A project for running, developing, and switching Aiko personas with agents such as Codex and Claude Code / Persona-driven AI agent framework for running and customizing Aiko across Codex and Claude Code.
A documentation skill that creates or updates an AI-facing INDEX.md and a human-facing README.md at a project directory’s entry point. The index focuses on structure and conventions; the README focuses on purpose, setup, and current status.
A fill-in template for recording a project's programming languages, packages, services, APIs, and development tools. It organizes these choices by areas such as the front end, back end, and data storage, with their purposes and documentation links.
A command-line tool that downloads a Google Slides presentation and extracts its slide text and speaker notes into Markdown. It accepts a presentation ID or a shared Google Drive URL.
A skill for showing an HTML file or static project on a temporary live URL that can be opened from another device on the same private Tailscale network. Tailscale is a private network connecting approved devices.
A command for recording an agent session in JSONL, a text format with one JSON object per line, and pushing the resulting logs to GitHub. It is intended for use when a work session has ended.
A manually run command for checking and starting four named helper agents: reviewer, scout, lab, and janitor. It can show when each last ran and whether work is waiting.
A command wrapper for sending and receiving messages between separate Claude Code sessions running in different terminals. It supports requests such as reviews, parallel tasks, completion notices, and ordinary messages.
A workflow for handling a pull request, which is a proposed code change awaiting review before it is added to a project. It checks automated tests and reviewer comments, applies fixes, and can merge the change when it is ready.
A short self-check for messages, files, calendar entries, and email drafts sent to the project owner. It checks whether the result can be opened, is the right size, and supports an immediate decision.
A command for loading a named work role into the current agent session. A role is a set of purpose, skills, tools, principles, and decision rules for a type of work.
A command for checking and manually running recurring tasks recorded in a repository. It can show task status, run maintenance agents, or start organization-specific jobs such as data collection and report generation.
A session-start routine for an agent-based workspace. It loads recent logs, operating rules, available skills, and unfinished input so the agent can resume with the needed context.
A nine-step planning skill for breaking a large project or initiative down from its purpose to concrete preparation. It separates goals, current conditions, approaches, measures, actions, and deliverables.
A command for synchronizing a local agent-definition folder with GitHub. GitHub is a service for storing and sharing code and related files, while synchronization keeps local and remote copies aligned.
A task-list skill that stores a project's unfinished work in a tasks.json file. It responds to commands for listing, adding, updating, and closing tasks.
A session-ending workflow for an AI agent that updates its work log, runs scheduled self- or peer reviews, and pushes the changes to Git.
★not rated 3 1mo agoA120 tokens
originalMIT
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: