HN Showcase
Back to browse
GitHub Repository

Achieve extraordinary results with claude code across a variety of tasks

49 starsShell

Swarm – Get consistent results from Claude Code

by bushido·Apr 17, 2026·1 point·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidBig BrainNiche GemSolve My Problem

Recursive review cycles force agent confidence scores before you ever see the output.

Strengths
  • •Recursive review loops cycle back until confidence hits 9/10, hiding intermediate failures.
  • •Role-based team shapes let you tune cost versus quality dynamically without changing prompts.
  • •Audit commands check project context for artifacts that might interfere with agent reasoning.
Weaknesses
  • •Depends on experimental agent teams flag, risking future breakage if Anthropic changes API.
  • •Locked into Claude Code ecosystem, useless for Cursor, VS Code, or other editors.
Target Audience

Developers using Claude Code CLI

Similar To

CrewAI · LangGraph · AutoGen

Post Description

Swarms is the result of months of work where I have spent time tuning my memories, skills, and creating prompts which create consistent results when using agent teams.

I originally put this in a plugin to share it with co-workers, friends, and family so that they could achieve similar results to what I was achieving without having to learn all the different whack-a-mole strategies to keep Claude in check.

This was especially helpful over the last week where making some surgical changes allowed me to maintain quality.

Interestingly, with Opus 4.7, I am seeing some degradation in the initial quality of code that the main agent produces, but by the time it goes through the process which has been defined in this structure, it does result in a shape which I've come to expect.

It does especially well with the review cycles and the quality of writing that it can produce.

Similar Projects

Developer Tools●●Solid

Mimir – Shared memory and inter-agent messaging for Claude Code swarms

Mimir hooks into Claude Code lifecycle events so agents can 'mark' facts (e.g., "API uses snake_case") into a DuckDB-backed memory and RAG pipeline, then auto-injects that context as additionalContext for later agents. It's a pragmatic, well-scoped solution to the annoying problem of agent amnesia — very useful if you run agent swarms, but its impact is limited by Claude Code adoption and the need for the surrounding infra (BGE keys, hooks).

Niche GemShip It
deejaydev
213mo ago