Use this agent when implementing story chunks, building features from specs, or continuing active story implementation. Owns the implement → validate → refine loop for each chunk. Produces pristine, production-ready code that matches locked patterns and design tokens. Context: Orchestrator is implementing a story and…
Use this agent for autonomous story planning — deep codebase research + detailed chunk breakdown in one focused pass. Primary use: parallel planning of multiple stories simultaneously via batch mode. Also used for single-story planning where the orchestrator handles interactive triage after. The orchestrator MUST…
🌌 PARA Workspace is an open-source workspace framework that defines how humans and AI agents organize knowledge and collaborate on projects. It ships as a repo containing a kernel (constitution), CLI tools, and templates — which generates workspaces where you actually work.
🌌 PARA Workspace is an open-source workspace framework that defines how humans and AI agents organize knowledge and collaborate on projects. It ships as a repo containing a kernel (constitution), CLI tools, and templates — which generates workspaces where you actually work.
Pre-execution briefing session that collects case context through multi-agent panel consultation, builds a structured execution plan, and persists state for cross-session recovery.
Coordinates multi-agent legal workflows including due diligence pipelines, litigation preparation, contract lifecycle management, and parallel agent execution with data passing.
Transforms vague legal queries into structured prompts through Socratic dialogue, recommends optimal workflows, and guides system navigation with persistent cross-session learning.
Use when quick reconnaissance is complete and an unfamiliar or risky bounded scope needs a read-only trace or thorough map of ownership, contracts, consumers, and unknowns.
Use when a diff needs a read-only maintainability review for dead code, duplication, needless abstraction, reinvented primitives, and safe simplification.
Polishes .beads/beads.jsonl in isolated context. Runs the full polish loop (self-containment, dependencies, test obligations, coverage vs plan, duplicates, Forge invariants) and returns a focused report. Use when you want to burn a polish round without filling the main conversation.
Reviews Forge TypeScript changes for correctness, security, sandbox/permission coverage, state-machine integrity, and test adequacy. Invoke for any non-trivial diff before merge.
A scored comparison of AI agents and the language models connected to them, based on the agents' self-assessments. It rates skills from 1 to 10 across areas such as PHP, Symfony, testing, Git, Docker, and web development.
An index of documentation about working with AI coding agents, including their profiles, capabilities, and operating rules. It includes materials for Codex and Codex CLI in English and Russian.
A process for measuring and reviewing how AI coding agents are used in a project. It uses Git history and GitHub pull requests to track changes by week, then aggregates results in Google Sheets.