Building agents

NVIDIA/cuopt

Skill Claude CodeCodex ✓ vendor

After solving a non-trivial problem, detect generalizable learnings and propose skill updates. Always active — applies to every interaction.

fy-agent/fyagent

Skill Claude CodeCodex

Understand and customize the local Trellis architecture inside a user project. Use when modifying .trellis plus platform hooks, settings, agents, skills, commands, prompts, workflows, the channel runtime (trellis channel), bundled runtime agents under .trellis/agents/, selectable workflow templates, registry-backed…

agenmod/immortal-skill

Skill Claude CodeCodex

A framework for building a digital version of a person from conversations, social-media material, and documents. It extracts working methods, interaction patterns, memories, and personality into a reusable agent skill, with templates for different relationships.

AgriciDaniel/banana-claude

Instructions file Claude Code

Instructions for AgriciDaniel/banana-claude, covering banana claude development contract, current architecture, provider state, verified 2026-08-29, development boundaries and python support.

ArcadeAI/arcade-mcp

Instructions file Claude Code

Claude Code instructions for ArcadeAI/arcade-mcp, covering claude.md, what this is, commands, library dependency graph and versioning rules.

tong-io/tongflow

Instructions file Claude Code

Claude Code instructions for tong-io/tongflow, covering claude.md, directory conventions, contract enforcement: compile-time only, plugin authoring rules and registering an official plugin.

freekmurze/dotfiles

Skill Claude CodeCodex

Working with Conductor (conductor.build), the parallel-agent app. Creating local and cloud workspaces, the conductor CLI and public API, auth, sessions and messages, deep links, settings and setup scripts, environment variables, and writing briefs for handed-off agents. Use when asked to open, create, rename, archive…

jarrodwatts/claude-delegator

Instructions file Claude Code

Instructions for jarrodwatts/claude-delegator, covering claude.md, what this is, development commands, test plugin locally (loads from working directory) and run setup to test installation flow.

jezweb/claude-skills

Instructions file Claude Code

Claude Code instructions for jezweb/claude-skills, covering claude skills, philosophy, directory structure, plugin anatomy (anthropic spec) and adding a new plugin.

DannyMac180/fable-advisor

Plugin Claude Code

Bundles 1 skill, 3 agents · 565 tokens together

Run your session on Fable 5.1 as a full-time architect: it writes specs and verdicts and picks a reasoning effort per task, GPT-5.6 Luna (via Codex) does the routine typing, GPT-5.6 Sol takes the high-complexity one-offs — and Fable 5.1 reviews every deliverable before it ships.

Agent-Field/SWE-AF

Skill Claude CodeCodex

Autonomous engineering team runtime — one API call spins up coordinated AI agents to scope, build, and ship software.

Spielewoy/autoprompt-skill

Skill Claude Code

Explicit-only useful-first orchestration. Invoke only when the user names autoprompt - typed as /autoprompt or in plain language such as "act in autoprompt mode" - to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Do not infer invocation from…

anthropics/launch-your-agent

Skill Claude Code ✓ vendor

Close out (or revisit) a Claude Managed Agent build — refresh the overview page, recap every primitive the founder now owns, show the run log and live status, suggest 1–2 tailored next upgrades, and sweep hygiene (sessions archived, key only in .env, no literal dates in deployment kickoffs). Use when the founder says…

jiweiyeah/Skills-Manager

Skill Claude CodeCodex

Drive the Skills Manager CLI (skm) to initialize the hub, adopt unmanaged skills, list/enable/disable skills per AI tool, and doctor/fix symlink sync. Use whenever the user or an agent needs to manage skills from a terminal, SSH session, CI job, or headless machine; when a skill is missing in Claude Code, Codex…

activeagents/activeagent

Agent Claude Code

System-level messages that guide agent behavior, personality, capabilities, and tool usage. The agent's operating manual for every interaction.

psi-oss/get-physics-done

Agent Claude Code

Default writable implementation agent for bounded GPD research execution. Handles PLAN.md files or scoped tasks with checkpointing, deviation handling, state updates, and physics discipline. Spawned by execute-phase, quick, and parameter-sweep workflows.

russelleNVy/three-man-team

Instructions file Claude Code

Instructions for russelleNVy/three-man-team, covering three man team — session router, token rules — always active, session start — every role and reference files — on demand only.

LearnPrompt/luban-skill

Skill Claude CodeCodex

A workshop guide for improving an existing AI skill before publishing it for others to use. It evaluates the skill’s purpose, compares it with similar tools, tests its real output, and refines it through measured revisions.

Kulaxyz/self-learning-skills

Cursor rule Cursor

Self-learning — recognize a hard-won "golden path" during a task and persist it as a reusable Cursor rule so the next session already knows it. Applies whenever a task succeeds only after several tries, uses non-obvious tooling or commands, reveals project facts (how to reach the DB, where creds/env vars live, how to…

MeisnerDan/mission-control

Instructions file Claude Code

Claude Code instructions for MeisnerDan/mission-control, covering solo entrepreneur workspace — agent operations manual, quick start for ai agents, workspace map, data schema reference and tasks.json — { "tasks": task[] }.

xiaotianfotos/homerail

Skill Codex

Run, monitor, inspect, debug, and author HomeRail DAG workflows through the CLI or Manager Tools, including supervised multi-Actor runs with stable live Surfaces and later per-Actor follow-ups. Use when: (1) listing templates, (2) starting a DAG run, (3) supervising or watching a run, (4) inspecting chats, handoffs…

ccplugins/awesome-claude-code-plugins

Plugin Claude Code

Lists 48 plugins

Plugin marketplace listing 151 plugins: context-memory, documentation-generator, lyra, analyze-codebase, update-claudemd.

SethGammon/Citadel

Instructions file CodexOpenCode

AGENTS.md instructions for SethGammon/Citadel, covering codex harness, what this is, key conventions, testing and review guidelines.

luongnv89/asm

Skill Claude Code

Create, improve, evaluate, benchmark skills. Use when authoring a new skill, updating an existing one, running evals, or optimizing a skill's description for triggering. Don't use for invoking skills, writing prose, or scaffolding Python projects.