git:20261013.e5754e9 to git:20261013.66fea96

15 added, 14 removed. Audit A to A.

---

name: total-review

- description: 'Run four independent Max-effort reviews (Fable 5.1, Opus 5.5, GPT-6 Astra, GPT-6.1 Sol), 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.'

+ description: '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.'

disable-model-invocation: true

---

# Total Review

- Four reviewers, the two best models from Anthropic and from OpenAI, all at `max` effort and in **full permission mode** (the harness maximum). Never swap or downgrade a model, effort, or permission mode. If one is unavailable, stop and tell the user.

+ Five reviewers: the two best models from Anthropic and from OpenAI, plus Meta's Muse Wonder, all at their highest effort and in **full permission mode** (the harness maximum). Never swap or downgrade a model, effort, or permission mode. If one is unavailable, stop and tell the user.

## Permissions

- Always spawn with `--permission-mode full`. That is Claude Code's bypass permissions (`--dangerously-skip-permissions`) and Codex's YOLO mode (no approvals, `danger-full-access` sandbox). A child cannot exceed its parent, so if this thread is not in full mode, stop and tell the user.

+ Always spawn with full permission mode. That is Claude Code's bypass permissions and Codex's YOLO mode (no approvals, full-access sandbox). A child cannot exceed its parent, so if this thread is not in full mode, stop and tell the user.

## Reviewers

- **Fable 5.1**: `--provider claude-code --model claude-fable-5-1`

- **Opus 5.5 (1M)**: `--provider claude-code --model 'claude-opus-5-5[1m]'`

- **GPT-6 Astra**: `--provider codex --model gpt-6-astra`

- **GPT-6.1 Sol**: `--provider codex --model gpt-6.1-sol`

+ - **Muse Wonder**: `--provider pi --model openrouter/meta/muse-wonder` (Pi harness, OpenRouter). Only OpenRouter offers `max` for Muse; never use the `vercel-ai-gateway` route.

## 1. Launch

- 1. Confirm each model is listed with `max` in `supportedReasoningEfforts`: <provider model-list command for Claude Code> and <provider model-list command for Codex>.

- 2. Spawn all four in parallel, one thread each, with the reviewer flags plus `--reasoning-level max --permission-mode full --title "Total review: <model>"`:

- - **Local thread:** <local thread-spawn command, with the appropriate project and environment selected>

- - **Cloud thread:** <cloud thread-spawn command>

- - **Fallback only:** <fallback thread-spawn command> (see <fallback CLI documentation>).

- 3. Confirm with <thread status command> that each thread runs the right model at `max` in `full` permission mode.

+ 1. Confirm each model is listed with `max` in its supported reasoning efforts using the configured provider interface.

+ 2. Spawn all five in parallel, one thread each, using the reviewer settings plus max reasoning, full permission mode, and a title such as "Total review: <model>":

+ - **Local thread:** Use the configured local thread-spawn workflow.

+ - **Cloud thread:** Use the configured cloud thread-spawn workflow.

+ - **Fallback only:** Use the configured fallback thread-spawn workflow.

+ 3. Confirm in each thread's status that it runs the right model at its selected effort in full permission mode.

## 2. Brief

- Send all four the same neutral brief: scope, paths, intended behavior, and diff/base revision.

+ Send all five the same neutral brief: scope, paths, intended behavior, and diff/base revision.

Ask for a thorough senior-developer review, including related code and tests. Review only; change no files. Report serious or critical issues with file and line, a fix, and merge readiness. Separate verified findings from guesses. Use plain English.

Never hint at suspected bugs, mention the other reviewers, or share one reviewer's output with another.

## 3. Collect

- Run <thread wait command>, then <thread output command>, on each. Idle status, timeouts, and queued retries are not completion. Report a failed reviewer; never pass off partial output as a review.

+ Wait for each thread to finish, then collect its output. Idle status, timeouts, and queued retries are not completion. Report a failed reviewer; never pass off partial output as a review.

## 4. Merge and report

- Read all four reports in full. Deduplicate. Keep only real bugs and risks; drop style preferences, theoretical edge cases, and non-issues. Agreement alone does not prove an issue is real.

+ Read all five reports in full. Deduplicate. Keep only real bugs and risks; drop style preferences, theoretical edge cases, and non-issues. Agreement alone does not prove an issue is real.

Show the user:

- A numbered list, one line per issue: what + where.

- - Tags for who found it: `[fable]`, `[opus]`, `[astra]`, `[sol]`. Most-reported first.

+ - Tags for who found it: `[fable]`, `[opus]`, `[astra]`, `[sol]`, `[muse]`. Most-reported first.

- One line: how many findings were dropped.

- Ask: approve these fixes, or adjust the list?

Share full reports only if the user asks.

## 5. Fix and ship

- Only after the user approves: fix the approved issues, then commit and push using the applicable workflow.

+ Only after the user approves: fix the approved issues, then commit and push with the standard ship workflow.