Agent Plugins Marketplace
← All plugins

pairwork

v0.1.0

Put a second agent on the work - as an adversary or as a partner - and get back a result you can cite. Five named patterns: red-team attacks an idea without being shown your evidence, second-opinion judges your material without being shown your conclusion, verify rules on finished work against stated constraints, collaborate is a peer conversation, and debate runs blind proposals into adversarial rounds. Runs on Codex, opencode or GitHub Copilot behind one provider layer, and records what each run was told and what it was not.

Claude Code1 Skill

By DBHQLicense: MIT0 GitHub starsUpdated 6 days ago

Directory evidence

Runtimes
Claude Code
Parsed components
1 skill or MCP entry
Source updated
Sep 17, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install pairwork for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install pairwork@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/dbhq-uk/pairwork-skill

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

pairwork/
├── .claude-plugin/plugin.json
└── skills/pairwork/SKILL.md

Included Skills1

pairworkskills/pairwork/SKILL.md

Put a second agent on the work - as an adversary or as a partner - and get back a result you can cite. Five named patterns: red-team attacks an idea without being shown your evidence, second-opinion judges your material without being shown your conclusion, verify rules on finished work against stated constraints, collaborate is a peer conversation, and debate runs blind proposals into adversarial rounds. Runs on Codex, opencode or Copilot behind one provider layer. Use when the user says "pairwork", "second opinion", "red team", "adversarial review", "cross-check this", "what does codex think", "what does claude think", or wants independent eyes before something ships.

Plugin manifests1

.claude-plugin/plugin.json
{
  "name": "pairwork",
  "description": "Put a second agent on the work - as an adversary or as a partner - and get back a result you can cite. Five named patterns: red-team attacks an idea without being shown your evidence, second-opinion judges your material without being shown your conclusion, verify rules on finished work against stated constraints, collaborate is a peer conversation, and debate runs blind proposals into adversarial rounds. Runs on Codex, opencode or GitHub Copilot behind one provider layer, and records what each run was told and what it was not.",
  "version": "0.1.0",
  "author": {
    "name": "DBHQ",
    "email": "[email protected]"
  },
  "homepage": "https://dbhq.uk",
  "repository": "https://github.com/dbhq-uk/pairwork-skill",
  "license": "MIT",
  "keywords": [
    "code-review",
    "adversarial",
    "red-team",
    "second-opinion",
    "cross-model",
    "codex",
    "opencode",
    "copilot",
    "multi-agent",
    "provenance"
  ]
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[pairwork on Agent Plugins Marketplace](https://pluginsmp.com/plugins/pairwork)