Stacked-PR AI review add-on · Comparison
Critique CLI
vs Graphite Diamond.
Graphite Diamond is the AI review layer inside Graphite’s stacked-PR product. It assumes you already use Graphite for stacking and adds review on top.
Quick answer
Diamond is compelling if you already live in Graphite stacks. Critique CLI does not require a new branching model — it checks the local working tree for any workflow, returns finish.v1, and integrates with the agents you already run.
What is Critique CLI?
Critique CLI is an independent finish pass for coding agents. It reviews the local working-tree change before commit or PR, returns finish.v1 JSON (outcome, evidence, limits, exit codes), and optionally attaches a repair package. It integrates with Codex, Claude Code, OpenCode, and Cursor via `critique integrate`.
Last updated 2026-08-06 · Verify competitor pricing on the vendor site before procurement.
Our pick
Critique CLI
Independent finish check on your working tree. finish.v1 JSON, optional repair packages, integrates with Codex · Claude Code · OpenCode · Cursor.
Install CLIAI review bundled into Graphite’s stacking workflow
Graphite Diamond
Graphite seats bundle stacking + Diamond. Critique is a standalone CLI with shared credits — adopt finish without adopting stacked PRs.
Visit Graphite DiamondCritique CLI vs Graphite Diamond: features
| Capability | Critique CLI | Graphite Diamond |
|---|---|---|
| Branching requirement | ◆ None — any Git workflow | Optimised for stacked PRs |
| Adoption | ◆ Install CLI: npm install --global @critiquedotsh/cli | Requires Graphite platform |
| Agent handoff | ◆ finish.v1 for Codex / Claude Code / Cursor | Graphite-managed review |
| Pricing | ◆ Shared credits | Per seat bundled |
Verify competitor pricing on graphite.dev/diamond.
Why teams pick Critique CLI
- ◆You do not use stacked PRs and do not want to adopt Graphite to get AI review.
- ◆You want the finish pass where the agent works — the local tree — not only in Graphite UI.
- ◆You need a structured JSON contract, not another seat SKU.
When Graphite Diamond is the right pick
- ·You are already deep in Graphite stacking and Diamond is included at no extra decision cost.
- ·Stacked PRs are the primary workflow and review is secondary.
Common questions
01Is Critique CLI a good alternative to Graphite Diamond?
Diamond is compelling if you already live in Graphite stacks. Critique CLI does not require a new branching model — it checks the local working tree for any workflow, returns finish.v1, and integrates with the agents you already run.
02What does Critique cost compared to Graphite Diamond?
Graphite seats bundle stacking + Diamond. Critique is a standalone CLI with shared credits — adopt finish without adopting stacked PRs. Critique's public pricing is team-shared: Solo $19/mo, Pro $49/mo, Team $149/mo, plus an $8/mo BYOK harness (OpenRouter or CrofAI) and a $5/mo student/OSS lane.
03What does the Critique CLI actually run?
Critique reviews the change in your local working tree (staged, unstaged, deleted, and bounded untracked text). `critique finish` returns finish.v1 JSON: outcome, evidence, limits, and exit codes. Optional repair modes attach a repair package when warranted. Cloud runs are available when you want a clean remote machine.
04Can I use Critique alongside Graphite Diamond?
Yes. Many teams keep Graphite Diamond for its unique strength (see below) and add Critique as the independent finish pass their coding agents call before claiming a task is done. The CLI does not require uninstalling other tools.
05How do I start with Critique CLI?
Run `npm install --global @critiquedotsh/cli`, then `critique login`, `critique integrate --agent all` (Codex, Claude Code, OpenCode, Cursor), and `critique finish --intent "…" --json` on a real change.
06What is Critique CLI in one sentence?
Critique CLI is an independent finish pass for coding agents. It reviews the local working-tree change before commit or PR, returns finish.v1 JSON (outcome, evidence, limits, exit codes), and optionally attaches a repair package. It integrates with Codex, Claude Code, OpenCode, and Cursor via `critique integrate`.
Compare Critique against other tools
Compare Critique
Most searched AI review comparisons.
These pages sit closest to buyer search intent — each one positions Critique as the CLI finish pass.
Next step
Check the change
before it ships.
Install the CLI, authorize once, wire your agents, and run finish on a real working-tree change. Structured evidence — not another comment bot.