Borrowing it
Nothing to install: this file belongs to lglucas/ai-dev-operating-system. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lglucas/ai-dev-operating-system/main/.claude/commands/multi-ai-review.mdgit clone --depth 1 https://github.com/lglucas/ai-dev-operating-systemWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/lglucas/ai-dev-operating-system/multi-ai-review)<a href="https://agentmods.dev/commands/lglucas/ai-dev-operating-system/multi-ai-review"><img src="https://agentmods.dev/badge/commands/lglucas/ai-dev-operating-system/multi-ai-review.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.00559 |
| Opus 5 | $0.00026 | $0.00280 |
| Sonnet 5 | $0.00010 | $0.00112 |
| Haiku 4.5 | $0.00005 | $0.00056 |
Grade A, and why
multi-ai-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/multi-ai-review
Cross-review a hard-to-reverse decision through 2–4 independent reviewer roles, reconcile disagreements, and decide proceed / modify / block before committing.
Expected input
/multi-ai-review
Optional arguments:
/multi-ai-review artifact="<path or short name>" blast="<reversible|cosmetic|financial|customer-trust|P0>" reviewers="<role1,role2,...>"
If arguments are omitted, the skill reads the current diff / branch state and asks for the missing fields. The skill will not proceed without an explicit blast-radius statement.
Actions
- Invoke the
multi-ai-reviewskill (.claude/skills/multi-ai-review/SKILL.md). - Pick at least 2 reviewer roles. Default: devil's advocate + technical/security red team. Add more for higher blast radius.
- Dispatch reviewers in parallel; each answers the same 4 questions (concern, failure mode, alternative, confidence 0–10).
- Reconcile: agreed concerns, disagreements, net confidence (= MIN of individual scores).
- Decide: Proceed / Modify and re-review / Block.
- Log via the
decision-logskill intosession-log/.
When to use
- Architecture, auth, data model, payments.
- Migrations or anything irreversible without a backup restore.
- Pricing/packaging changes.
- Public legal/compliance text (Privacy Policy, ToS, refund, LGPD/GDPR).
- Deploy gates with non-trivial rollback.
- Adopting a new external
#agents-marketplaceskill bundle. - The user says "isso é importante" / "não posso errar aqui" / "double-check isso".
When NOT to use
- Routine edits, refactors, bug fixes with tests.
- Reversible UI tweaks.
- Internal-only docs.
Cross-references
- Skill:
.claude/skills/multi-ai-review/SKILL.md - Principle:
ETHOS.mditem 15. - Existing reviewer agents:
.claude/agents/devils-advocate-agent.md,.claude/agents/technical-security-red-team-agent.md,.claude/agents/business-red-team-agent.md. - Often paired with:
/processize,/grow-sustainably,release-check,privacy-audit,business-plan-impact-review.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 54 lines · 52 tokens per session scan A fba4d13264bd
multi-ai-review is a command published in the GitHub repository lglucas/ai-dev-operating-system (11 stars, last pushed 29d ago), licensed MIT. It adds 52 tokens to every session and 559 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
branch-review
Command "branch-review" from hamr0/agentic-toolkit, covering guardrails, target — check the tree first, then interpret $arguments, effort level, stage 1 — general review and stage 2 — security (always full).
code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches superpowers:code-reviewer subagent to review implementation against plan or requirements before proceeding.
refactor
Refactor and optimize [code].
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
init
Install the formatters this repository needs, with every command visible before it runs.