Tools & agents

Pi Outliner integration for Claude Code, following the outline the session folder is bound to: typed outline, workboard and door tools for agents (read, find, edit, comment, changes, draft.patch, ep0ch act), clickable references, and completed responses that mention [[pages]], ((block ids)) or Work IDs in the Outliner's Recent Mentions navigator.

A second_opinion tool and /tribunal command: your diff is reviewed by Codex and Grok side by side, read-only, inside the session

Gives Claude a first-class nushell beside Bash

A workbench for building Claude Code mods: which mods loaded, a live tape of every event with its real payload, the four ship gates on the mod in progress, and tools so Claude can read payloads and run the gates itself

Spotify in Claude Code: connect your account, see what's playing above the prompt, and control playback with /spotify or by asking Claude.

Run OpenAI Codex and Google Antigravity execution lanes from Claude Code with background event delivery, status tracking, and raw command protection.

Manage AI agent skills (SKILL.md), playbooks and value chains: list, toggle, categorise, install from GitHub/monorepo/ZIP/local/marketplace, update, freeze, scan, export, index; run and organise playbooks; map skills and playbooks to value chains. Port of the Obsidian Skills Manager plugin plus BOB playbooks.

Project notes in .claude/notes.md: live dev servers, recent artifacts and pinned links, in a side panel and with /notes.

Provisions a temporary Boomi runtime in the session and hands its ID to Boomi Companion

Checks Boomi Companion's components against the team's standards before they are created, pushed or deployed

See and use Claude Code chats from your other machines

A mod for debugging mods: inspects the session's loaded mods, attributes hook failures (throws, timeouts, rejections) to the mod that caused them, times the chain per plugin, exposes /modscope plus mcpmodscope* tools the model can call, and can ask the session's model to diagnose a failing mod from its own source.

Code review inside Claude Code: the branch diff in a pane, draft comments from you or Claude on any line, sent as a pending GitHub pull-request review. Needs Claude Code 2.1.287 or later, git and gh.

Draw a formula and show the PNG in a pane

What Claude is building (website, mobile app, desktop client, Unity game…), live in a panel of the client (desktop, mobile in Remote Control, terminal): Claude hooks up the project and the network bridge itself, and drives the same target as you

Full-duplex voice conversation with your running Claude Code session, powered by OpenAI gpt-live-1. Toggle with /talk.

Don't reinvent the wheel: finds existing GitHub projects, MCP servers, skills and plugins that fit the conversation and shows them in a small pager above the prompt.

Live subscription usage and pace bars, with an optional provider-neutral delegation advisor.

Gates git work: no commit, push or merge without the user's say-so in their latest message; a push to a branch that already landed is refused; a pushed series must leave the project working at every commit; commit messages (format and the issue it is about, then a Haiku review of the body) and MR descriptions kept tidy.

Understand what you ship: plan with a real diagram and decisions you make yourself, then get grilled on it after building.

Replaces the engine's compaction with a subagent's handoff, and measures whether it can be one

Runs the Laya decision model on your machine: checks each prompt, hints Claude at the right folder and task type, gives Claude a fast laya decide tool, and shows every decision in a band above the prompt.

SKILL.state explicit execution state: schema-validated state tool, action-bound tool gating and turn-end frame compaction

A state-machine graph engine that drives a ticket through claim -> worktree -> coding -> evaluate -> review -> human approval, spawning and monitoring subagents at each step.