Thimble
Open source Claude Code plugin that explains what an agent did, with visualizations in the terminal.
Claude skill that scores how ready a repo is for a coding agent. Open source.
Open source Claude Code plugin that explains what an agent did, with visualizations in the terminal.
An 8 KB skill for reverse engineering with plain CLI tools and no MCP server. Free and open source.
Chess inside Claude Code. A ladder of bots sits above the prompt while the agent works.
Wires Jev into Claude Code so every review finding is scored before you read it.
I built thimble, an open source Claude Code plugin that makes it easy to understand what agents did. It adds explainers and interactive visualizations in your terminal. If Claude Code is for building, thimble is for understanding. Install thimble here! github.com/safety-researc…
Introducing LeanREA: one 8 KB skill file that does what REA does, with plain CLI tools and no MCP. Benchmarked in Claude Code (Sonnet 5.5, 36 runs) against REA: 38% faster, 35% cheaper, 56% fewer turns, same accuracy. Free and open source: github.com/aicodeking/lea…
I got so bored waiting for Claude to write my code that I built chess into Claude Code. Now I can lose to bots while my agents do actual work. github.com/0xdiid/chessmod
I wired TypeSafe's Jev into Claude Code so every code-review finding gets scored before I ever read it. First real run, I pointed it at the plugin's own file reader. It found a genuine bug I had shipped 20 minutes earlier. MIT: github.com/buchmark/claud…