daintreehq/daintree

A delegation environment for orchestrating AI coding agents. Manage Claude, Gemini, and Codex sessions across git worktrees with integrated terminals, context injection, and workflow automation.

56Stars on the repository
11Mods indexed here, across every type
todayLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied

stabilize

01

daintreehq/daintree

Skill Claude CodeCodex

USE ONLY WHEN A HUMAN EXPLICITLY INVOKES IT — never auto-select or run this proactively: not after adding a feature, fixing a bug, or finishing a task, not as a routine or ambient health check, and not as a step inside another workflow. This is a deliberate, multi-hour overnight workflow. Once a human explicitly…

not rated 56 today A 263 tokens

daintreehq/daintree

Skill Claude CodeCodex

Guide for creating, modifying and REVIEWING Daintree themes. Use when working on theme palettes, semantic tokens, component extensions, built-in theme definitions, bundled theme preview imagery, or when visually reviewing/refining any existing theme in the real app.

not rated 56 today A 57 tokens

demo-video-creator

03

daintreehq/daintree

Skill Claude CodeCodex

Record a polished 4K screencast/demo video of Daintree by driving the in-app demo engine (window.electron.demo — animated cursor, spotlight, captions) from a Playwright spec. Use whenever the user wants to make a demo video, screencast, product/marketing clip, or feature walkthrough of Daintree — either from a…

not rated 56 today A 97 tokens

monitoring-sweep

04

daintreehq/daintree

Skill Claude CodeCodex

Sweep every open GitHub issue labelled monitoring and decide whether the external event each one is waiting on has actually happened. Monitoring issues are blocked on something outside the repo's control (an upstream stable release, a third-party repo going public, a dependency shipping a fix, a spec landing), so they…

not rated 56 today A 170 tokens

optimize

05

daintreehq/daintree

Skill Claude CodeCodex

USE ONLY WHEN A HUMAN EXPLICITLY INVOKES IT — never auto-select or run this proactively: not after writing code that looks slow, not because a benchmark moved, not as a step inside another workflow. Once a human starts it with /optimize (Claude Code) or $optimize (Codex) it runs FULLY AUTONOMOUSLY to the end, never…

not rated 56 today A 333 tokens

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: