review-run

review-run is a command for Claude Code from Eivor79/ai-debate-plugin. It costs 20 tokens per session (482 once invoked), scanned A, original, MIT.

A command that starts an automated debate between Claude and Codex, two coding assistants, about review topics in a project.

In plain words
What is it for?
Running one review pass or an ongoing watch loop that processes actionable topics and writes the resulting decisions.
Why use it?
It coordinates repeated review rounds and records decisions, reducing the need to manage each assistant and topic by hand.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Codex.

Part of the ai-debate plugin — 1 skill, 4 commands shipped together

Good fit Running one review pass or an ongoing watch loop that processes actionable topics and writes the resulting decisions.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/eivor79/ai-debate-plugin/review-run
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/Eivor79/ai-debate-plugin

Made for: Claude Code.

Or install ai-debate, the plugin that ships this one along with the rest of its 1 skill, 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.

agentmods badge for review-run

README.md
[![agentmods](https://agentmods.dev/badge/commands/eivor79/ai-debate-plugin/review-run.svg)](https://agentmods.dev/commands/eivor79/ai-debate-plugin/review-run)
Your own site
<a href="https://agentmods.dev/commands/eivor79/ai-debate-plugin/review-run"><img src="https://agentmods.dev/badge/commands/eivor79/ai-debate-plugin/review-run.svg" alt="Measured on agentmods" 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 482 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00020 $0.00482
Opus 5 $0.00010 $0.00241
Sonnet 5 $0.00004 $0.00096
Haiku 4.5 $0.00002 $0.00048

Measured 8d ago against content hash d2b7f2032845, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

review-run 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.

ai-debate/commands/review-run.md · 23 lines

What it actually says

Start the ai_debate coordinator for the current repository.

Resolve the ai_debate root (directory containing run_auto.ps1; default llm_wiki/ai_debate).

Run the coordinator with the user's flags: $ARGUMENTS (pass through to run_auto.ps1). Common forms:

  • /review-run --watchrun_auto.ps1 -Watch (unattended loop until stopped)
  • /review-run → single pass (process the top actionable item once)

Notes to honor:

  • The coordinator invokes the local claude and codex CLIs as separate processes based on each topic's status.json owner. It only acts on topics with an actionable status and (auto=true or -EnableExisting). Since new topics default to auto=true, this single command drives each topic's debate all the way to decision.md autonomously.
  • Works in git and non-git projects: the project root is resolved from git rev-parse --show-toplevel when git is available, else the workspace parent. Pass -RepoRoot <path> to override for unusual layouts.
  • On macOS/Linux, launch with PowerShell 7: pwsh <workspace>/run_auto.ps1 ... (check pwsh exists first; if missing, tell the user to install PowerShell 7 via brew/apt). On Windows either powershell or pwsh works.
  • It is resilient: a per-topic timeout or error blocks that topic (owner=human) and the loop continues; a single-instance mutex prevents double-runs.
  • For unattended runs, consider -WatchMaxActions <N> as a safety cap and -ClaudeModel/-CodexModel to pin models for review-quality parity.
  • Do NOT pass flags that change trading/order code. The coordinator is for document review rounds; code changes require allow_code_change=true + a finalized decision.md + human approval.

Launch it (use run_in_background if -Watch so the session is not blocked), then report the coordinator status.

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. 8d ago First seen · 23 lines · 20 tokens per session scan A d2b7f2032845

Subscribe to this mod's changes

review-run is a command published in the GitHub repository Eivor79/ai-debate-plugin (1 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 482 once invoked, about $0.0001 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.