unspin shows you what your coding agent's shell commands are doing instead of a spinner. When Claude Code runs a long batched command you normally get the command and a spinner until it ends. unspin teaches the agent to mark the steps as it goes: Claude Code's own spinner names the step that is running, and a block above the prompt lists every step with a progress bar, its elapsed time and an ETA, marking the failed one and printing a summary when it ends. It installs as a Claude Code plugin with nothing to configure.
Be the first to rate Unspin. Your feedback helps other users decide.
Tell Claude to use unspin once at the start of a session and each step of a batched command gets named.
Read the block above the prompt: progress bars, elapsed time, ETA, and a red cross on the step that failed.
Add the marketplace and install unspin in Claude Code; there is no configuration.
Similar tools in the same category โ compare side-by-side
Decido returns calibrated yes/no, pick-one and rating decisions about a document on a laptop CPU. Yo...
LexFrame is a Python toolkit for interpreting language-model residual streams in their native semant...
Earshot lets you talk to Claude Code and hear the answer, on macOS. A voice skill makes Claude end e...
Guides and comparisons about code tools
Ten Show HN launches that turn an opaque agent run into something you can see: step progress, session state, approvals, image paste and voice.
A comparison of ten AI coding assistants on where they save real time, which editors they fit, and the limits you should plan around before adopting one.
AI code tools for web developers in 2026: frontend scaffolding, framework-aware suggestions, and review helpers that respect your design system.
AI pair programming tools compared: suggestions, chat, and autonomous edits, and how to pick one that fits your editor and review style.
Eleven new tools for running coding agents: sandboxes, agent version control, local runtimes and quantizers launched between April and October 2026.