t800-start
97Command
A single command for creating or updating development helpers such as rules, skills, commands, subagents, and hooks. It can target a plugin, the current project, or shared settings.
1,590 tagged agents, measured the same way as everything else here.
Browse within: agentic 158gemini 144agents-md 139claude-agent-sdk 133openrouter 133ai-tools 131Autonomous 125ai-governance 124ai-skills 124embodied-ai 121Workflows 115devops-tools 115fantasy-rpg 115hermes-agent 115
Command
A single command for creating or updating development helpers such as rules, skills, commands, subagents, and hooks. It can target a plugin, the current project, or shared settings.
Command
NEVER workspace/[name].md (wrong) ALWAYS workspace/company/[name].md (correct).
Command
Create a feature branch with sequential or timestamp numbering.
Command Claude Code
Pick an Outfit (agent persona) to wear in this project.
Command
Audit agent configuration files for security vulnerabilities and misconfigurations. Classifies findings as P0 or P1.
Command
Run local code review with openlens.
Command Claude Code
Define the product — brief → personas → journeys → feature map, with a gate at each stage.
Command Claude Code
Before executing this command, CONFIRM these files exist and are readable.
luca-mastrostefano/agent-native-setup
Command Claude Code
Extract a complete profile from an existing repo (runs the extract-profile skill).
Command Claude Code
Mines an external agent/skill collection and curates keepers into this repo's catalog (agents/, skills/, README links). Use when importing, adapting, or evaluating external agents, skills, or commands for agenticat.
CyrusZhang23/AI-learning-by-claude-code
Command Claude Code
Read every layer-.md file under labs/ and show a concise list of all layers (Layer 0 placement + Layers 1–7), each with.
Command Codex
Resolve reviewer feedback - from GitHub PRs, chat, or any reviewer.
Command
Perform trend, sentiment, and entity analysis.
Command Claude Code
Run a MultiAgentRuntime swarm in file mode — local journal at .runtime/conversation.md, no network.
Command Claude Code
Run the project test suite and report results.
Command
One-shot LLM-authored OpenExpertise SOP. Drives oe ultra and reports the result.
Command
Deploy the current branch to staging.
Command Claude Code
Claim a card before working on it.
Command
Author a concrete blueprint for a slug — what we wanted (intent) + what we're building now (classes, interfaces, dependencies, module relationships, build order) with Mermaid UML. Optional, after /draft-plan. Presents the draft for accept/edit/reject, then writes to .claude/docs/ /v .md and the Obsidian vault.
Command Claude Code
Install Pi Verifier Agent — prerequisites, deps, persona validation, and provider env.
andiupn/andy-universal-agent-rules
Command Cursor
Scan this chat session and save important learnings to the knowledge base.
Command Claude Code
Scaffold and implement a new tool for VisionAgent.
Command
Configure the local OpenDexter proxy and verify its hosted-only seven-tool surface.
Cyvid7-Darus10/claude-code-config
Command
Quick reference for ponytail levels, skills, and commands.
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: