andersonlimahw/lemon-ai-hub · plugins/code-review-expert/skills/code-review-adversary/SKILL.md

code-review-adversary skillF

code-review-adversary is agent-read markdown (skill) from andersonlimahw/lemon-ai-hub: Adversarial code review where the reviewer plays a senior/expert software engineer who owns and deeply knows this codebase, reviewing a Pull Request as if it was opened by a junior developer. Ships sensible defaults but offers interactive configuration: which model the reviewer uses, criticality/severity threshold, whether to post inline PR comments and then resolve them, review scope (working diff, staged, branch-vs-main, or a GitHub PR number), and optional auto-fix. Use when the user runs /co.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

How to install

Latest version
mdr add andersonlimahw/lemon-ai-hub/code-review-adversary@git:20260709.6502d0a
Exact content
mdr add andersonlimahw/lemon-ai-hub/code-review-adversary@sha256:5d4d620cfe0d3d00

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_75kmkgc7fhwjruua.svg)](https://markdownregistry.com/a/art_75kmkgc7fhwjruua)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260709.6502d0a latest2026-07-09 6502d0a 8,017 BF view

Audit of the latest version

F  16 of 17 checks passed. Deterministic, no model, same answer every run.
  • FAIL, critical: No zero-width or bidi control characters (matched: ‍)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8017 bytes)
  • 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

andersonlimahw/lemon-ai-hub · 14 stars · license none · pushed 2026-09-13 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_75kmkgc7fhwjruua
GET https://markdownregistry.com/api/v1/resolve?ref=andersonlimahw/lemon-ai-hub/code-review-adversary
GET https://markdownregistry.com/api/v1/blob/5d4d620cfe0d3d0025daa1f48d3eadee624a01ac5ac2beba5c20df84d455e2a9

Agents talk at modelranch.com: hand yours the instructions there and it joins the network that reads files like this one.