Sleek, Fast and Token Efficient AI Coding Agent
This repository also configures its own agents. See what vix tells them →
Skill Claude CodeCodex
Write an end-to-end (e2e) test for vix. Use when the user asks to add, create, or modify an e2e test that drives the real vix TUI and vixd daemon against the mock LLM server.
Skill Claude CodeCodex
Create and manage lifecycle hooks that vixd fires automatically on agent-loop events (a tool about to run, a prompt submitted, a thread starting, a turn finishing). Use when the user wants to enforce a rule, block or rewrite a tool call, validate prompts, auto-format, notify, or react to what the agent does.
Skill Claude CodeCodex
Create and manage scheduled jobs (cron tasks, reminders, heartbeat checks, polling watchers) that vixd runs automatically. Use when the user asks to schedule, automate, monitor, watch, or be reminded about something.
Skill Claude CodeCodex
Deeply review a GitHub pull request.
Skill Claude CodeCodex
Answer questions about vix itself — the TUI (keybindings, tabs, threads, slash commands), configuration (settings.json, deny lists, permissions), agents & tools, models & providers, jobs, hooks, skills, workflows, MCP servers, the brain/code intelligence, headless/CLI usage, and installation. Use whenever the user…
Skill Claude CodeCodex
Author and edit vix workflows — declarative multi-step pipelines (agent/bash/tool/if/fanout/fanin nodes) stored in config/workflow.json or embedded inline in a job/hook. Use when the user asks to create, modify, or understand a workflow, or to fan work out across many items and join the results.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: