lucasduys/forge
9 subagents
Subagent
forge-complexityAnalyzes task description and codebase context to recommend complexity depth level (quick/standard/thorough). Lightweight analysis run on every /forge command startup.forge-executorImplements individual tasks from a frontier. Follows TDD when available, commits atomically, updates state. Dispatched during /forge execute.forge-plannerDecomposes a specification into an ordered task frontier with dependency DAG, token estimates, and repo tags. Dispatched during /forge plan.forge-researcherMulti-source research agent that investigates best practices, official documentation, and academic literature before implementation. Dispatched before complex tasks to ensure the executor has authoritforge-reviewerReviews code against spec requirements and quality standards. Returns PASS or ISSUES with file:line references and severity levels. Dispatched after task implementation.forge-speccerWrites specifications with R-numbered requirements and testable acceptance criteria from brainstorm output. Use during /forge brainstorm to generate spec files.forge-speccer-validatorPre-planning path-validation gate. Scans a spec file for path tokens inside code fences or backticks, checks each against the target repo, and returns REPLAN_NEEDED with (spec-line, missing-path) pairforge-verifierGoal-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.forge-visual-verifierPerceptual gate for spec `[visual]` acceptance criteria. Drives Playwright MCP (navigate + take_screenshot + evaluate), compares the resulting image against a saved baseline via an LLM-vision step, an