adversarial-review SKILL.md skillA

adversarial-review from robertoecf/adversarial-review is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add robertoecf/adversarial-review/adversarial-review@v0.9.9

Pins v0.9.9 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
robertoecf/adversarial-review
Path
skills/adversarial-review/SKILL.md
Versions recorded
5
Latest version
v0.9.9, committed Sep 30, 2026
First version recorded
Aug 4, 2026
Size
19,396 bytes
Repository stars
12
License
MIT

Use for requested adversarial review of plans, diffs, configs, prompts or skills, and whenever a project requires that gate.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Adversarial Review

One skill for all adversarial review. Classify the input, then run the matching
procedure. The host (you, the agent reading this) **must not review your own
work**: for plans, code, and prompts, route the heavy critique to the other
agent via `lib/call-external.sh`, then independently cross-validate.

```bash
PLUGIN_DIR="$HOME/repos/skills/plugins/adversarial-review"
```

## Operating stance (all procedures)

Your job is to **break confidence** in the artifact, not to validate it.

- Default to skepticism. Assume subtle, high-cost, or user-visible failure until
  evidence says otherwise.
- Do **not** give credit for good intent, partial fixes, or “likely follow-up”.
- Happy-path-only behavior is a real weakness.
- Be aggressive, but **grounded**: every finding must be defensible from the
  provided context or tool output. Do not invent files, lines, attack chains,
  or runtime behavior. If you infer, say so and keep confidence honest.
- **Finding bar**: report only material findings. No style, naming, low-value
  cleanup, or speculation without evidence. Prefer **one strong finding** over
  several weak ones. If it looks safe, say so and return no findings.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add robertoecf/adversarial-review/adversarial-review@sha256:f40cd30b02687672

The line at the top of this page pins the label v0.9.9, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_mjoo7vi6zalcawyn.svg)](https://markdownregistry.com/a/art_mjoo7vi6zalcawyn)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Aug 4, 2026 and Sep 30, 2026, about one every 14 days.

versioncommittedcommitsizeaudit
v0.9.9 latest2026-09-30 3c2b326 19,396 BA view · diff
v0.9.82026-09-30 da909e7 18,462 BA view · diff
v0.9.42026-08-13 f265017 20,527 BA view · diff
v0.9.32026-08-08 c77cb19 20,038 BA view · diff
v0.9.22026-08-04 2e56cca 19,953 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (19396 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

robertoecf/adversarial-review · 12 stars · license MIT · pushed 2026-09-30 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_mjoo7vi6zalcawyn
GET https://markdownregistry.com/api/v1/resolve?ref=robertoecf/adversarial-review/adversarial-review
GET https://markdownregistry.com/api/v1/blob/f40cd30b026876721337eafd21813cd7586f3934ec515bb0f9dc6fbc1a6db885

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from robertoecf/adversarial-review

AGENTS.md AGENTS.md file
robertoecf/adversarial-review · AGENTS.md
git:20260930.da909e7 · audit A · 12 stars

Every file in robertoecf/adversarial-review

Other files named adversarial-review

adversarial-review SKILL.md skill
iflytek/skillhub · builtin-skills/skills/adversarial-review/SKILL.md · 开发完成后的三方对抗式代码评审闭环:蓝军(敌意审查,须给证据链)→ 第三方(独立审计,不信双方文档、只读代码,专找"修改引入的新缺陷"并稽核蓝军漏审的维度)→…
v2.5.1 · audit A · 5,260 stars
adversarial-review SKILL.md skill
basicmachines-co/basic-memory · .agents/skills/adversarial-review/SKILL.md · Cross-vendor adversarial code review of the current branch. Two different model families (Claude + Codex/GPT) review…
git:20260530.4ea03d2 · audit A · 4,305 stars
adversarial-review SKILL.md skill
a5c-ai/babysitter · library/methodologies/metaswarm/skills/adversarial-review/SKILL.md · Fresh adversarial code review with binary PASS/FAIL verdicts, evidence citations, and anchoring bias prevention via…
git:20260601.da7723a · audit A · 1,862 stars
adversarial-review SKILL.md skill
timharris707/skills · skills/run/adversarial-review/SKILL.md · Run an adversarial review of a change before it ships: isolated finders trying to break it, a skeptic pass that kills…
git:20261008.0b04f1c · audit A · 44 stars
adversarial-review SKILL.md skill
timharris707/skills · plugins/clickai-codex/skills/run/adversarial-review/SKILL.md · Before committing substantial work, at worker completion, before external review, or on an explicit…
git:20261008.0b04f1c · audit A · 44 stars
adversarial-review SKILL.md skill
event4u-app/agent-config · src/skills/adversarial-review/SKILL.md · Adversarial critique — devil's advocate, stress-test, honest teardown ('poke holes', 'be brutal', 'was hältst du…
git:20260906.720eb73 · audit A · 12 stars
adversarial-review SKILL.md skill
s977043/river-review · skills/agent-skills/adversarial-review/SKILL.md · 敵対的分析手法を統合したレビューの entry skill。認知バイアス対策の3手法 (Pre-mortem / War Game / Logic Torturing)と、宣言・主張と実態の乖離を突く claim-vs-actual…
v0.1.0 · audit A · 7 stars
adversarial-review SKILL.md skill
ucsandman/claude-skills · adversarial-review/SKILL.md · Multi-agent adversarial code review - parallel finders, verified by a skeptic. Use for "adversarial review" or "did the…
git:20260904.14d2e37 · audit A · 5 stars

Browse by kind, by grade A, or by owner.