Water Code — Development skill for Claude Code
A clean-room terminal coding agent built from Claude Code architecture research.
How to install Water Code
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open pacificwater2/water-code and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Water Code does
A clean-room terminal coding agent built from Claude Code architecture research.
Alternatives in Development
- OpenAI Codex CLI — (Rust implementation) 67.8k ★
- OpenMythos — A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the availabl 14.8k ★
- Financial Services Plugins — Plugins that turn Claude into a specialist for financial services — investment banking, equity research, priva 7.7k ★
README
Water Code
Water Code is a clean-room terminal coding agent project built from architecture research on Claude Code, but intentionally re-designed as a simpler, zero-dependency Node MVP.
Detailed Chinese usage guide:
docs/user-manual-zh.mddocs/github-publish-guide.mddocs/github-release-v0.1.0.md
The first version focuses on the core loop:
- CLI entrypoint
- interactive REPL
- session persistence
- agent loop
- tool registry
- pluggable providers
- explicit permission handling for dangerous tools
This repo does **not** try to clone every advanced subsystem on day one. It starts with a practical minimal core that can grow into a larger product.
Why this exists
The research showed that the most durable Claude Code idea is not any single hidden feature. It is the product skeleton:
`main -> commands/tools -> REPL -> query loop -> state/extensions`
Water Code uses that skeleton as inspiration while keeping the first implementation much smaller and easier to evolve.
MVP scope
Current MVP includes:
- one-shot or interactive CLI
- first-class slash commands
- project context loading
- git-aware project state and worktree awareness
- formal JSON tool-calling protocol
- diff preview and exact patch editing
- structured tool result rendering
- richer permission modes
- approval history and remembered approvals for dangerous tools
- project custom commands
- project custom agents
- project skills
- project plugins
- project-level
WATER.mdinstructions - local MCP server loading
- sequential multi-agent orchestration
- background tasks
- local HTTP bridge surface
- bridge request timeouts and stream heartbeats
- provider abstraction
- planner provider for local testing
- optional Anthropic-backed provider via environment variables
- tools:
list_filesread_filegit_statusgit_worktreespreview_diffpatch_filewrite_filelist_background_tasksget_background_taskstart_background_task
Related Skills
E8 Eea
A collaboratively stress-tested architecture for emergent emotional awareness using E8 hypergraph memory, pred
Calyx
A native macOS terminal app built on Ghostty for running and supervising coding agents
Handmux
A mobile vibe-coding cockpit — built on tmux: drive your live session, Claude Code / Codex — anything a termin
Fixo CLI
Fixo CLI is a terminal-based autonomous coding assistant designed to execute complex programming tasks directl
Rmine
Redmine CLI in Go, built for two callers: a developer at a terminal and a coding agent. Ships an embedded Clau
Stvena
Your coding agent. Your changes. One terminal. A live review workspace for Codex and Claude Code, built in Go.
Related Agents
10x
10x is a terminal-based CLI coding agent (installed via npm install -g 10x-cli) built around the observation t
Engine Design Review Architecture
Before a change you've asked for gets built, checks whether the plan is soundly designed — clean boundaries, a
Part 13: Memory Bridge (Give Coding Agents Your Brain)
When you spawn Codex or Claude Code to build something, they start blind. They don't know your architecture de