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.
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.
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.
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.
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.
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.
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.
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.
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 "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.
Turn review into an organizational judgment asset. Review Judgment as Code for AI-assisted development, delivered as a capability pack for Claude Code: your team's review criteria as versioned, repo-owned skills (a Skill Registry), driven by a review agent that runs perspective-based reviewer roles (code, security…
A pre-merge checklist command for a GitHub pull request. A pull request is a proposed code change, and the command checks whether it meets the project’s documented requirements before merging.
A command that plans the order for merging several pull requests (PRs), which are proposed code changes reviewed before entering a shared branch. It checks their status and file changes, then studies dependencies and overlap to reduce rebasing work.
A pre-work check for finding whether a coding task or pull request is already finished, obsolete, or being handled elsewhere. A pull request is a proposed change to a code repository.
A command that investigates whether a requested issue is already implemented before proposing it. It searches code, schemas, scripts, tests, history, pull requests, and existing issues, then classifies the result.
A release command for the River Review project that checks release instructions and pull-request state, updates an out-of-date branch, and verifies the release after merging.
A command for checking whether an agent’s reported branch, pull request, commit, or files actually exist. A pull request is a proposed code change submitted for review.