agentmods.dev

review-new

review-new is a command for Claude Code from Eivor79/ai-debate-plugin. It costs 32 tokens per session (753 once invoked), scanned A, original, MIT.

A command that opens a topic for a structured agent debate, runs the participants and coordinator, and reports a decision.

In plain words
What is it for?
Use it to create and run debates about competing options, set a priority or round limit, request manual review, or create a debate without starting it.
Why use it?
It turns a discussion question into a tracked process with topic files, rounds, optional human review, and a final verdict.

Command for Claude Code

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

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

not rated 1repo 2mo ago A scan 32 tokens original MIT

Good fit Use it to create and run debates about competing options, set a priority or round limit, request manual review, or create a debate without starting it.

Compare 6 commands from other repositories ↓
View source ↗ Eivor79/ai-debate-plugin
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 Eivor79/ai-debate-plugin
Claude Code
/plugin install ai-debate

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-new

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/eivor79/ai-debate-plugin/review-new"><img src="https://agentmods.dev/badge/commands/eivor79/ai-debate-plugin/review-new.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 753 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 $0.00032 $0.00753
Opus 5 $0.00016 $0.00377
Sonnet 5 $0.00006 $0.00151
Haiku 4.5 $0.00003 $0.00075

Measured 8d ago against content hash 0bd010ab389c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

review-new 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-new.md · 21 lines

What it actually says

One-shot entry point: after this command the user does nothing until the verdict is ready.

Arguments: $ARGUMENTS — first token(s) form the topic (kebab-case slug, or a natural-language phrase you convert to one). Optional: priority (default p2), --rounds N (round budget: 1 round = 1 numbered doc; sets max_rounds: N, after which a JUDGE verdict is forced — also use this when the user says "N라운드로"), --manual (per-round human review, no auto-run), --no-run (create only, do not start the coordinator).

Steps:

  1. Scaffold if missing: resolve the workspace (directory containing run_auto.ps1, default llm_wiki/ai_debate). If none exists, scaffold it now: create the workspace + _templates/, copy scripts (run_auto.ps1, wait_for_review.ps1, update_status.ps1, scan_queue.ps1) and templates from ${CLAUDE_PLUGIN_ROOT}/scripts/, copy templates/rules.md → workspace README.md, create index.md, and (git repos only) add */run_auto.log.jsonl + */status.json.tmp to .gitignore.
  2. Create the topic in one shot: folder <YYYY-MM-DD>_<slug>/. Write topic.md from _templates/topic.template.md, filling the background/problem/competing-options yourself from conversation context — do not interrogate the user (one clarifying question max, only if genuinely ambiguous).
  3. status.json from _templates/status.template.json: owner=claude, status=ready_for_claude, next_action=design, next_doc=001_claude_design.md, auto=true, allow_code_change=false, priority, updated_at=today, max_rounds = N from --rounds (0/absent = coordinator default 5). With --manual: auto=false, owner=human.
  4. Add a row to index.md.
  5. Start the debate (skip if --manual or --no-run): launch the coordinator in the background — run_auto.ps1 -Watch (pwsh on macOS/Linux, powershell on Windows), using run_in_background. The single-instance mutex makes this safe to attempt even if one is already running (the duplicate exits immediately).
  6. Wait hands-free (skip if --manual/--no-run): launch wait_for_review.ps1 <topic> -UntilStatusLike decided* with run_in_background. When it completes, read decision.md and report the verdict: adopted findings, the ruling, residual risks, next step. If the watcher reports owner=human/blocked_reason instead, report what needs the user's attention.
  7. Remind: code changes still require decision.md + allow_code_change=true + the user's approval.

Follow the workspace README.md rules. Never call codex:* skills to write another agent's round.

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 · 21 lines · 32 tokens per session scan A 0bd010ab389c

Subscribe to this mod's changes

review-new is a command published in the GitHub repository Eivor79/ai-debate-plugin (1 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 753 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.

Building agentsClaude Codeadversarial-reviewai-agentsclaude-code-plugincodex
Related

Other commands, from other repositories

merge-check

A pre-merge checklist command for a GitHub pull request. A pull request is a proposed code change, and the command checks whether it meets the project’s documented requirements before merging.

s977043/river-review · 39 tokens

release-kick

A release command for the River Review project that checks release instructions and pull-request state, updates an out-of-date branch, and verifies the release after merging.

s977043/river-review · 64 tokens

plan-merge-order

A command that plans the order for merging several pull requests (PRs), which are proposed code changes reviewed before entering a shared branch. It checks their status and file changes, then studies dependencies and overlap to reduce rebasing work.

s977043/river-review · 25 tokens

register-plugin-asset

A project command for adding a distributable command, agent, or agent skill to a plugin manifest, the file that lists what a plugin provides.

s977043/river-review · 28 tokens

verify-agent-report

A command for checking whether an agent’s reported branch, pull request, commit, or files actually exist. A pull request is a proposed code change submitted for review.

s977043/river-review · 34 tokens

preflight

A pre-work check for finding whether a coding task or pull request is already finished, obsolete, or being handled elsewhere. A pull request is a proposed change to a code repository.

s977043/river-review · 36 tokens