Jeffrigby Somepulp Agents
jeffrigby-somepulp-agents is a Claude Code plugin for the Ship phase that adds AI agents for deep code auditing, research, and Codex/Gemini second opinions.
by jeffrigby · github.com/jeffrigby/somepulp-agents
Add specialist Claude Code agents that audit your codebase, research libraries, and pull second opinions from Codex and Gemini.
Add it to Claude Code
Install the plugin in Claude Code. One command, paste-ready.
/plugin install jeffrigby-somepulp-agents@jeffrigby/somepulp-agentsBuilt to be called by your agent
Skillselion is itself an MCP server. Your agent can pull this entry and a paste-ready install config straight from the API - no copy-paste.
Retrieve this entry with skillselion.get_details("plugin:jeffrigby/somepulp-agents") and the paste-ready config with skillselion.get_install_config("plugin:jeffrigby/somepulp-agents").
What it does
jeffrigby-somepulp-agents is a Claude Code plugin bundle that ships three AI-powered agents for solo builders who want stronger review and research loops without leaving the editor. The emphasis is on comprehensive code auditing, library and documentation lookups, and explicit second opinions via OpenAI Codex and Google Gemini alongside Claude. You reach for it in the ship phase when a PR or release needs a deep health pass, but the same agents support build-time pretask research and operate-time doc updates. It is intermediate in complexity because you coordinate multiple models and interpret audit output, not because setup is heavy. Treat it as an agent layer on top of your normal workflow: run audit before merge, research before risky deps, and consultation when architectural choices feel one-sided.
Highlights
- 3-plugin bundle focused on auditing, research, and multi-model consultation
- deepaudit and dead-code oriented workflows for codebase health
- Codex and Gemini opinion agents for a second model view on design choices
- Pretask research and official-docs lookups before implementation
- Documentation maintenance helpers aligned with ongoing code changes
Why builders use it
Solo builders often ship without a second reviewer, reliable audit pass, or fast path to official docs and cross-model sanity checks.
After install, you can trigger dedicated audit and research agents plus Codex and Gemini opinions so review and pretask research happen inside Claude Code.
At a glance
- Type - Plugin in AI Agents.
- Adoption - 0 installs, 5 stars, 0 votes.
FAQ
Who is jeffrigby-somepulp-agents for?
It is for Claude Code users who want structured auditing, research agents, and optional Codex or Gemini second opinions on code and design.
When should I use jeffrigby-somepulp-agents?
Use it before merging large changes, when evaluating unfamiliar libraries, or when you want another model’s take on an architecture decision.
How do I add jeffrigby-somepulp-agents to my agent?
Install the jeffrigby/somepulp-agents Claude Code plugin bundle and configure API access for Codex and Gemini if you use the opinion agents.
Comments
Share how you use jeffrigby-somepulp-agents, gotchas, or tips for other indie builders.
No comments yet - be the first to share how you use it.