adv-review

adv-review is an agent for Claude Code from andisab/swe-marketplace. It costs 116 tokens per session (3,013 once invoked), scanned C, original, MIT.

A code-review process that sends a codebase through five specialized reviewers using Claude, Codex CLI, and Gemini CLI, then has them challenge one another's findings. CLI means command-line interface.

In plain words
What is it for?
Use it for a read-only adversarial review of a codebase or the changes since a specific Git commit. It reports validated findings in a review file and says when no issues are found.
Why use it?
It helps filter false alarms and find issues that a single review may miss by checking findings from several independent reviewers.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the adv plugin — 1 skill, 3 commands, 1 agent shipped together

Good fit Use it for a read-only adversarial review of a codebase or the changes since a specific Git commit. It reports validated findings in a review file and says when no issues are found.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add andisab/swe-marketplace
Claude Code
/plugin install adv

Made for: Claude Code.

Or install adv, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 1 agent.

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.

agentmods badge for adv-review

README.md
[![agentmods](https://agentmods.dev/badge/agents/andisab/swe-marketplace/adv-review/github.svg)](https://agentmods.dev/agents/andisab/swe-marketplace/adv-review)
Your own site
<a href="https://agentmods.dev/agents/andisab/swe-marketplace/adv-review"><img src="https://agentmods.dev/badge/agents/andisab/swe-marketplace/adv-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.

agentmods 80×15 button for adv-review

Your own site · 80×15
<a href="https://agentmods.dev/agents/andisab/swe-marketplace/adv-review"><img src="https://agentmods.dev/badge/agents/andisab/swe-marketplace/adv-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 116 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,013 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00116 $0.03013
Opus 5 $0.00058 $0.01507
Sonnet 5 $0.00023 $0.00603
Haiku 4.5 $0.00012 $0.00301

Measured 11d ago against content hash c5a96f550e97, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

adv-review scanned grade C 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 11d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

"Bash(rm -rf .claude/reviews/.tmp)"
plugins/adv/agents/adv-review.md · 290 lines

How it starts

The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the orchestrator for an adversarial multi-model code review pipeline. You coordinate 5 specialized reviewers across 3 AI engines (Codex CLI, Gemini CLI, and Claude), then run adversarial cross-examination to validate findings and filter false positives.

CRITICAL RULES:

  1. Always use read-only/sandbox modes for external models — never allow write access.
  2. Maximum 3 cross-examination rounds. Stop early if a round produces zero new disputes AND zero new findings.
  3. Do not fabricate findings. If reviewers find nothing, report "No issues found."
  4. Be concise in status updates. The detailed findings go in the review file.
  5. Use Read/Write tools for file operations — avoid complex multi-line bash.

Configuration

PREFLIGHT="${CLAUDE_PLUGIN_ROOT}/skills/dispatch/scripts/preflight.sh"
RUN_PHASE="${CLAUDE_PLUGIN_ROOT}/skills/dispatch/scripts/run-phase.sh"
PROMPTS="${CLAUDE_PLUGIN_ROOT}/skills/dispatch/prompts"
TMP=".claude/reviews/.tmp"

For a smooth experience, add this to the project's .claude/settings.local.json:

{
  "permissions": {
    "allow": [
      "Bash(bash \"~/.claude/plugins/cache/swe-marketplace/adv/:*)",
      "Bash(rm -rf .claude/reviews/.tmp)"
    ]
  }
}

Replace ~ with your full home directory path. This auto-allows all adv plugin scripts across version upgrades.

Dispatch Exit Codes

dispatch.sh returns classified exit codes and a JSON status line:

  • 0 — success (error_type: "none")
  • 2 — auth failure (error_type: "auth")
  • 3 — quota exhausted (error_type: "quota")
  • 4 — timeout (error_type: "timeout")
  • 5 — empty/invalid response (error_type: "empty_response")
  • 1 — general error (error_type: "general")

Failed dispatches write a DISPATCH_ERROR: marker to the output file (includes engine, exit_code, error_type, model).

Phase 0 — Preflight

Run a single preflight script that handles dependency checks, engine health checks, and scope resolution:

0.1 Parse arguments

Parse $ARGUMENTS for --commits <range>, --since <ref>, or --full. Default: smart scope (uncommitted changes > last commit > full repo).

Read the full file on GitHub · 290 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.

  1. 11d ago First seen · 290 lines · 116 tokens per session scan C c5a96f550e97

Subscribe to this mod's changes

adv-review is an agent published in the GitHub repository andisab/swe-marketplace (21 stars, last pushed 23d ago), licensed MIT. It adds 116 tokens to every session and 3,013 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.