cc-sdd 🤖 Agent Open source
Spec-driven development harness with Agent Skills and long-running autonomous implementation
- GitHub stars
- 3.7k
- Stars this week
- +14
- Forks
- 291
- Licence
- MIT
- Last push
- 2026-09-23
- Maintainer
- gotalab
npx cc-sdd@latestThird-party subagents & agents run with your permissions. Read the source before installing, and prefer pinned versions.
Works with
About cc-sdd
What it does
cc-sdd installs a spec-driven development workflow as Agent Skills, turning approved specifications into long-running autonomous implementation. One command sets up an agentic SDLC: discovery, requirements, design, tasks, and then autonomous implementation with per-task independent review. It treats the spec as a contract that makes boundaries between parts of the system explicit, so humans approve at phase gates while the agent carries tasks through. The approach is inspired by Kiro IDE, and existing Kiro specs remain compatible.
What is inside
A set of seventeen skills, identical across every supported agent and loaded on demand. The entry point /kiro-discovery routes new work into extending a spec, implementing directly, creating one spec, or decomposing into several. Spec skills produce EARS-format requirements.md, a design.md with Mermaid diagrams and a File Structure Plan, and a tasks.md with boundary and dependency annotations. /kiro-impl then runs tasks autonomously with test-driven RED to GREEN cycles behind feature flags, an independent reviewer pass, and an auto-debug pass that investigates root causes in a clean context when a task is blocked. /kiro-spec-batch turns a roadmap into multiple specs with cross-spec review. Templates and rules under a settings directory are editable per team.
Works with
Claude Code and Codex (stable), plus Cursor, GitHub Copilot, Windsurf, OpenCode, Gemini CLI, and Google Antigravity (beta). Thirteen document languages are supported.
How to install
npx cc-sdd@latest
Maintenance and safety
MIT licensed and active. The installer writes skills and templates into your project; a --dry-run flag previews changes first. Subagents are spawned through each platform's native mechanism, with no external service dependencies. Autonomous implementation edits code, so review the phase gates.
Who should use it
Teams that want disciplined, spec-first development with autonomous per-task implementation and review, across more than one coding agent.
Pros
- Full SDLC from discovery to autonomous per-task TDD with independent review
- Same 17-skill set installs across eight coding agents
Cons
- Only Claude Code and Codex are stable; other platforms are beta
- Autonomous implementation edits code and needs gate review
Similar subagents & agents
All agent workflows & frameworks →Spec Kit 🤖 AgentFree
GitHub's toolkit for spec-driven development with AI coding agents
Task Master 🤖 AgentFree
AI task management that turns a PRD into tasks your coding agent works through
Fast Agent 🤖 AgentOpen source
Python framework for building, orchestrating and evaluating MCP-native AI agents
OpenSpec 🤖 AgentFree
Lightweight spec-driven development: agree on changes before the agent codes
CC Safety Net 🤖 AgentOpen source
Pre-execution guard that blocks destructive commands and secret access for coding agents
BMAD Method 🤖 AgentFree
Agile AI-driven development with analyst, PM, architect, developer and UX agents