README
01Agent Claude Code
A directory guide for AI agent definitions used by Claude Code and Codex CLI. It lists the agents, their files, and their roles in a shared development workflow.
Agent Claude Code
A directory guide for AI agent definitions used by Claude Code and Codex CLI. It lists the agents, their files, and their roles in a shared development workflow.
Agent Claude Code
An AI agent that checks whether a software change meets the completion conditions written in test-cases.md. It runs each test case and judges PASS or FAIL from fresh execution results.
Agent Claude Code
An AI agent for improving code readability and efficiency without changing how the software behaves. It restricts changes to items such as duplicated code, names, unused code, types, and outdated comments.
Agent Claude Code
A technical documentation agent for writing documents such as READMEs, API references, and changelogs. It follows the project’s documentation locations, language rules, and existing documentation structure.
Agent Claude Code
A coding agent focused on exploring unfamiliar codebases and understanding how their parts fit together. It can inspect structure, dependencies, design patterns, technical debt, and integration possibilities.
Agent Claude Code
An implementation workflow for building code from an approved design document. It breaks the work into small units and records the review results and known problems.
Agent Claude Code
A short-lived implementation agent that completes one assigned coding task from a workflow coordinator. It follows test-driven development, or TDD, which means writing a failing test, making it pass, and then improving the code.
Agent Claude Code
An automated lint-fixing agent for a software project. A linter checks source code for style and potential problems; this agent first applies automatic fixes, then attempts guided fixes, and finally records explicit suppressions for unresolved issues.
Agent Claude Code
A coordinating agent that manages a multi-step software workflow. It moves work through defined phases, assigns tasks to other agents, checks completion requirements, and combines the final handoff.
Agent Claude Code
A project-planning agent that turns a software request into ordered tasks, file plans, agent assignments, and dependencies. A dependency is a task that must be completed before another task can begin.
Agent Claude Code
A review agent that checks completed work against the agreed acceptance conditions and prepares the handoff to the next person. Acceptance conditions are the specific checks a feature must pass.
Agent Claude Code
An agent that turns an initial request into an implementation-ready specification. It records required features, quality requirements, exclusions, edge cases, risks, and acceptance conditions.
Agent Claude Code
Agent "retrospective-analyst" from s977043/PlanGate, covering retrospective analyst — post-exec improvement agent, conductor との役割分担, 分析プロセス, step 1: 生データ収集 and step 2: パターン分析.
Agent Claude Code
An interactive setup guide that checks whether a project is configured correctly and records setup progress. It leaves actions owned by a person, such as changing settings, for the user to perform.
Agent Claude Code
A Japanese-language agent for designing repository-owned Codex or Claude Code skills. A skill is a reusable set of instructions that guides an coding agent through a specific kind of work.
Agent Claude Code
An agent that turns confirmed requirements into an implementation plan covering modules, data flow, state, failures, testing, dependencies, and trade-offs. Requirements are the agreed description of what a system must do.
Agent Claude Code
An agent that turns an unclear idea or request into a structured work package for a software team. It defines the goal, scope, acceptance criteria, decisions, risks, unknowns, and assumptions.
Agent Claude Code
Agent "workflow-conductor" from s977043/PlanGate, covering workflow conductor, iron law, 起動前提(router が capability preflight 済み / task-0072), common rationalizations and 8つの役割.