A command that asks several AI models to review a document, plan, or general topic independently, then combines their findings.

Use it for reviewing specifications, proposals, research notes, or other text that is not specifically source code or an implementation plan.

It reduces reliance on one model's opinion and organizes different observations into a shared review.

review — Command for Claude Code by AltimateAI/claude-consensus

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/AltimateAI/claude-consensus

Made for: Claude Code.

Or install consensus, the plugin that ships this one along with the rest of its 8 skills, 4 commands.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/altimateai/claude-consensus/review/github.svg)](https://agentmods.dev/commands/altimateai/claude-consensus/review)

Your own site

<a href="https://agentmods.dev/commands/altimateai/claude-consensus/review"><img src="https://agentmods.dev/badge/commands/altimateai/claude-consensus/review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/altimateai/claude-consensus/review"><img src="https://agentmods.dev/badge/commands/altimateai/claude-consensus/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 6,859 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00020	$0.06859
Opus 5.5	$0.00008	$0.02744
Sonnet 5.5	$0.00004	$0.01372
Haiku 4.5	$0.00002	$0.00686

Measured 4d ago against content hash 73680bce9854, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

review scanned grade B with 1 finding 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 4d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

[ -f ~/.claude/.env ] && export OPENROUTER_API_KEY=$(grep '^OPENROUTER_API_KEY=' ~/.claude/.env | cut -d= -f2- | tr -d '"')

plugins/consensus/commands/review.md · 621 lines

How it starts

The opening of the file, as written. The whole thing — 621 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Model Review

Get independent reviews from multiple AI models (Claude + configured external models) on documents, plans, specs, or any free-text topic. Compare findings and converge on a unified review through structured synthesis and agreement rounds.

For code reviews, use /consensus:code-review. For implementation plans, use /consensus:plan-review. This command covers everything else.

Compaction Resilience

This is a long-running command. Context compaction may erase in-memory state mid-run.

Check resume: Glob data/scratch/active-progress-consensus-review-*.md — find any with Status IN_PROGRESS and < 24h old. If found, read its SESSION_DIR and skip to first unchecked goal. If Status is COMPLETED or FAILED, ignore it.
Write progress: After creating SESSION_DIR, create a unique progress file: data/scratch/active-progress-consensus-review-{SESSION_ID}.md (where SESSION_ID is the random suffix from SESSION_DIR, e.g. X4f2kL)
Mark done: Set Status to COMPLETED at end of successful run, or FAILED on abort
Save incrementally: Write/append to $SESSION_DIR files after each phase, not at the end

Goals Template

# consensus:review — {TARGET}
Started: [timestamp]
Status: IN_PROGRESS
Command: consensus:review
SESSION_DIR: {SESSION_DIR path}
TTL: 24h

## Goals
- [ ] Phase 1 — Setup: load config, detect review type, write prompt, create team
- [ ] Phase 2 — Spawn reviewers: launch teammate agents + write Claude's review
- [ ] Phase 3 — Collect reviews: wait for all models to send their reviews
- [ ] Phase 4 — Analyze & compare: build comparison table, identify consensus issues
- [ ] Phase 5 — Synthesize: draft unified review (type-specific format)
- [ ] Phase 6 — Convergence: send draft to all models, collect APPROVE/CHANGES NEEDED
- [ ] Phase 7 — Present final review with attribution table, cleanup team

## Progress
- [HH:MM] Starting execution...

Checkpoints

After Phase 2: Claude's review written to $SESSION_DIR/claude.md
After Phase 3: All model reviews on disk at $SESSION_DIR/{model.id}.md
After Phase 5: Draft review at $SESSION_DIR/draft.md
After Phase 6: Convergence responses at $SESSION_DIR/{model.id}-convergence.md

Read the full file on GitHub · 621 lines

Changes

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.

4d ago Changed · +2 lines 73680bce9854
2mo ago First seen · 619 lines · 20 tokens per session scan B 4db42e4e2fd3

Subscribe to this mod's changes

review is a command published in the GitHub repository AltimateAI/claude-consensus (33 stars, last pushed 4d ago), licensed MIT. It adds 20 tokens to every session and 6,859 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Code review Research ai claude-plugin consensus developer-tools

review next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
reviewAltimateAI/claude-consensus	Command	33	4d ago	MIT	B	20	Claude Code
review-pryonatangross/orchestkit	Command	299	today	MIT	A	48	Claude Code, Cursor
assessyonatangross/orchestkit	Command	299	today	MIT	A	57	Claude Code, Cursor
iterate-planyonatangross/orchestkit	Command	299	today	MIT	A	38	Claude Code, Cursor
review-artifact-commentsyonatangross/orchestkit	Command	299	today	MIT	A	45	Claude Code, Cursor
review-prMadaraUchiha-314/the-loop	Command	8	8d ago	MIT	A	34	Claude Code
clean-checkTeamManagementPlugin/claude-plugin	Command	6	24d ago	MIT	A	27	Claude Code

review