open-walnut

Review recent activity and generate a standup update. Use when the user asks for a standup, "what did I do yesterday", or a daily summary.

Install, configure, verify, update, and remove Walnut plugins from git repos through the Plugin Store REST API. Use when the user pastes a plugin share snippet ({"walnut_plugin_source": ...}) or a git repo URL and wants the plugin installed, or says "install plugin", "add plugin source", "update/remove a plugin", or asks why a plugin is not active.

Distill a workflow, doc, or conversation into a reusable skill. Use when the user says "learn this", "save this as a skill", or wants a procedure captured for reuse.

Register a repository — delegate a Claude Code session to explore the codebase and create a structured profile. Use when the user says "register repo", "add this repo", or wants a repository profile created.

Triage and prioritize pending tasks. Use when the user asks to triage, review priorities, clean up stale tasks, or decide what to work on next.

Summarize the week's progress across all projects. Use when the user asks for a weekly review, week summary, or "what happened this week".

Deep implementation details for src/core/ — task model (5 text fields, phase lifecycle, dependencies, session slots, child tasks), session monitoring (3-layer), message queue & FIFO/JSONL delivery patterns, daemon-uniform file access rule, chat history compaction. Use when implementing or debugging anything in src/core/ or the session data layer.

Implementation details for src/agent/ — runAgentLoop internals (providers, auth, retry, streaming, abort, continuation), prompt caching, tool return types, tool module file map. Use when modifying the butler agent loop, providers, or agent tools.

Logging system details for src/logging/ — logger API & child loggers, log levels, automatic secret redaction, browser console log persistence (how to investigate frontend issues from disk logs). Use when adding logging or investigating issues via /tmp/open-walnut logs.

Testing details for the Walnut repo — 5-tier pyramid (unit/integration/e2e/browser/live), per-tier vitest configs & parallelism, how to judge if YOUR change caused a failure (isolated run + HEAD baseline diff), known pre-existing failures, mock-constants helper, live test pattern, Playwright modes. Use when running tests, adding tests, or triaging test failures.

Implementation details for web/src/ (React SPA) — session chat single-timeline model (streaming blocks, render-filter absorption, optimistic dedup, turn watermark), UX patterns (task refs, images, plan cards, slash commands), frontend file structure. MUST read before touching session chat, turn boundaries, or streaming block rendering.

4-agent pipeline: design + implement code tests + Playwright UI tests + quality gate. Reads walnut-console-ops first.

Create and manage routines — scheduled automations that run on a trigger (cron / interval / one-shot) with a pluggable executor (main-agent, walnut-agent, or claude-code session, local or remote host). Use when the user says "every morning", "every weekday", "remind me daily", "schedule", "routine", "automate this", "run X at Y time", or wants to set up a recurring job / virtual employee.

Hands-on setup agent for Open Walnut. Paste into your OWN Claude Code session — it makes Walnut's butler able to talk on first launch. It mirrors however THIS Claude Code is already authenticated (SSO profile, bearer token, or access keys) into Walnut, installs, starts the server, and proves it works with a real model call — fixing auth errors itself and asking you only when it truly can't proceed. Use when a user wants to install or set up Open Walnut.

Manage repository profiles — add, view, edit, or remove registered repositories. Each repo stores name, description, tech stack, host paths, architecture notes, and common commands as structured YAML. Use when user says "add repo", "manage repos", "register repository", "show my repos", "edit repo", or wants to manage repository profiles.

Deep-explore current codebase and register it as a Walnut repository. Produces a rich profile: what the project does, architecture overview, key components, tech stack, and common workflows. Use when user says "register repo", "add this repo", "/walnut-register-repo", or wants to create a Walnut repository profile for the current project.

Operating the Walnut web UI (localhost:3456) via Playwright MCP tools — understanding the UI layout, chatting with main agent, interacting with sessions, monitoring status changes. Use when asked to test, verify, or interact with the Walnut web console as a human user would.