Plugin Claude Code
Autonomous spec-driven development loop for Claude Code.
Plugin Claude Code
Autonomous spec-driven development loop for Claude Code.
Plugin Claude Code
Autonomous spec-driven development loop for Claude Code with behavioral guardrails, knowledge graph integration, and design system support.
Instructions file CodexOpenCode
Instructions for LucasDuys/forge, covering forge — agent routing, agent definitions, forge-speccer, forge-planner and forge-executor.
Instructions file
Instructions for LucasDuys/forge, covering forge — autonomous agent coding system, what this is, project structure, workflow enforcement (critical) and architecture.
Agent
Analyzes task description and codebase context to recommend complexity depth level (quick/standard/thorough). Lightweight analysis run on every /forge command startup.
Agent
Implements individual tasks from a frontier. Follows TDD when available, commits atomically, updates state. Dispatched during /forge execute.
Agent
Decomposes a specification into an ordered task frontier with dependency DAG, token estimates, and repo tags. Dispatched during /forge plan.
Agent
Multi-source research agent that investigates best practices, official documentation, and academic literature before implementation. Dispatched before complex tasks to ensure the executor has authoritative guidance.
Agent
Reviews code against spec requirements and quality standards. Returns PASS or ISSUES with file:line references and severity levels. Dispatched after task implementation.
Agent
Pre-planning path-validation gate. Scans a spec file for path tokens inside code fences or backticks, checks each against the target repo, and returns REPLANNEEDED with (spec-line, missing-path) pairs when any are missing. Invoked automatically by /forge plan before forge-planner.
Agent
Writes specifications with R-numbered requirements and testable acceptance criteria from brainstorm output. Use during /forge brainstorm to generate spec files.
Agent
Goal-backward phase verification — checks that spec requirements are actually met, detects stubs and placeholders, verifies cross-component wiring. Dispatched after all tasks in a phase complete.
Agent
Perceptual gate for spec [visual] acceptance criteria. Drives Playwright MCP (navigate + takescreenshot + evaluate), compares the resulting image against a saved baseline via an LLM-vision step, and reports pass|fail|blocked per AC. Invoked after all task-level structural checks pass and before FORGECOMPLETE is…
Command
Trace a bug back to a spec gap and generate regression tests.
Command
Turn an idea into concrete specs with testable requirements.
Command
Opt-in multiplayer mode -- brain-dump together, claim tasks across machines, flag decisions async.
Command
Run the autonomous implementation loop.
Command
Display the following help text to the user.
Command
Decompose specs into task frontiers with dependency tracking.
Command
Continue Forge execution after context reset or interruption.
Command
Review an existing branch holistically before merging — blast radius, conventions, security, and spec compliance.
Command
Detect missing CLI tools and install them to enhance Forge capabilities.
Command
Audit every skill and command Forge can see — group by status (active, duplicate, deprecated, archived).
Command
Show Forge progress and status.