メニュー
Start, stop, and troubleshoot agentd services. Use when checking service health, starting/stopping services, viewing logs, or diagnosing connectivity issues between services.
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
Store, search, and manage shared knowledge through the memory service. Use for persisting information across agent sessions, semantic search over stored knowledge, and inter-agent knowledge sharing.
Browse, read, and author per-project knowledgebase documents through the knowledge service CLI. Use for creating, updating, listing, and reading markdown documents stored against a project, and reconciling DB rows against disk.
Cut a new agentd release. Suggests the next semver version from conventional commits (or accepts an explicit `x.y.z`), bumps the workspace version, regenerates the changelog with git-cliff, then commits, tags, and pushes the `v*` tag that triggers the Release workflow. Use when the user runs /release or asks to publish/cut/tag a new version.
Create a new GitHub plan issue with the "Plan: <title>" format, appropriate labels, and structured body. Use when the user wants to capture a high-level plan for future work.
Ask the human user a question during workflow execution and check for answers. Use for agent-to-human Q&A, collecting decisions, and reacting to human responses via ask_response workflow triggers.
Branch stacking and PR management with git-spice for the agentd project. Use when creating stacked branches, submitting PRs, syncing with upstream, resolving rebase conflicts, or navigating a branch stack.
| name | service-ops |
| description | Start, stop, and troubleshoot agentd services. Use when checking service health, starting/stopping services, viewing logs, or diagnosing connectivity issues between services. |
Operational skill for managing the agentd service fleet.
| Service | Dev Port | Prod Port | Binary | Env Var |
|---|---|---|---|---|
| Ask | 17001 | 7001 | agentd-ask | AGENTD_ASK_SERVICE_URL |
| Notify | 17004 | 7004 | agentd-notify | AGENTD_NOTIFY_SERVICE_URL |
| Wrap | 17005 | 7005 | agentd-wrap | AGENTD_WRAP_SERVICE_URL |
| Orchestrator | 17006 | 7006 | agentd-orchestrator | AGENTD_ORCHESTRATOR_SERVICE_URL |
# Check all services at once
agent status
# Check individual service health
curl -s http://localhost:7006/health | jq .
curl -s http://localhost:7004/health | jq .
curl -s http://localhost:7005/health | jq .
curl -s http://localhost:7001/health | jq .
# Start all services (recommended)
cargo xtask start-services
# Start individual services for development
RUST_LOG=debug cargo run -p agentd-orchestrator
RUST_LOG=debug cargo run -p agentd-notify
RUST_LOG=debug cargo run -p agentd-wrap
RUST_LOG=debug cargo run -p agentd-ask
# Start with dev ports (prefix AGENTD_PORT=)
AGENTD_PORT=17006 cargo run -p agentd-orchestrator
# Kill specific service
pkill -f agentd-orchestrator
pkill -f agentd-notify
pkill -f agentd-wrap
pkill -f agentd-ask
# Kill all agentd services
pkill -f agentd-
All services expose Prometheus metrics:
curl -s http://localhost:7006/metrics
curl -s http://localhost:7004/metrics
lsof -i :<port>RUST_LOG=debug for verbose outputagent status~/.local/share/agentd-orchestrator/ or ~/Library/Application Support/agentd-orchestrator/~/.local/share/agentd-notify/ or ~/Library/Application Support/agentd-notify/.db file and restart the service# Structured JSON logging
AGENTD_LOG_FORMAT=json RUST_LOG=debug cargo run -p agentd-orchestrator
# Filter by module
RUST_LOG=agentd_orchestrator::scheduler=debug cargo run -p agentd-orchestrator
# Debug build (fast)
cargo build --workspace
# Release build
cargo build --release --workspace
# Install to ~/.local/bin
PREFIX=$HOME/.local cargo xtask install-user