Skip to content
Agentmart
Submit a tool

adv

Adversarial review from another local model.

Skill by Morrison-Lab

IndexedMIT★ 4
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/morrison-lab-adv

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Adversarial review from another local model.

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/adv

What's inside

Skill name
adv
Description
Adversarial review from another local model.
License
MIT
Instructions
23 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# adv (Codex wrapper)

This is a generated Codex wrapper around the canonical ai-config Claude skill.

Source: [skills/adv/SKILL.md](../../skills/adv/SKILL.md)

Before acting, read the source skill completely and follow its workflow, adapting it to Codex.

The source lives at `skills/adv/SKILL.md` in the same ai-config checkout as this wrapper.
If this wrapper was loaded through `${CODEX_HOME:-$HOME/.codex}/skills/adv`, resolve the symlink target for this wrapper directory first, then read `../../skills/adv/SKILL.md` relative to that real directory.
Do not resolve that relative path from inside `${CODEX_HOME:-$HOME/.codex}/skills`, because it points back at the wrapper tree.

- Treat `user-invocable` and `allowed-tools` as Claude metadata, not Codex permissions.
- Use the tools available in this Codex session for equivalent operations.
- If the source mentions a Claude-only path such as `~/.claude/skills`, use this repository's `skills/` path while editing.
- Keep procedural changes in the canonical source skill unless the user specifically asks to change this wrapper.

## Tool mappings

The canonical skill names `gh`/`git` commands (and sometimes `mcp__github__*` tools).
Resolve those operations using the full per-model reference at [tool-mappings.md](../../tool-mappings.md), preferring the GitHub MCP tool when this Codex session has it and otherwise using the CLI.

From Morrison-Lab/ai-config, MIT.

Signals

Stars
4
Forks
1
Open issues
752
Last commit (this folder)
Sep 3, 2026 (1 month ago)
Last release
Jul 2, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Morrison-Lab

Cite this page

adv skill. Agent Mart. https://agentmart.dev/skills/morrison-lab-adv (last updated 2026-10-24)