Ship eight side projects in four days with Claude Code and parallel agents

Thiraphat Phutson ran Claude Code from one shared workspace for four days and got about 140 commits across eight repos, two npm libraries and a 439-icon set.

Done withClaude CodeinGitHubNPMCloudflare· Nov 18, 2026

What they did

Starting from an empty folder on November 15, Phutson used Claude Code as a shared workspace for several personal projects at once: a React component library, an icon set, a Thai font, a portfolio rebuild, a typing trainer, an uptime monitor on Cloudflare Workers and a pixel-art music page. A workspace CLAUDE.md and one per project set the rules, including an ask-before list for pushing, creating repos, publishing to npm and bumping versions. The agent kept its own memory notes on decisions and machine quirks. It set up Changesets, GitHub Actions release pipelines with npm trusted publishing, and branch rulesets. For the icons it wrote a design spec and a linter, drew the first 140 itself, then split the other 299 into batches for smaller sub-agents that could draw but not build or commit, and reviewed their output as contact sheets.

How it went

Git counted about 140 commits in four days: 60 on the component library (v0.8.0 on npm, 25 components), 16 on the icon set (439 icons, v0.1.0 on npm), 13 on the font and the rest spread over the other repos. On the last day one change flowed through four repos, from the icon release to the library to three apps that depend on it. Of the 299 sub-agent icons, 15 to 20 needed fixes even though all passed the linter, such as an umbrella that read as a mushroom at 16 px. The agent also traced a failed npm publish to a placeholder token and a production-only CSS bug to the minifier. Taste, logins, first publishes and every push stayed with him.

Worth knowing

The linter could not tell whether an icon read correctly, so a single reviewer looking at rendered output was what made the parallel drafting usable. Credentials stayed manual by design. Some builds would not run locally because Windows App Control blocks unsigned Python modules, so the agent verified those through CI instead.

Try it

With Claude Code· 4 parts to fill in

Act as the builder for [my set of projects] in one shared workspace. First write a short CLAUDE.md for the workspace and one for each project, with an ask-before list: pushing, creating repos, publishing to [npm or my registry], bumping versions and adding dependencies. Commit locally only after [build and test command] passes. For wide repetitive work like [icons, components or pages], write a spec and a checker, then split it into batches for sub-agents that may draft but not commit, and review every batch yourself by rendering the output. Keep short notes on decisions and environment quirks. Stop and ask me before anything leaves this machine.

Square brackets are the parts to fill in. The prompt is ours; the story is theirs.

Where they said it

Related