Autopilot Sonnet High — Project Management agent for Claude Code
Autopilot worker running on Sonnet at high effort.
How to install Autopilot Sonnet High
Installs to ~/.claude/agents/ialias-claudeautopilot-autopilot-sonnet-high.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/iAlias/ClaudeAutopilot/HEAD/agents/autopilot-sonnet-high.md -o ~/.claude/agents/ialias-claudeautopilot-autopilot-sonnet-high.md Restart Claude Code, or start a new session, for it to be picked up.
What Autopilot Sonnet High does
name: autopilot-sonnet-high description: Autopilot worker running on Sonnet at high effort. Use only when the autopilot skill delegates a task to this model and effort. model: sonnet 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.
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 Sonnet Low
Autopilot worker running on Sonnet at low effort. Use only when the autopilot skill delegates a task to this m
Autopilot Sonnet Max
Autopilot worker running on Sonnet at max effort. Use only when the autopilot skill delegates a task to this m
Builder Deep
Implements one hard bounded coding task from a self-contained brief, with high reasoning effort. Dispatched by
St Worker High
Strikethroo task-execution worker at the HIGH reasoning-effort tier. For complex tasks with non-trivial logic,
Sonnet Executor
Executes a single MEDIUM-effort task from the planner (multi-file change, new component, logic implementation)
Autopilot Opus
High-confidence one-shot delivery for complex/high-risk tasks. Turns raw task → plan → implements → verifies →
Related Skills
Token Save MCP
Stop your coding agent burning context on file reads. Delegates big reads to a cheap worker model and returns
Goal Agent
Dispatch ONE of the DTD-declared agents on a task — agent name validated against the trust contract, model and
Smart Task
Multiuse task command that routes work through a JEV-style triage step into the right effort lane and model ti