メニュー
View Self-Evolving Loop session status, history, and memory metrics
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Guided 5-minute onboarding for Director Mode Lite. Use immediately after installing Director Mode Lite, or when unsure which command to run next.
Self-Evolving Development Loop - Dynamic skill generation with learning and evolution
Automatically routes tasks to external AI CLIs (Codex or Gemini) when more efficient; routing decisions are made automatically based on task type, with no manual commands needed. Use when a task is a large refactor, a batch operation, or needs 100K+ tokens of context better handled by an external CLI.
Validate custom agent file format and structure. Use after creating or editing an agent, before committing agent changes, or when an agent fails to load.
Generate custom agent from template. Use when creating a new subagent from scratch, or scaffolding an agent file with correct frontmatter.
List all available agents (core, expert, self-evolving). Use when the user asks what agents are available or runs /agents.
| name | evolving-status |
| description | View Self-Evolving Loop session status, history, and memory metrics |
| user-invocable | true |
View status, history, and memory metrics for evolving-loop sessions.
# Current session status
/evolving-status
# Detailed view
/evolving-status --detailed
# View specific report
/evolving-status --report analysis
/evolving-status --report validation
/evolving-status --report decision
/evolving-status --report learning
/evolving-status --report patterns
# View event history
/evolving-status --history
# View skill evolution
/evolving-status --evolution
# View memory system
/evolving-status --memory
# View tool dependencies
/evolving-status --dependencies
Status: in_progress
Phase: EXECUTE
Iteration: 3 / 50
Started: 2026-01-14T12:00:00Z
Request: Build REST API with user authentication...
Skill Versions:
executor: v2
validator: v1
fixer: v1
Lifecycle Status:
executor: task-scoped
validator: task-scoped
fixer: task-scoped
Task Type: auth (pattern: auth)
Acceptance Criteria:
[x] AC-F1: GET /users endpoint
[x] AC-F2: POST /users endpoint
[ ] AC-F3: Input validation
| Flag | Description |
|---|---|
--detailed | Full JSON state |
--report <type> | View specific report |
--history | Last 20 events |
--evolution | Skill version history |
--memory | Memory system metrics |
--dependencies | Tool co-usage graph |