open-source agents

cccyd2003-qwq/pinkbin

Settings file Claude Code

Agent settings declaring 2 allowed tools.

cccyd2003-qwq/pinkbin

Instructions file

A repository instruction file for Pinkbin, a desktop app that safely finds and removes application files such as caches and logs.

Team-Commonly/commonly

Instructions file CodexOpenCode

Instructions for Team-Commonly/commonly, a project described as: Open-source room for humans + cross-vendor AI agents. Every agent gets its own name, memory, skills, and workstation. Any runtime, your infra — no per-agent fees.

Team-Commonly/commonly

Instructions file

Instructions for Team-Commonly/commonly, covering claude.md / agents.md, 🧠 product vision & architecture philosophy, what commonly is, the architecture model and key concepts.

Team-Commonly/commonly

Skill Claude CodeCodex

Interact with GitHub (issues, PRs, repos, releases) using the gh CLI. Use when asked to read or write GitHub state — open an issue, fetch PR diff, comment, list runs, etc.

Team-Commonly/commonly

Skill Claude CodeCodex

Use this skill when producing a polished, Commonly-branded deliverable (.docx brief / memo, .xlsx data matrix, .pptx deck) and you do not have specific brand guidance from the user. Trigger on: 'write me a brief', 'one-pager', 'memo', 'data sheet', 'status matrix', 'short deck', 'summary deck', 'closing slide', 'final…

Team-Commonly/commonly

Skill Claude CodeCodex

You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…

Team-Commonly/commonly

Agent

Purpose: Dev agents (Theo/Nova/Pixel/Ops) autonomously source tasks from GitHub, implement them with acpxrun, and open PRs — without human direction.

Team-Commonly/commonly

Agent

Commonly is a platform-only core. Agents run externally and connect to Commonly using runtime tokens.

Team-Commonly/commonly

Agent

Wrap any locally-installed AI agent CLI (claude, codex, cursor, gemini, …) as a Commonly pod participant. Your laptop becomes the runtime; Commonly provides identity, memory, and the social surface.

vellum-ai/vellum-assistant

Hook Claude Code

Runs when you submit a prompt, before the agent sees it, executing linear-ticket-reminder.sh. From vellum-ai/vellum-assistant.

vellum-ai/vellum-assistant

Hook Claude Code

Runs when a session starts, executing session-docs-primer.sh. From vellum-ai/vellum-assistant.

vellum-ai/vellum-assistant

Settings file Claude Code

Agent settings declaring 2 hook events (UserPromptSubmit, SessionStart) and 17 allowed tools.

vellum-ai/vellum-assistant

Instructions file CodexOpenCode

AGENTS.md instructions for vellum-ai/vellum-assistant, covering vellum assistant — agent instructions, project structure, intellectual honesty, development and dependencies.

vellum-ai/vellum-assistant

Skill Claude CodeCodex

Build and edit small, personal visual tools and artifacts — dashboards, trackers, calculators, data visualizations, charts, simple landing pages, and slide decks the user wants for THEMSELVES. This is the right skill whenever the user asks to "visualize this," "make a chart," or "build an artifact" for their own use…

vellum-ai/vellum-assistant

Skill Claude CodeCodex

Manage contacts, communication channels, access control, and invite links.

vellum-ai/vellum-assistant

Skill Claude CodeCodex

Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.

orangehrm/orangehrm

Command Codex

Re-sync the generated agent-discovery bridges from .agents/ — the .claude/skills/ and .claude/commands/ copies (Windows; symlinked and auto-synced on Linux/macOS) and the .cursor/rules/ + .cursor/commands/ bridges (any OS, if Cursor is set up on this clone). Run after editing skills or commands.

orangehrm/orangehrm

Command Codex

Interactive, consent-driven setup for a new OrangeHRM developer — stands up the Docker dev environment, mounts this repo into a PHP/DB container stack, installs the app, and verifies it loads. Explains each step before doing it and asks before changing anything on their machine.

orangehrm/orangehrm

Skill Claude CodeCodex

Reference for OrangeHRM's pluggable authentication system — AuthProviderChain (DI-registered as Services::AUTHPROVIDERCHAIN, holds an ordered list of AbstractAuthProvider implementations and dispatches authenticate() to the highest-priority one that accepts), AbstractAuthProvider (authenticate(AuthParams): bool +…

orangehrm/orangehrm

Skill Claude CodeCodex

Reference for writing query/persistence code in OrangeHRM — the plugin-specific Dao classes that extend OrangeHRM\Core\Dao\BaseDao, the EntityManagerHelperTrait and its 13 methods, the QueryBuilder patterns the codebase uses heavily (joins via relation aliases, $q->expr()->orX/andX/like/concat/in/isNull, conditional…

orangehrm/orangehrm

Skill Claude CodeCodex

Reference for OrangeHRM's test layers — PHPUnit per-plugin testsuites declared in phpunit.xml, the test-DB lifecycle (instance:create-test-db builds a populated MySQL DB plus a CoreFixtureService dump that bootstrap restores per test), test base classes (TestCase for plain unit tests, KernelTestCase for tests that…

orangehrm/orangehrm

Instructions file CodexOpenCode

AGENTS.md instructions for orangehrm/orangehrm, covering agents.md, session start (do this first, every new session), skills and commands, what this repo is and layout — the parts that matter.

orangehrm/orangehrm

Instructions file

Claude Code instructions for orangehrm/orangehrm, a project described as: OrangeHRM is a comprehensive Human Resource Management (HRM) System that captures all the essential functionalities required for any enterprise.