A read-only command that sends a draft to an adversarial reviewer, which examines an idea by looking for weaknesses and counterarguments. It returns a SHIP, REWRITE, or KILL verdict with prioritized issues.

It is for reviewing decision records, position papers, board materials, customer messages, fundraising narratives, constitution changes, and forecasts.

It exposes problems and the strongest opposing case before a draft is shared or used for a decision.

How jaroslavsoucek-art/Giovanni configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jaroslavsoucek-art/Giovanni. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/jaroslavsoucek-art/Giovanni/main/.claude/commands/review.md

Clone the repo

git clone --depth 1 https://github.com/jaroslavsoucek-art/Giovanni

Made for: Claude Code.

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/jaroslavsoucek-art/giovanni/review/github.svg)](https://agentmods.dev/commands/jaroslavsoucek-art/giovanni/review)

Your own site

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

Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,711 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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	$0.00037	$0.01711
Opus 5	$0.00018	$0.00856
Sonnet 5	$0.00007	$0.00342
Haiku 4.5	$0.00004	$0.00171

Measured 10d ago against content hash 0ed85eff8861, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

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 10d 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.

.claude/commands/review.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/review

Run adversarial review on a draft (decision record, position paper, board material, customer message, fundraise narrative, constitution patch, predictive forecast). This command is a thin shell — the adversarial mode policy, four-pass protocol, strongest counter-case requirement, and SHIP/REWRITE/KILL discipline live in the adversarial-reviewer agent. This file is the invocation contract.

Usage

/review <draft-path>                     # required positional — path to draft file
/review <draft-path> --position "..."    # optional one-line position statement
/review <draft-path> --audience external # internal | external | mixed

If <draft-path> is omitted, the orchestrator looks for the draft inline in the message (paste-mode). If neither is present → STOP with usage hint.

Argument syntax

Arg	Type	Default	Meaning
`<draft-path>`	positional	—	Relative path to draft file (e.g. `deliverables/<file>`, `memory/briefs/<file>`, `memory/decisions/<file>`).
`--position "<text>"`	parameterized string	derived from draft	One-line statement of the position the draft is defending. If absent, the agent derives it from the draft itself. If the agent can't derive a clear position, that ambiguity is itself a finding.
`--audience <level>`	parameterized	inferred	`internal` / `external` / `mixed`. If absent, the agent infers from path and content.

Quoted strings supported. --flag=value and --flag value both work.

Pre-flight (binding — STOP on failure)

Before spawning adversarial-reviewer:

CWD check. Working directory is a Giovanni repo. Otherwise STOP.
Agent definition present. .claude/agents/adversarial-reviewer.md exists. Missing → STOP.
Draft accessible. If <draft-path> is set: file exists and is readable. Otherwise STOP: ERROR: cannot read <path>.
Trigger sanity check. If the draft contains explicit out-of-scope markers ("brainstorming", "thinking out loud", "[no review yet]"), surface advisory: WARN: draft contains brainstorming-mode marker. Adversarial review may suppress the exploration that's the point. Proceed? [y/N]. Default = abort.
No required state files. Adversarial review is read-only over the draft and repo — no state files to validate.

Read the full file on GitHub · 119 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.

10d ago First seen · 119 lines · 37 tokens per session scan A 0ed85eff8861

Subscribe to this mod's changes

review is a command published in the GitHub repository jaroslavsoucek-art/Giovanni (2 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 1,711 once invoked, about $0.0002 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 2026-08-31.

Claude Code agent-framework agentic-ai ai-agents anthropic chief-of-staff

Giovanni: Command for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/review

Usage

Argument syntax

Pre-flight (binding — STOP on failure)

What this file has done since we first saw it

Other commands, from other repositories

refactor-clean

agentlas-local

export-closedloop-learnings

spreadsheet-audit

handoff

custom-brief