forge

    ███████╗ ██████╗ ██████╗  ██████╗ ███████╗
    ██╔════╝██╔═══██╗██╔══██╗██╔════╝ ██╔════╝
  █████╗  ██║   ██║██████╔╝██║  ███╗█████╗
  ██╔══╝  ██║   ██║██╔══██╗██║   ██║██╔══╝
    ██║     ╚██████╔╝██║  ██║╚██████╔╝███████╗
    ╚═╝      ╚═════╝ ╚═╝  ╚═╝ ╚═════╝ ╚══════╝

What Forge Does

Forge treats software construction as a series of earned progressions. Each phase produces demonstrable evidence before the next phase unlocks. The agent cannot skip steps, cut corners, or claim completion without proof.

Rules are suggestions. Gates are enforcement. You can write "always test first" in CLAUDE.md, and the agent will agree, then skip it when it feels confident. Forge enforces at two levels: hooks intercept tool use at runtime (phase-gate blocks code edits during pre-execution phases; commit-guardian requires passing test evidence before commits), and skills provide deeply specified workflow instructions with hard gates, anti-patterns, and evidence requirements that resist rationalization under pressure. Hooks are walls. Skills are the operating manual that makes those walls effective.

Workflow

stateDiagram-v2
    direction LR

    [*] --> Discovery
    Discovery --> Design : direction approved
    Design --> Planning : spec approved
    Planning --> Execution : plan approved
    Execution --> Verification : all tasks complete
    Verification --> Integration : evidence collected
    Integration --> [*] : code landed

    state Execution {
        direction TB
        [*] --> ProveFail: write test
        ProveFail --> Implement: RED confirmed
        Implement --> ProvePass: run test
        ProvePass --> Review: GREEN confirmed
        Review --> [*]: approved
        Review --> ProveFail: issues found
    }

    state Verification {
        direction TB
        [*] --> Tests
        Tests --> Build
        Build --> Security
        Security --> SpecAudit
        SpecAudit --> [*]: all pass
    }

Each transition requires evidence. No phase advances on assertions alone.

Skill Selection

Forge uses a three-tier routing system instead of blanket invocation rules.

Tier 1 -- Unconditional. These apply to all implementation and debugging work. No exceptions.

Tier 2 -- Intent-matched. Activate when their description matches the task.

discover-intent | shape-design | chart-tasks | drive-execution | inspect-work | land-changes | distill-lessons | receive-feedback

Tier 3 -- User-invoked. Available via slash invocation, never auto-triggered. All carry disable-model-invocation: true.

Install

# Add the marketplace and install
claude plugins marketplace add caseyrtalbot/forge
claude plugins install forge@forge

Or from a local clone:

git clone https://github.com/caseyrtalbot/forge.git
claude plugins marketplace add ./forge
claude plugins install forge@forge

Restart Claude Code after installing to load skills, agents, and hooks.

Requirements: Claude Code v1.0.33+, Node.js 18+, Git

Quick Start

/forge:start "Add user authentication"   # Begin a workflow
/forge:status                             # Check current phase
/forge:advance                            # Advance when gates pass
/forge:audit                              # Run full quality audit