Calico Claude — Development skill for Claude Code

Calico Claude

**Calico Claude** is a self-hosted, verifiable supply chain for patched native Claude Code binaries. It is a fork of [`a-connoisseur/patch-claude-code`](https://github.com/a-connoisseur/patch-claude-code) (reviewed at upstream commit `729494e`). The display patches are unchanged in intent; this fork adds its own branding, patch-integrity assertions, dependency pinning, and a CI pipeline that publishes SHA-256 checksums plus build provenance attestations. Releases live at [`Nanako0129/calico-claude`](https://github.com/Nanako0129/calico-claude).

Contents

• What this does
• Install
• Keeping it updated
• Trust and security
• Verify the installed binary
• Patch modules in detail
• Related research
• Questions and answers

---

What this does

This repo publishes patched native Claude binaries that make output more transparent without verbose mode, and adds a set of adapters that stay completely dormant unless a launcher such as [remora](https://github.com/Nanako0129/remora-cc) turns them on. Every change is a local patch to the binary's own rendering and request-building code; nothing is proxied, and no protocol is modified.

Display patches (always active)

Module	Effect
thinking-inline	Renders thinking blocks inline instead of hiding them behind transcript mode
thinking-streaming	Streams thinking live, so a 10-minute think shows progress instead of a silent spinner
redacted-thinking-inline	Renders redacted thinking summaries inline as thinking text
subagent-prompt	Shows subagent Prompt: blocks outside transcript mode
tool-call-verbose	Forces verbose rendering of collapsed read/search tool calls
create-diff-colors	Renders created files through the diff component with + lines
`wo