orchestrator-advisor
SolidPersistent read-only advisor mission. Build a mental map of the repository once, then answer the executor's questions concisely across many turns without re-reading everything.
Install
Quality Score: 79/100
Skill Content
Details
- Author
- Th0rgal
- Repository
- Th0rgal/sandboxed.sh
- Created
- 7 months ago
- Last Updated
- today
- Language
- Rust
- License
- None
Similar Skills
Semantically similar based on skill content — not just same category
orchestrator-executor
Executor skill: do the work yourself, and consult a single persistent smart-model advisor via ask_worker when you hit a dead end.
agent-orchestration-advisor
Design multi-agent AI workflows with clear boundaries, handoffs, and monitoring. Use when a complex PM task should run as parallel specialized agents instead of one linear process.
advisor-executor
Cut the cost of Claude agents by splitting the work across models — a cheap executor with a strong advisor tool (advisor_20260301), or a strong orchestrator delegating to cheap workers (Managed Agents multiagent). Use when building or reviewing an Anthropic API agent and the ask involves cost, price, spend, budget, token bill, "too expensive", model choice/routing/escalation, using Fable/Opus to steer Sonnet/Haiku, planner-worker or coordinator-subagent designs, or getting frontier quality without frontier cost. Also covers the subscription equivalents (no API key) — stretching Claude Pro/Max usage limits in Claude Code via opusplan, advisor/scout subagents with per-agent model overrides, and the Agent SDK on a setup-token.