OpenAI API |
How does FollowAgents rate this agent?
Why each dimension lost points
Evidence shows security hooks (e.g., output secret filter, remote command guard, DB guard) and user confirmation mechanisms (e.g., confirmation for dangerous operations), but no implementation details or test results are provided. Dependency security: CI includes secret scanning and ShellCheck, but no dependency vulnerability scanning. External effects: install script creates symlinks and modifies shell config, but risks are not clearly flagged. Rollback: --upgrade backup exists, but no full rollback mechanism. Source attribution: MIT license and contributor list present, but publisher unverified. Hence low scores.
Self-consistency: README claims component counts roughly match directory structure, but inconsistencies exist (e.g., README says 34 commands, directory tree shows 34; skill count in v3.1.0 increased from 24 to 25, but README lists 26). Dependency availability: dependencies Node.js, jq, git are listed, but no version requirements or installation instructions. Failure messages: install script has --help and --dry-run, but no detailed error handling documentation.
Audience and scenarios: README targets non-developers and developers, provides multiple workflows (new feature, bug fix, security audit, team collaboration). Capability boundaries: clearly distinguishes Method A and B feature differences, and notes some features unavailable. Trigger precision: commands and skills have clear descriptions, but no detailed trigger conditions. Environment fit: supports macOS/Linux and Windows (WSL/PowerShell), but no detailed system requirements.
Information architecture: clear directory structure with README, docs, reference. Install notes: multiple installation methods including one-liner and plugin. Naming stability: command and skill names consistent, but no naming conventions. Examples and FAQ: workflow examples and FAQ provided. Known limitations: Method A limitations stated, but others not mentioned. License: MIT license clear. Versioning and changelog: MIGRATION.md and version update notes present. Maintenance responsibility: CONTRIBUTING.md and SECURITY.md present, but maintainers not clearly identified.
Output usability: commands and skills have clear output descriptions, but no actual output examples. Marginal value: rich feature set, but no comparison with other tools. Cost-benefit: easy installation, but no performance or resource consumption data.
Claim traceability: README claims lack specific evidence (e.g., test results). Cross-source corroboration: CI workflows provide some validation, but not independent verification. Fact-inference separation: README mixes facts and inferences without clear distinction.
- Publisher identity unverified; install script modifies user environment (creates symlinks, modifies shell config), review in isolated environment before running.
- README claims component counts inconsistent with directory structure (e.g., skill count), dependency versions not specified, may affect compatibility.
- Security hooks' actual effectiveness not independently tested, dependency security not vulnerability-scanned, review yourself.