Is Adversarial Review safe and trustworthy?

tashan scores Adversarial Review on public evidence — tashan score 47.0/100, it is currently active. Audit scope: OSV advisories, install-time scripts, build provenance and declared permission surface. We do not review source code or execute the capability.

How do I install Adversarial Review?

Drop the skill folder into ~/.claude/skills/ (user scope) or .claude/skills/ (project scope).

Who maintains Adversarial Review?

2 GitHub contributors, source: Grimblaz/agent-orchestra.

‹ The Index

Adversarial Review

skill

Reusable adversarial review methodology for prosecution, defense, design challenge, and proxy review passes. Use when reviewing code, plans, designs, or external review ledgers with evidence-first rigor; also when prosecuting a remedy for the defect class it closes, when a change demotes or removes a signal, when judging whether a proposed guard or a substring pin actually holds, when a finding narrows a guard or hardens a selector, and when the thing under review is a newly built mechanism. DO NOT USE FOR: final judgment ownership, GitHub intake routing, or fix execution decisions (use review-judgment or code-review-intake).

Works with: Claude Code (native) · Cursor, Codex CLI (manual)
native: this artifact type is that client's own format

Category: Security — see all ranked ›

Install (Claude Code):

cp -r adversarial-review ~/.claude/skills/

tashan score: 47.0
Adoption: 2 repos
Upkeep: 82.0
Freshness: 99.0
Evidence coverage: 84% of the inputs this score can use — the rest are unknown, and the score is discounted for it
Health: active
Contributors: 2
License: MIT

Security audit

Not scanned yet. We audit npm-published capabilities for known advisories, install-time scripts and permission surface; this one has no npm package we can resolve, or has not reached the queue.

Its own instructions

Its SKILL.md says when to use it, covers setup and states a limitation.

Read from the capability’s own SKILL.md. This is not a grade and does not compare to the instruction-depth verdict on an MCP server — a skill has no tools to document, so that rubric does not apply to it.

You searched for one. Check the rest of your stack:

npx tashan-cli doctor

Reads the config already on your machine and names what is dead, deprecated or running code at install time. No account, nothing uploaded.

tashan Pro$6/mo

Adversarial Review scores 47 today. Pro keeps the series, so you can see whether that is a project getting better or one on its way down — and tells you the day it moves.

Every score since we started measuring, for any capability
The named replacement when something you run is dying — not just that it is
tashan doctor over the config you already have, on your machine

Start a 7-day trial › Everything measured on this page stays free.

Show your score

Measured this well? Put the live badge in your README — it updates as the score does.

[![tashan](https://tashan.sh/badge/skill-grimblaz-adversarial-review.svg)](https://tashan.sh/capability/skill-grimblaz-adversarial-review.html)

source ↗ · skill:Grimblaz/adversarial-review

Everything on this page is public evidence and free. What it cannot know is whether you run this — npx tashan-cli doctor reads your own config and names what is wrong in it, also free. tashan Pro tells you the day any of it changes.

Already running this? npx tashan-cli doctor checks your whole config against the Index — how it works ›

Measured 2026-08-14 · scorer s5 · how · something wrong here?