Sandbox
238 repos for skill · Code reviewClear
deepklarity/
harness-kit

A kit for building with AI agents and also the engineering patterns around it.

97
kayba-ai/
Kyoko

🔨 Kyoko is the all-in-one, fully local tool for debugging and improving your AI agents.

97
rse/
ase
rse/asePlugins

Agentic Software Engineering (ASE)

52
codeany-ai/
open-agent-sdk-typescript

Agent-SDK without CLI dependencies, as an alternative to claude-agent-sdk, completely open source

2.7k
KonghaYao/
peri

14MB ACP-Rust Agent, Claude Code Plugin compatible, Dynamic Workflow, Goal, Artifacts, Free Web Search, full feature and better support!

164
risingwavelabs/
box0

Open-Source Platform for Subagents and Agent Teams. Long-running, collaborative, proactive.

81
0xranx/
agentbrief

Pluggable role definitions for AI coding agents — one command turns Claude Code / Cursor / OpenCode / Codex into a specialized professional

45
backnotprop/
plannotator

Annotate and review coding agent plans and code diffs visually, share with your team, send feedback to agents with one click.

8.6k
VisionForge-OU/
foreman

A Boris-style agentic orchestrator TUI that supervises headless Claude Code agents through a gated software-delivery pipeline — pointed at any repository.

443
mvschwarz/
openrig

Multi-agent harness that runs Claude Code and Codex together as one system

66
avivsinai/
agent-message-queue

File-based message queue for local agent-to-agent communication (Maildir-style)

85
zgsm-ai/
costrict

Costrict - strict AI coder for enterprises, quality first, including AI Agent, AI CodeReview, AI Completion.

4.4k
ctxrs/
ctx

Instant recall for coding agents. Search the history already on your machine. Git blame, but for agent sessions.

1.1k
Robotti-io/
copilot-security-instructions

✨ A customizable copilot-instructions.md ruleset & prompts to guide GitHub Copilot toward secure coding defaults in Java, Node.js, C# and Python. Blocks risky patterns, teaches safe habits.

42

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

138k
1 add
spencermarx/
open-code-review

AI-powered multi-agent code review. Simulates a customizable team of Engineers performing code review with built-in discourse.

355
petergyang/
human-review

A visual tool to edit HTML and Markdown files, leave comments like a Google Doc, and send feedback to your AI agent. Works inside your favorite AI harness.

1.2k

AI Badger - Local-first tool that extracts focused repo context for any AI chat (Claude, ChatGPT, Grok, etc.) without wasting tokens on irrelevant files.

35
FlyFission/
nuclear-grade-context-engineering

AI agents now operate with authority. Authority without discipline is how complex systems fail. Nuclear’s control loop, ported to AI-assisted software engineering.

33