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.
npx skills add patrickdappollonio/claude-plugins --skill adversarial-review-quickgit clone --depth 1 https://github.com/patrickdappollonio/claude-pluginsWrote 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.
[](https://agentmods.dev/skills/patrickdappollonio/claude-plugins/adversarial-review-quick)<a href="https://agentmods.dev/skills/patrickdappollonio/claude-plugins/adversarial-review-quick"><img src="https://agentmods.dev/badge/skills/patrickdappollonio/claude-plugins/adversarial-review-quick.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00210 | $0.08404 |
| Opus 5 | $0.00105 | $0.04202 |
| Sonnet 5 | $0.00042 | $0.01681 |
| Haiku 4.5 | $0.00021 | $0.00840 |
Grade A, and why
adversarial-review-quick 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial Review — Quick Panel
Overview
The same hostile review as the full adversarial-review skill, on an 8-reviewer panel instead of 18. Each reviewer runs as a fresh subagent that assumes the code is broken and tries to prove it, from one narrow angle. Because they are fresh, none of them inherit the main session's reasoning or the author's rationalizations — that is the whole point.
The panel is the two charters that check the design itself, plus the six bug-hunting angles that historically produced the most confirmed high- and medium-severity findings. The verifier and the fix validator are not cut — they are what makes the output trustworthy, and they cost two agents.
Claude: do not use dynamic workflows. That means more token consumption for no functional gain. Dispatch plain subagents in parallel.
Say what this panel does not cover
This is a narrower net, and the user must know which way it is narrow. Ten angles are not on this panel:
| Not covered | Escalate to the full adversarial-review when |
|---|---|
| Input Attacker, Authorization Attacker | the change touches untrusted input, authentication, or permissions |
| Concurrency & State Saboteur | the change touches shared state, locking, or parallelism |
| Failure Injection Adversary | the change talks to networks, disks, databases, or third-party services that can fail mid-operation |
| Resource Exhaustion Adversary | the change touches unbounded collections, loops over user data, or hot paths |
| Rollback & Change-Safety Adversary | the change includes migrations, rollouts, or anything that must be reversible under pressure |
| Maintainability Cynic, Karpathy Minimalist | the change is large, or you suspect scope creep |
| AI Anti-Slop Critic, Fact-Checker | the code is AI-generated, or leans on claims about libraries, versions, or standards |
If the change touches any of those, stop and ask before dispatching anyone. Use AskUserQuestion (multi-select): one option per missing angle the change actually touches — named for the risk, not the charter ("it calls services that can fail mid-operation", not "Failure Injection Adversary") — plus a "quick panel as-is" option. Do not ask about angles the change doesn't touch.
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.
- 7d ago First seen · 382 lines · 210 tokens per session scan A 6080cca599be
adversarial-review-quick is a skill published in the GitHub repository patrickdappollonio/claude-plugins (8 stars, last pushed today), licensed MIT. It adds 210 tokens to every session and 8,404 once invoked, about $0.0011 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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.