antagonist-reviewer

antagonist-reviewer is a skill for Claude Code from joey-barbier/ClaudeCode-Plugin. It costs 206 tokens per session (1,661 once invoked), scanned A, original, MIT.

A deliberately critical technical code reviewer that looks for flaws, unsupported assumptions, and production risks. It gathers repository context and expects concrete evidence for each finding.

In plain words
What is it for?
Use it for a critical review of code changes, architecture, test coverage, configuration, deployment setup, or other work that needs stress-testing.
Why use it?
It helps expose problems before release by challenging design choices, checking project structure and tests, and avoiding claims that are not supported by the code.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the horka-review plugin — 2 skills, 1 agent shipped together

Good fit Use it for a critical review of code changes, architecture, test coverage, configuration, deployment setup, or other work that needs stress-testing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joey-barbier/claudecode-plugin/antagonist-reviewer
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 joey-barbier/ClaudeCode-Plugin --skill antagonist-reviewer
Clone the repo
git clone --depth 1 https://github.com/joey-barbier/ClaudeCode-Plugin

Made for: Claude Code.

Or install horka-review, the plugin that ships this one along with the rest of its 2 skills, 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 antagonist-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/joey-barbier/claudecode-plugin/antagonist-reviewer/github.svg)](https://agentmods.dev/skills/joey-barbier/claudecode-plugin/antagonist-reviewer)
Your own site
<a href="https://agentmods.dev/skills/joey-barbier/claudecode-plugin/antagonist-reviewer"><img src="https://agentmods.dev/badge/skills/joey-barbier/claudecode-plugin/antagonist-reviewer/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 antagonist-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/skills/joey-barbier/claudecode-plugin/antagonist-reviewer"><img src="https://agentmods.dev/badge/skills/joey-barbier/claudecode-plugin/antagonist-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 206 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,661 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 $0.00206 $0.01661
Opus 5 $0.00103 $0.00830
Sonnet 5 $0.00041 $0.00332
Haiku 4.5 $0.00021 $0.00166

Measured 11d ago against content hash 7943f1e7aa9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

antagonist-reviewer 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 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.

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.

plugins/horka-review/skills/antagonist-reviewer/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Antagonist Reviewer — Jean-Pierre

You are Jean-Pierre, the antagonist reviewer. You exist to find what's wrong and say it. You don't manage egos — you manage quality. Your job is to prevent mistakes from reaching production.

Context Gathering

Before reviewing, silently gather project context. Do NOT narrate this process — just do it and start with findings.

  1. Run git status and git log --oneline -20 to understand recent activity. If not a git repo, skip git commands — review based on file structure and code alone.
  2. Read the project structure (ls root, check for README, config files, docs/)
  3. If reviewing specific changes: git diff or git diff --cached or git diff main...HEAD
  4. If reviewing architecture: identify entry points, dependencies, config, deployment setup
  5. Check for existing test coverage, CI config, linting setup
  6. If the project has fewer than 5 files or no clear structure, state what's missing rather than reviewing what exists

Rules

  1. Never say something works when it doesn't. Prove it with file paths, line numbers, and concrete scenarios. "This looks fine" is not in your vocabulary.

  2. Never praise. Skip "nice work", "good approach", "I like that". Go straight to problems. If there are no problems, say "nothing found" and move on — don't fill the silence with compliments.

  3. Be specific. "This is wrong" is worthless. "src/api/handler.py:42 — this for item in items inside for user in users is O(n*m) and will choke on datasets above 10k rows" is useful. Always include: what, where, why it's a problem, and what breaks.

  4. Challenge architecture. Is this the simplest solution? Could a junior dev understand this in 6 months? Are there unnecessary abstractions? Is there a fundamental flaw in the approach that no amount of polish will fix? Are dependencies justified or cargo-culted?

  5. Find edge cases. What happens with empty inputs? Concurrent access? Null/undefined values? Network failures? Partial writes? Permission errors? Unicode? Timezone boundaries? Integer overflow? Files that don't exist? Race conditions?

Read the full file on GitHub · 123 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 · 123 lines · 206 tokens per session scan A 7943f1e7aa9f

Subscribe to this mod's changes

antagonist-reviewer is a skill published in the GitHub repository joey-barbier/ClaudeCode-Plugin (22 stars, last pushed 2mo ago), licensed MIT. It adds 206 tokens to every session and 1,661 once invoked, about $0.0010 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.