Deevsdeevs Agent System
deevsdeevs-agent-system is a Claude Code plugin bundle for the Build phase that installs twelve orchestrated agent personas for research, audit, coding, and validation workflows.
by DeevsDeevs · github.com/DeevsDeevs/agent-system
Orchestrate a twelve-plugin Claude Code agent system with specialized personas for research, audits, quantitative analysis, and senior dev workflows across the repo.
Add it to Claude Code
Install the plugin in Claude Code. One command, paste-ready.
/plugin install deevsdeevs-agent-system@DeevsDeevs/agent-systemBuilt 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:DeevsDeevs/agent-system") and the paste-ready config with skillselion.get_install_config("plugin:DeevsDeevs/agent-system").
What it does
deevsdeevs-agent-system is a Claude Code plugin marketplace described as a complete agent system for becoming a ten-times more effective engineer. The bundle exposes twelve plugins whose keywords read like a squad of specialists: architects, reviewers, quantitative researchers, forensic auditors, concurrency purists, and domain experts spanning finance microstructure, science papers, and polyglot implementations. Solo builders who already treat Claude Code as a daily IDE partner can install the collection to route tasks through named personas instead of one generic prompt. It is journey-wide in practice because the same orchestration layer can support early research reads, implementation depth, adversarial review, and test-oriented validation, even though Skillselion shelves it under Build agent-tooling as the install moment. Complexity is advanced: you must understand which sub-plugin to invoke, avoid overlapping personas, and supply enough repository context for multisession flows. It is not a beginner-friendly single command; it is an opinionated multi-agent operating model bundled for Claude Code.
Highlights
- Twelve-plugin agent-system marketplace bundle for DeevsDeevs/agent-system
- Keyword surface spans adversarial review, forensic audit, hypothesis testing, and quantitative flows
- Persona-oriented experts for Python, Rust, Golang, devops, and research paper workflows
- Trading and microstructure-themed specialists alongside general senior developer patterns
- Multisession orchestration, lazy streaming, and systematic validation motifs across plugins
Why builders use it
One generic agent session cannot match the depth of specialized review, research, and implementation roles a solo builder needs on hard repos.
After registering the marketplace bundle, you can invoke targeted expert plugins from a twelve-plugin squad instead of re-prompting a single general assistant.
At a glance
- Type - Plugin in AI Agents.
- Adoption - 0 installs, 38 stars, 0 votes.
FAQ
Who is deevsdeevs-agent-system for?
It is for experienced builders who want DeevsDeevs’s multi-plugin agent squad inside Claude Code for deep engineering and research tasks.
When should I use deevsdeevs-agent-system?
Use it whenever you would otherwise spin up separate review, audit, or domain-expert chats—from idea research through ship-time testing—not for a one-line codegen snippet.
How do I add deevsdeevs-agent-system to my agent?
Install the DeevsDeevs/agent-system marketplace entry in Claude Code, enable the relevant plugins from the twelve-plugin set, and follow each sub-plugin’s invoke guidance in the repo.
Comments
Share how you use deevsdeevs-agent-system, gotchas, or tips for other indie builders.
No comments yet - be the first to share how you use it.