Agent
Analyzes task description and codebase context to recommend complexity depth level (quick/standard/thorough). Lightweight analysis run on every /forge command startup.
55 1mo ago A 35 tokens
original MIT
55Stars on the repository
39Mods indexed here, across every type
1mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Agent
Implements individual tasks from a frontier. Follows TDD when available, commits atomically, updates state. Dispatched during /forge execute.
55 1mo ago A 33 tokens
original MIT
Agent
Decomposes a specification into an ordered task frontier with dependency DAG, token estimates, and repo tags. Dispatched during /forge plan.
55 1mo ago A 32 tokens
original MIT
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.
55 1mo ago A 36 tokens
original MIT
Agent
Reviews code against spec requirements and quality standards. Returns PASS or ISSUES with file:line references and severity levels. Dispatched after task implementation.
55 1mo ago A 33 tokens
original MIT
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.
55 1mo ago A 67 tokens
original MIT
Agent
Writes specifications with R-numbered requirements and testable acceptance criteria from brainstorm output. Use during /forge brainstorm to generate spec files.
55 1mo ago A 31 tokens
original MIT
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.
55 1mo ago A 39 tokens
original MIT
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…
55 1mo ago A 81 tokens
original MIT