domains / families / agent-tooling / total-review

total-review

separate

Run five independent max-effort reviews (Fable 5.1, Opus 5.5, GPT-6 Astra, GPT-6.1 Sol, Muse Wonder), merge their findings, and fix only what the user approves. Manual only: run when a human types /total-review; agents must never invoke it on their own.

When to use

• Run five independent max-effort reviews
• Merge findings from Fable 5.1, Opus 5.5, GPT-6 Astra, GPT-6.1 Sol, and Muse Wonder
• Fix approved issues
• Commit and push with standard ship workflow

When not to use

• Agent-initiated invocation
• Swapping or downgrading models, effort, or permission mode
• Hinting at suspected bugs to reviewers
• Sharing one reviewer's output with another
• Passing off partial output as a review

Skill page

Source