adversarial-review

adversarial-review is a command for Claude Code from Agents365-ai/pi-plugin-cc. It costs 12 tokens per session (446 once invoked), scanned A, original, Apache-2.0.

A review command that asks the Pi coding agent to challenge an implementation's approach, design choices, assumptions, and tradeoffs.

In plain words
What is it for?
Use it for a read-only review of current changes or a branch, with optional focus text and multiple review models.
Why use it?
It can reveal problems in the overall direction that a review focused only on coding defects may miss.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

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 pi plugin — 3 skills, 8 commands, 1 agent, 3 hooks shipped together

Good fit Use it for a read-only review of current changes or a branch, with optional focus text and multiple review models.

Compare 6 commands 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 Agents365-ai/pi-plugin-cc
Claude Code
/plugin install pi

Made for: Claude Code.

Or install pi, the plugin that ships this one along with the rest of its 3 skills, 8 commands, 1 agent, 3 hooks.

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 adversarial-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/agents365-ai/pi-plugin-cc/adversarial-review/github.svg)](https://agentmods.dev/commands/agents365-ai/pi-plugin-cc/adversarial-review)
Your own site
<a href="https://agentmods.dev/commands/agents365-ai/pi-plugin-cc/adversarial-review"><img src="https://agentmods.dev/badge/commands/agents365-ai/pi-plugin-cc/adversarial-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 adversarial-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/agents365-ai/pi-plugin-cc/adversarial-review"><img src="https://agentmods.dev/badge/commands/agents365-ai/pi-plugin-cc/adversarial-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 446 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 $0.00012 $0.00446
Opus 5 $0.00006 $0.00223
Sonnet 5 $0.00002 $0.00089
Haiku 4.5 $0.00001 $0.00045

Measured 9d ago against content hash b6c29ca10b2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

adversarial-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 9d 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/pi/commands/adversarial-review.md · 39 lines

What it actually says

Run an adversarial Pi review through the shared plugin runtime. Position it as a challenge review that questions the chosen implementation, design choices, tradeoffs, and assumptions. It is not just a stricter pass over implementation defects.

Raw slash-command arguments: $ARGUMENTS

Core constraint:

  • This command is review-only.
  • Do not fix issues, apply patches, or suggest that you are about to make changes.
  • Your only job is to run the review and return Pi's output verbatim to the user.
  • Keep the framing focused on whether the current approach is the right one, what assumptions it depends on, and where the design could fail under real-world conditions.

Execution:

  • Run the review in the foreground.
  • If there is nothing to review (empty working tree and no base branch diff), say so and skip the review.
  • /pi:adversarial-review uses the same review target selection as /pi:review.
  • It supports working-tree review, branch review, and --base <ref>.
  • It does not support --scope staged or --scope unstaged.
  • Unlike /pi:review, it can still take extra focus text after the flags.
  • --models <m1,m2,...> (2+ models) runs the adversarial review as a multi-model panel with merged, consensus-ranked findings.

Foreground flow:

  • Run:
node "${CLAUDE_PLUGIN_ROOT}/scripts/pi-companion.mjs" adversarial-review "$ARGUMENTS"
  • Return the command stdout verbatim, exactly as-is.
  • Do not paraphrase, summarize, or add commentary before or after it.
  • Do not fix any issues mentioned in the review output.
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. 9d ago First seen · 39 lines · 12 tokens per session scan A b6c29ca10b2c

Subscribe to this mod's changes

adversarial-review is a command published in the GitHub repository Agents365-ai/pi-plugin-cc (44 stars, last pushed 25d ago), licensed Apache-2.0. It adds 12 tokens to every session and 446 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 2026-08-30.