Claude Code mod
sabai
Pixel-art band above the prompt: folder, git and node; task progress with Clawd and his moods; a row of subagents; context, session and weekly limits; a toolbar. A Subagents pane with reports, and a Settings pane with raised or flat cards (light and dark), bar styles, alerts and an optional guard with per-rule Block / Ask. In the conversation: tool calls as one-line rows, test results, callout boxes and a receipt at the end of each working turn.
Install
/plugin marketplace add panupat-top/claude-sabai
/plugin install sabai@claude-sabaiMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L2Writes or runs: runs processes, drives Claude, reads files, reads mod state, persists state, draws
- Sees
- compaction, subagent spawns, Bash calls, Read calls, Edit calls, Write calls, Monitor calls, TaskStop calls, every prompt, every tool call, TaskCreate calls, TaskUpdate calls, TodoWrite calls, classic hooks
- Draws in
PaneToolUseToolGroupAssistantMessageAbovePrompt- Hooks
session.startsession.attachsession.compactsession.endagent.spawnturn.stepturn.completecommand.runui.rendersession.measuretool.calltool.checkprompt.submitclassic.PermissionRequestturn.startprompt.compose
From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.
How Claude Code mods work
- A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
- It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
- Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
- Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Details
- Repository
- panupat-top/claude-sabai
- Folder
plugins/sabai- Marketplace
claude-sabai- Author
- Panupat Top
- License
- MIT
- Last updated
- 13 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is sabai?
Pixel-art band above the prompt: folder, git and node; task progress with Clawd and his moods; a row of subagents; context, session and weekly limits; a toolbar. A Subagents pane with reports, and a Settings pane with raised or flat cards (light and dark), bar styles, alerts and an optional guard with per-rule Block / Ask. In the conversation: tool calls as one-line rows, test results, callout boxes and a receipt at the end of each working turn. It is a mod for Claude Code, from panupat-top/claude-sabai on GitHub.
What can the sabai mod access?
Its widest reach is "writes or runs" (runs processes, drives Claude, reads files, reads mod state, persists state, draws). It sees compaction, subagent spawns, Bash calls, Read calls, Edit calls, Write calls, Monitor calls, TaskStop calls, every prompt, every tool call, TaskCreate calls, TaskUpdate calls, TodoWrite calls, classic hooks. It draws in Pane, ToolUse, ToolGroup, AssistantMessage, AbovePrompt. Like any mod, it runs with your permissions.
How do I install sabai?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add panupat-top/claude-sabai and then /plugin install sabai@claude-sabai.
More context & usage mods
routing-mod
blackmath88/routing-mod-claude
Routes each subagent to Haiku, Sonnet or Opus by the [tier:...] tag from your plan. The main session never switches model, so its prompt cache stays intact.
savepoint
KYWAxx/savepoint
Context hygiene with safeguards: checkpoint each finished step, then reset the context to that save, never mid-project.
research-offloader
timothylok/ClaudeCodeModsByTimLok
Spots research prompts and keeps them out of the main context: sends them to your own research endpoint (e.g. a NotebookLM bridge) if configured, otherwise makes Claude delegate to a cheap subagent.
savvy-progress
Berkay2002/berkays-mods
Progress bar above the prompt and an agents panel (/agents-info): running, finished and planned subagents with model, progress, context, cost and time. Crabs for the claude-config scout, builder and reviewer. Copy of johnnyvizz/claude-kit savvy-progress 1.2.0.
reply-line
soonavi/claude-mods
Ends each reply with one status line: context fill, usage windows and their resets, each repo's unpushed work, and what the turn did. For sessions watched in an app that draws no status lines.
savvy-progress
Isaacg1000/isaac-mods
Progress bar above the prompt plus a live panel of every subagent with model, tokens, cost and a customizable pixel crab.
Browse the most popular Claude Code mods, all context & usage mods, or the skills and MCP server directories.