agent_stack
01Agent
Three jobs, three decisions. Do not merge them.
Agent
Three jobs, three decisions. Do not merge them.
Agent
This document describes the user interface flows, state transitions, and data interactions for [Project Name], ensuring seamless navigation and consistency.
Agent
This document provides design and coding standards for the client of [Project Name], ensuring consistent UI/UX and maintainable code.
Agent
This document defines mandatory coding standards for [Project Name]. It adapts two foundational frameworks into actionable, language-agnostic rules that all source code, scripts, and tests must follow.
Agent
This document defines documentation practices for [Project Name], ensuring maintainability, onboarding speed, and reliable agent comprehension. Documentation is a living artifact and must evolve with code.
Agent
This template enforces process artifacts — task memories (docs/memories/), docs/code/ mirrors for every code file, and recorded reasoning — through a single script, scripts/check-task-compliance.sh. The script is the one source of truth for "is this change compliant?"; everything else is just a trigger that runs it.
Agent
Work runs on two pipelined tracks, both already embodied by this template's artifacts.
Agent
This document outlines the file organization for [Project Name], ensuring modularity and maintainability across source, scripts, tests, and docs.
Agent
This document provides a sprint-based roadmap for [Project Name], breaking development into actionable steps using Agile/Scrum.
Agent
ODW does not embed models. Each agent() call names an executor string; the host supplies RunOptions.executors: Record . An Executor is (ExecOptions) => Promise — typically spawn a coding-agent CLI, feed the prompt (stdin or argv), parse stdout/JSONL, return final text / structured output.
Agent
This document outlines the high-level requirements, objectives, and scope for [Project Name], serving as the foundation for all development. It defines user needs, core features, and boundaries to guide sprints and agents.
Agent
This document defines the server architecture, data models, and rules for [Project Name], ensuring scalable and secure data management.
Agent
This document lists the technologies, packages, dependencies, APIs, and tools for [Project Name], with purposes and documentation links to guide implementation.
Agent
(while the marker exists the gate is dormant — the pristine template).
Agent
This document defines testing strategy and test-quality standards for [Project Name]. Tests are the executable safety net for refactoring, deployment confidence, and regression prevention.
Agent
Lockfiles (requirements.txt, requirements-dev.txt, requirements-notebooks.txt) are compiled from the .in sources with hashes. Never edit a .txt directly; bump the .in and re-compile.