debate-review

debate-review is a skill for Claude Code, Codex from amElnagdy/review-skills. It costs 53 tokens per session (1,014 once invoked), scanned A, original, MIT.

A code review workflow in which two AI models debate findings before one final review is produced. It can review a GitHub, GitLab, or Azure DevOps change, or inspect local uncommitted work before a pull request exists.

In plain words
What is it for?
Use it for local pre-commit reviews and for posting inline comments on pull requests or merge requests across the supported code-hosting services.
Why use it?
It gives reported issues a second challenge before they reach the developer, helping distinguish real problems from weak findings. It then posts or prints one consolidated review without approving or requesting changes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

not rated 108repo +13 17d ago A scan Socket: warnSnyk: warnSkillSpector: pass 53 tokens original MIT

Good fit Use it for local pre-commit reviews and for posting inline comments on pull requests or merge requests across the supported code-hosting services.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/amelnagdy/review-skills/debate-review
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.

Any agent
npx skills add amElnagdy/review-skills --skill debate-review
Clone the repo
git clone --depth 1 https://github.com/amElnagdy/review-skills

Made for: Claude Code, Codex.

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 debate-review

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/amelnagdy/review-skills/debate-review"><img src="https://agentmods.dev/badge/skills/amelnagdy/review-skills/debate-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,014 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
  • Socket warn 27 Aug 2026
  • Snyk warn 27 Aug 2026
How audits are shown
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 $0.00053 $0.01014
Opus 5 $0.00026 $0.00507
Sonnet 5 $0.00011 $0.00203
Haiku 4.5 $0.00005 $0.00101

Measured 13d ago against content hash af0dce8aa6ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

debate-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 13d ago.

The scan reads SKILL.md. This mod also ships 8 executable files (scripts/lib/diff.mjs, scripts/lib/dispatch.mjs, scripts/lib/forge.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/debate-review/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

debate-review

Two models argue before anything is posted. A main reviewer finds issues. A debate reviewer tries to knock them down and may add its own. The main reviewer then makes the final call, and one review with inline comments lands on the PR or MR. It posts from the user's own gh, glab or az account as a non-approval review or comment. It never approves and never requests changes.

You are the orchestrator. You run one command and relay the result. You do not review the diff yourself, and you do not touch the PR.

Run it

node "<skill-dir>/scripts/review-pr.mjs" --local [--base <ref>]
node "<skill-dir>/scripts/review-pr.mjs" <pr-url | number> [--dry-run]
  • If the user wants a review and there is no PR/MR URL, run --local from the repo (or --repo-dir). Do not invent a URL. Relay stdout. --local never talks to a forge and rejects non-UTF-8 Git paths rather than decoding them lossily.
  • <pr-url> is a GitHub /pull/N, GitLab /-/merge_requests/N, or Azure DevOps /_git/<repo>/pullrequest/N URL (dev.azure.com or the legacy *.visualstudio.com). A bare number resolves against the cwd's origin, including Azure DevOps https and ssh.dev.azure.com:v3/ remotes.
  • --dry-run prints a live PR review instead of posting it. It does not combine with --local.
  • Azure DevOps needs az logged in (az login) with access to the project. No extension is required, the script talks to the REST API through az rest. A review there is N inline comment threads plus one closed summary thread, since Azure DevOps has no single review object; the alert blockquotes render as plain quotes, which still read.
  • The reviewers are two delegate-skills lanes, review-main and review-debate. If either is missing the script says so. Add them with delegate-setup. Pick two different implementers, since the debate is only worth something when the second model doesn't share the first one's blind spots (main claude or grok, debate codex at high effort is a good pair). For a one-off, pass --main <implementer> or --debate <implementer>. Only implementers whose relay has --read-only are accepted. These two lanes belong to the reviewer. Don't point them at a lane you use for other work, such as a plan-debate lane.
  • Exit code 3 means this head sha already has a debate-review. Re-run with --force to post again.
  • A run takes minutes, since it is two or three implementer sessions back to back. Run it in the background and report the printed URL when it finishes. Don't poll tightly.

Read the full file on GitHub · 63 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. 13d ago First seen · 63 lines · 53 tokens per session scan A af0dce8aa6ac

Subscribe to this mod's changes

debate-review is a skill published in the GitHub repository amElnagdy/review-skills (108 stars, last pushed 17d ago), licensed MIT. It adds 53 tokens to every session and 1,014 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

agent-watchdog

Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a Codex session ID, Claude Code session/transcript, chat/thread link, PR, branch, log, or pasted run summary. Monitor until the other agent is done or blocked, reconstruct what the user asked, independently investigate the same…

BuilderIO/skills · 115 tokens

comet-verify

Comet Phase 4: Verify and Close. Invoke with /comet-verify. Verify implementation matches design, handle development branch.

rpamis/comet · 32 tokens

agent-design-best-practices

Best practices for designing Claude Code agent files (.claude/agents/.md). This skill should be used when writing or reviewing agent markdown files to ensure proper design with focused domains, correct tool access, reusable definitions, and separation of capabilities from lifecycle. Combines Anthropic's official…

majiayu000/claude-skill-registry · 73 tokens

graphify-dotnet

Use graphify-dotnet to generate codebase knowledge graphs, architecture snapshots, and exportable repository maps from .NET or polyglot source trees, with optional AI-enriched semantic relationships. USE FOR: graphify commands; graph JSON, HTML, SVG, Cypher, Markdown, and Obsidian exports; repository map and…

managedcode/dotnet-skills · 125 tokens

map-codebase

Deep architecture report that fans out parallel inspections across different aspects of the codebase (structure, tech stack, APIs, patterns, data flow, dependencies, testing) and synthesizes findings into a comprehensive document at .turbo/codebase-map.md and .turbo/codebase-map.html. Use when the user asks to "map…

tobihagemann/turbo · 106 tokens

sonarqube-mcp

Provides SonarQube and SonarCloud integration patterns via the Model Context Protocol (MCP) server. Enables quality gate monitoring, issue discovery and triaging, pre-push code analysis, and rule education directly in the agent workflow. Use when the user wants to check quality gates, search for Sonar issues, analyze…

giuseppe-trisciuoglio/developer-kit · 127 tokens