my-claude-devteam - 12-agent dev team for Claude Code
Drop-in pack of 12 specialized agents and 15 automation hooks that wires Claude Code into a structured P7/P9/P10 review and delivery workflow.
Tag
21 entries tagged with #agents-md.
Templates, editors, and managers for AGENTS.md and the wider .cursor/.codex/.claude config sprawl.
Drop-in pack of 12 specialized agents and 15 automation hooks that wires Claude Code into a structured P7/P9/P10 review and delivery workflow.
Persistent plan-mode for coding agents: agents propose a typed English contract (paths, MUST/SHOULD/MAY behaviors, non-goals), you approve, and every future session reads it before coding.
Single config that follows you across every project and session: curated writing/routing/skills, plus a destructive-command guard for Claude Code, Codex, and friends.
CLI that continuously syncs codebase-tailored agent skills, MCP servers, and config files between Claude Code, Cursor, and Codex with one command.
Design-system skill pack that gives agentic CLIs a shared vocabulary for components, tokens, and design.md files so generated UI stays internally consistent.
Drop-in style guide for Claude Code, Codex, Copilot, Cursor, and Aider that makes their prose and commit messages read like a senior engineer instead of an LLM.
Structured expertise files that live in git and accumulate over time, giving any coding agent a persistent set of project-specific lessons learned.
Project initializer for Claude Code that sets up security guardrails, spec-driven structure, and AI-native conventions out of the box. Targets teams who want a consistent starting layout.
Pack of reusable skills for Codex and compatible coding agents covering PRD writing, code review, and implementation review. Drop-in skill files following the skills.sh convention.
Tauri desktop app that organizes, syncs, and shares skills across Claude Code, Codex, OpenCode, and other AI tools. React 19 frontend with a Rust core.
CLI that converts and syncs project rules, skills, and MCP configs across Claude Code, Cursor, Copilot, and other AI coding agents from a single source of truth.
Library of professional slash commands for Claude Code covering code review, feature scaffolding, security audits, and architectural analysis. Drop-in workflow recipes.
Structured spec-driven workflow that forces Claude Code through a Plan-Apply-Unify cycle to favor quality over raw output speed. Aimed at non-vibe coding sessions.
Toolkit for generating production-ready Claude Skills, custom slash commands, and prompt templates from structured templates, with workflow integration helpers.
Personal Claude Code and Codex setup with battle-tested skills, hooks, slash commands, sub-agents, and MCP servers. Useful as a starting template.
Open-source marketplace with 340 plugins and 1,367 agent skills for Claude Code, plus a CCPI package manager and orchestration patterns. Bulk source for skills.
Tool to override Claude Code's system prompts, themes, spinners, input box styling, and AGENTS.md handling, plus unlock unreleased features. Works on native and npm installs.
Define multi-agent coordination, human-in-the-loop intervention points, and audit recordings in YAML, across Claude Code, Codex, and OpenCode.
Standard markdown format for capturing the intent of a feature so any agent (Claude Code, Codex, Gemini CLI, Copilot) can build it. Vendor-neutral counterpart to AGENTS.md.
Curated AGENTS.md preset that kills sycophancy, blocks drive-by refactors, and forces verification loops. Synthesizes Karpathy's principles with Cherny's Claude Code workflow.
Browse, create, and edit AGENTS.md, .cursor, .codex, and 13+ other agent files from inside Obsidian. Cross-tool config without leaving notes.