adversarial-review

adversarial-review is a skill for Claude Code from SSBun/csl-agent-kit. It costs 79 tokens per session (945 once invoked), scanned A, original, MIT.

A review workflow that uses separate Reviewer and Editor roles to examine code, plans, specifications, and other deliverables until the reviewer approves them.

In plain words
What is it for?
It helps conduct adversarial reviews of code, pull requests, product requirements, technical proposals, design documents, and similar work.
Why use it?
It catches problems through an independent review loop and prevents approval while unresolved findings remain.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; mentions Codex.

Part of the csl plugin — 34 skills, 2 commands, 1 agent, 10 hooks shipped together

Good fit It helps conduct adversarial reviews of code, pull requests, product requirements, technical proposals, design documents, and similar work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ssbun/csl-agent-kit/adversarial-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 SSBun/csl-agent-kit --skill adversarial-review
Clone the repo
git clone --depth 1 https://github.com/SSBun/csl-agent-kit

Made for: Claude Code.

Or install csl, the plugin that ships this one along with the rest of its 34 skills, 2 commands, 1 agent, 10 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/skills/ssbun/csl-agent-kit/adversarial-review.svg)](https://agentmods.dev/skills/ssbun/csl-agent-kit/adversarial-review)
Your own site
<a href="https://agentmods.dev/skills/ssbun/csl-agent-kit/adversarial-review"><img src="https://agentmods.dev/badge/skills/ssbun/csl-agent-kit/adversarial-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 945 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 $0.00079 $0.00945
Opus 5 $0.00039 $0.00473
Sonnet 5 $0.00016 $0.00189
Haiku 4.5 $0.00008 $0.00094

Measured 4d ago against content hash 2ae4d8c5dc5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 4d 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.

skills/dev/adversarial-review/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adversarial Review

Gate Contract

  • Enter only from an explicit user request; never infer the need from risk, complexity, verification gaps, or another workflow.
  • Start BLOCKED with distinct Reviewer and Editor agents.
  • Prefer real isolated subagents for the Reviewer and Editor when the host can dispatch them; fall back to inline role-play with ISOLATION: simulated disclosed. Follow Subagent Dispatch.
  • While BLOCKED, do not finalize, approve, commit, publish, or externally share the artifact.
  • APPROVED is review evidence, not external-action authorization.
  • Set no total round or cycle limit. Continue by review state under Review Loop Contract.
  • Keep the active finding ledger in Reviewer–Editor handoffs; do not write report files during intermediate rounds.
  • Reviewed artifact changes invalidate APPROVED; return to BLOCKED and resume the same numbered review history.
  • No independent Reviewer: fail closed.

Roles

  • Coordinator: Pins scope, gate, routing, and verdict; may be Editor, never Reviewer.
  • Reviewer: Read-only; separates findings, required outcomes, and optional remedies under the shared principles.
  • Editor: Audits adequacy, minimal resolution, blast radius, and proportionality before accepting, narrowing, rejecting, acknowledging, or escalating; never self-approves.

Reuse the Reviewer. A replacement receives the complete state, artifact, available diff, round number, and finding IDs.

For multiple viable decisions, fixes, or plans, remain BLOCKED and use Decision Consensus Gate before choosing one.

Workflow

0. Resolve dispatch mode

Detect the host's dispatch capability, verify the dispatch path is actually ready (on Pi: the pi-agent carrier is registered and spawnable; on Codex: the host can spawn an agent process), record the mode and per-role readiness once per run, and print the dispatch metadata table to the user as the first output of the run — before any role pass — as specified in Subagent Dispatch. If all roles are ready, enter SUBAGENT mode without asking; if any role is missing, present the table and ask the user whether to proceed in INLINE-FALLBACK, and enter it only on explicit confirmation. Never enter the loop on an unverified dispatch path. The Review Loop Contract, finding ledger, and report format are identical in both modes; APPROVED reached under simulated isolation carries that caveat.

Read the full file on GitHub · 61 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. 4d ago Changed 2ae4d8c5dc5d
  2. 8d ago First seen · 61 lines · 79 tokens per session scan A 20d01bd0d635

Subscribe to this mod's changes

adversarial-review is a skill published in the GitHub repository SSBun/csl-agent-kit (10 stars, last pushed 7d ago), licensed MIT. It adds 79 tokens to every session and 945 once invoked, about $0.0004 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.