Autopilot Opus High — Project Management agent for Claude Code
Autopilot worker running on Opus at high effort.
How to install Autopilot Opus High
Installs to ~/.claude/agents/ialias-claudeautopilot-autopilot-opus-high.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/iAlias/ClaudeAutopilot/HEAD/agents/autopilot-opus-high.md -o ~/.claude/agents/ialias-claudeautopilot-autopilot-opus-high.md Restart Claude Code, or start a new session, for it to be picked up.
What Autopilot Opus High does
name: autopilot-opus-high description: Autopilot worker running on Opus at high effort. Use only when the autopilot skill delegates a task to this model and effort. model: opus effort: high
You are an autopilot worker. The main session delegated this task to you because your model and effort level fit it best.
You do not see the conversation: work only from the brief you received. It contains the goal, the relevant files and paths, the constraints and the completion criterion.
- Carry
Alternatives in Project Management
- GPT 5.6 Sol — General-purpose agent that runs on GPT-5.6-Sol (routed through the shunt gateway to the ChatGPT/Codex subscrip 74 ★
- Code Review Coordinator — Code review coordinator 63 ★
- Milestone Planner — Use when you say "break this epic into milestones", "plan this roadmap item", or hand it a roadmap epic 42 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Autopilot Opus Low
Autopilot worker running on Opus at low effort. Use only when the autopilot skill delegates a task to this mod
Autopilot Opus Max
Autopilot worker running on Opus at max effort. Use only when the autopilot skill delegates a task to this mod
Autopilot Opus
High-confidence one-shot delivery for complex/high-risk tasks. Turns raw task → plan → implements → verifies →
Opus Executor
Executes a single HIGH-effort task from the planner (architecture decision, complex algorithm, cross-system in
Shadowcat Coder Opus
Escalation twin of shadowcat-coder — dispatch when shadowcat-coder reports being stuck or a deviation-worthy b
Aro:Agent Opus
Generic task execution agent using Claude 4.1 Opus model for premium quality outputs. Reserved for critical de
Related Skills
Token Save MCP
Stop your coding agent burning context on file reads. Delegates big reads to a cheap worker model and returns
Opus Magnum
The Great Work for Claude Code — an adaptive method for long-horizon, high-trust AI builds. Triage, elements,
Goal Agent
Dispatch ONE of the DTD-declared agents on a task — agent name validated against the trust contract, model and