Skill Claude CodeCodex
A process for rewriting a reviewed plan into one self-contained final version before approval. It removes review-history notes and keeps only the currently agreed decisions.
2 yesterday A 92 tokens
original MIT
Skill Claude CodeCodex
A plan-review gate that checks whether a coding task has passed required self-review, external review, and human approval stages before execution begins.
2 yesterday A 62 tokens
original MIT
Skill Claude CodeCodex
A Japanese-language checklist for setting up and checking PlanGate, including steps that must be performed by a person.
2 yesterday A 98 tokens
original MIT
pr-decision
28Skill Claude CodeCodex
A decision-making recipe for deciding whether a code change is ready to become a pull request, based on evidence, review results, risks, checks, and a rollback plan. A pull request is a proposed change that others review before it is added to a codebase.
2 yesterday A 53 tokens
original MIT
Skill Claude CodeCodex
A repository scan that finds references to files or folders before they are deleted, moved, or renamed. A repository is the project’s stored source files and related documents.
2 yesterday A 160 tokens
original MIT
Skill Claude CodeCodex
A review that scans initial requirements for missing details, unclear points, hidden assumptions, exceptions, and items that should be excluded. Requirements are the agreed description of what a feature must do.
2 yesterday A 81 tokens
original MIT
review-gate
31Skill Claude CodeCodex
A structured review process for completed software changes, covering requirements, code correctness, common mistakes, security, and user experience.
2 yesterday A 116 tokens
original MIT
Skill Claude CodeCodex
A structured review of project constraints, unknowns, and technical risks. Each risk is given a severity and a way to reduce or handle it.
2 yesterday A 81 tokens
original MIT
Skill Claude CodeCodex
Design a new repo-owned skill from a concrete use case and produce a repo-ready skill package. Use when the user asks to create a new skill, define a skill's responsibility, draft SKILL.md, choose frontmatter, design supporting files, or prepare eval criteria for a new skill. Also trigger on "スキルを作りたい", "スキルを作って"…
2 yesterday A 103 tokens
original MIT
Skill Claude CodeCodex
A routing tool that takes a confirmed task type and operating mode, then returns the coding skills and required checks for that situation. Its rules distinguish which safeguards are required by the mode rather than by the task type.
2 yesterday A 93 tokens
original MIT
Skill Claude CodeCodex
A template for sending work to a subagent, meaning a separate coding agent working on an assigned task, and receiving a structured completion report.
2 yesterday A 177 tokens
original MIT
Skill Claude CodeCodex
A checklist-based setup guide for PlanGate, with checks for its required configuration and a doctor command as the source of truth.
2 yesterday A 58 tokens
original MIT
Skill Claude CodeCodex
A workflow for delegating planned coding tasks to separate subagents and checking each result in two reviews: one for matching the specification and one for code quality. A subagent is a separate agent assigned to a focused task.
2 yesterday A 114 tokens
original MIT
Skill Claude CodeCodex
A team-design skill for deciding when a software task needs multiple agents and assigning roles such as planning, implementation, review, security review, and test review.
2 yesterday A 152 tokens
original MIT
Skill Claude CodeCodex
A step-by-step debugging skill that gathers evidence, records symptoms, tests possible causes one at a time, and identifies the underlying cause before changes are made.
2 yesterday A 100 tokens
original MIT
Skill Claude CodeCodex
A skill for loading and updating the working context of a PlanGate task. Progressive disclosure means reading only the required level of task information, from a small summary to fuller details.
2 yesterday A 56 tokens
original MIT
plangate
41Plugin Claude Code
Plugin marketplace listing 1 plugin: plangate.
2 yesterday A
tokens not measured
original MIT
README
42Agent 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.
2 yesterday B 0 tokens
original MIT
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.
2 yesterday A 64 tokens
original MIT
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.
2 yesterday A 62 tokens
original MIT
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.
2 yesterday A 63 tokens
original MIT
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.
2 yesterday A 46 tokens
original MIT
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.
2 yesterday A 81 tokens
original MIT
implementer
48Agent 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.
2 yesterday A 66 tokens
original MIT