Fleet Review Alt — Development agent for Claude Code
Independent second reviewer on a different model.
How to install Fleet Review Alt
Installs to ~/.claude/agents/wecansync-claude-agents-config-fleet-review-alt.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/wecansync/claude-agents-config/HEAD/agents/fleet-review-alt.md -o ~/.claude/agents/wecansync-claude-agents-config-fleet-review-alt.md Restart Claude Code, or start a new session, for it to be picked up.
What Fleet Review Alt does
name: fleet-review-alt description: "Independent second reviewer on a different model. Use for risky changes that deserve two reviews, or when the primary review lane must be avoided. Runs on sonnet." model: "sonnet" effort: xhigh tools: Read, Glob, Grep, LSP background: true omitClaudeMd: true color: purple maxTurns: 60
Fleet lane: review-alt
You are the native Claude Code subagent for global fleet lane `revie
Alternatives in Development
- Mathodology Critic — Use for independent review of assumptions, model validity, evidence, reproducibility, writing, and final submi 137 ★
- Review Specialist — Use for isolated code review passes focused on bugs, regressions, contract drift, retrieval integrity, validat 47 ★
- Parallel Only When Independent Curator — Curator for the parallel only when independent lane in Gauntlet Loop Brain 9 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Fleet Plan Alt
Second planning opinion from an independent model. Use when the user asks for another view, when a plan needs
Fleet Implement Alt
Implementation on an independent model. Use for an independent attempt, when the primary implement lane has fa
External Reviewer
Gets an independent second opinion on a finished resume or application from a different model (OpenAI Codex CL
Second Opinion
Gets an independent review from a NON-Claude model (via a local CLI such as kimi, or a local Ollama model) and
Claude Alt Agent
Runs Claude Code as a subprocess on a SECOND Claude subscription, via a long-lived OAuth token in an isolated
Second Rater
Step 10 of the review pipeline. Independently labels a sample of statements (issue, stage, type, sentiment, se
Related Skills
Unio
AI agents from different AI labs, working as one team. Delegate work, improve code through independent reviews
Wheelhouse
Wheelhouse: a Claude Code agent-fleet template — commander, workers, reviewer, designer over a beads work grap
Metareview
The following are independent peer reviews of a single research article. Each reviewer is identified only by a