adversarial-review SKILL.md skillA
adversarial-review from basicmachines-co/basic-memory is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add basicmachines-co/basic-memory/adversarial-review@git:20260530.4ea03d2Pins git:20260530.4ea03d2 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- basicmachines-co/basic-memory
- Path
.agents/skills/adversarial-review/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260530.4ea03d2, committed May 30, 2026
- First version recorded
- May 30, 2026
- Size
- 7,902 bytes
- Repository stars
- 4,440
- License
- AGPL-3.0
Cross-vendor adversarial code review of the current branch. Two different model families (Claude + Codex/GPT) review the diff independently, then try to refute each other's findings; survivors are reported by confidence. Runs from either Claude Code or Codex. Use when the user asks for an adversarial review, a cross-model / second-opinion review, or wants high-confidence findings before merging. Report-only — never auto-applies fixes.
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 code review Two reviewers from **different model families** — **Claude** and **Codex/GPT** — review the same diff independently, then each tries to **refute** the other's findings. A finding's confidence comes from whether it survives that cross-examination. This kills the two failure modes of solo LLM review: self-ratification (a model won't critique its own work) and confident false positives. ## You are the orchestrator — and one of the two reviewers This skill runs from **either** Claude Code **or** Codex. First, **identify which model family you are** (Claude or Codex/GPT). Then: - **You** are reviewer #1. You review **natively**, in this session, using your own tools. - **The other family** is reviewer #2. You invoke it as a **subprocess CLI** for an independent pass: a fresh process, no shared context — that independence is the point. The CLI for "the other model": | If you are… | Invoke the other via… | |-------------|------------------------| | **Claude** | `codex exec` (GPT) | | **Codex** | `claude -p` (Claude) | Everything else in the flow is symmetric. Resolve the `prompts/` and `schemas/` paths …
Read the whole file at its exact version.
How to install
mdr add basicmachines-co/basic-memory/adversarial-review@sha256:5171d85fef990ee9The line at the top of this page pins the label git:20260530.4ea03d2, 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.
[](https://markdownregistry.com/a/art_b5oz33gaxluosgj7)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, all committed on May 30, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260530.4ea03d2 latest | 2026-05-30 | 4ea03d2 | 7,902 B | A | view · diff |
| git:20260530.c717d99 | 2026-05-30 | c717d99 | 7,196 B | A | view · diff |
| git:20260530.d8901ef | 2026-05-30 | d8901ef | 7,439 B | A | view · diff |
| git:20260530.f652a09 | 2026-05-30 | f652a09 | 7,889 B | A | view · diff |
| git:20260530.f865d39 | 2026-05-30 | f865d39 | 6,826 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7902 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
basicmachines-co/basic-memory · 4,440 stars · license AGPL-3.0 · pushed 2026-11-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_b5oz33gaxluosgj7 GET https://markdownregistry.com/api/v1/resolve?ref=basicmachines-co/basic-memory/adversarial-review GET https://markdownregistry.com/api/v1/blob/5171d85fef990ee990a3365c3172a8c69e36374d54b2c1c26d683472bd7a92bf
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 basicmachines-co/basic-memory
Every file in basicmachines-co/basic-memory