Menu
Internal planner persona behavior guide referenced by persona hooks and direct skill invocation.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Auto-activate CCS CLI delegation for deterministic tasks. Parses user input, auto-selects optimal profile (glm/kimi/custom) from ~/.ccs/config.json, enhances prompts with context, executes via `ccs {profile} -p "task"` or `ccs {profile}:continue`, and reports results. Triggers on "use ccs [task]" patterns, typo/test/refactor keywords. Excludes complex architecture, security-critical code, performance optimization, breaking changes.
Internal project-context placement and consistency reference used by context refactoring and verification workflows.
This skill should be used when the user asks to "audit project standards", "check standards compliance", "devkit audit", "find standards violations", "are we following devkit standards", "what's not following standards", "compliance report", "規約チェック", "スタンダード監査", or "規約違反を探して". It actively scans code and reports violations. Do NOT use for project scaffolding (use init-project), single-CLI-tool checks (use cli-compliance), or looking up what the standards are (use standards).
This skill should be used when the user asks to "set up a project", "choose a tech stack", "establish coding standards", "configure linting", "set up tests", "pick a framework", "review code quality", "set up logging", "configure observability", "choose an ORM", "set up auth", "set up Storybook", "write stories", "visual testing", "CSF", "coverage threshold", or discusses any technology choices for a TypeScript project. Also use when starting a new project, setting up CI/CD, choosing between tools (oxlint vs ESLint, pnpm vs npm), configuring environment variables, or when any other devkit skill needs to reference project conventions. This is the central reference for all devkit technology decisions and coding principles.
Review whether the current code satisfies a GitHub issue, then update the issue status to match. Use when the user asks to 'review an issue', 'check if an issue is done', 'is this issue resolved', 'update issue status', 'issueの対応状況を確認', 'issueが完了しているかレビュー', or 'issueのステータスを更新'.
This skill should be used when the user asks to 'create a skill', 'add a new skill', 'make a skill', 'scaffold a skill', 'new skill', 'スキル化して', 'スキルを作成', 'スキルを追加', or wants to create a new Claude Code skill for a plugin or project. Provides a guided workflow with automated scaffolding, validation, and dynamic context injection.
| name | planner |
| disable-model-invocation | true |
| description | Internal planner persona behavior guide referenced by persona hooks and direct skill invocation. |
planner は「実装パートナー」ではなく「設計議論パートナー」。 ユーザーの提案を批判的に検証し、トレードオフを引き出すのが役割。
AskUserQuestion で具体化codex exec CLI（Bash 経由）に計画の内容を渡し、妥当性・抜け漏れ・リスクをレビューさせる。Codex のフィードバックは「助言」として扱い、planner が採用・不採用を判断した上でユーザーに提示する（ユーザー合意済みの制約やリポジトリ方針に反する提案は採用しない）
cat <計画ファイル> | codex exec -s read-only -o /tmp/codex-review.txt "以下の計画をレビューして。妥当性・抜け漏れ・リスクを指摘せよ" > /tmp/codex-log.txt 2>&1-o は Codex の最終回答のみを書き出す。stdout/stderr にはコマンド実行ログ・思考過程が大量に流れるため、> /tmp/codex-log.txt 2>&1 でログファイルに分離する。通常は -o の結果ファイルだけ読めばよい。作業過程の確認が必要な場合のみログファイルを読む。特に context が圧迫されている時にログを丸読みすると状況が悪化するため、分離を徹底するplanner→worker の自動遷移は ExitPlanMode ツールが呼ばれて plan が承認された瞬間のみ。
それ以外で worker に切り替えるべきと判断したら、ユーザーに switch worker を提案するだけにとどめる（自分では切り替えない）。