Turn approved specs into long-running autonomous implementation. A minimal, adaptable SDD harness with Agent Skills for Claude Code, Codex, Cursor, Copilot, Windsurf, OpenCode, Gemini CLI, and Antigravity.
cc-sdd is a spec-driven development harness that installs 17 Agent Skills into AI coding environments via a single `npx cc-sdd@latest` command. It structures software delivery around a defined phase sequence: discovery, requirements, design, task breakdown, and autonomous implementation. The entry point skill, `/kiro-discovery`, analyzes an idea and routes it into the appropriate workflow, writing `brief.md` and optionally `roadmap.md` so work can resume without re-explaining scope. The `/kiro-impl` skill then drives long-running autonomous implementation where each task receives a dedicated implementer subagent running test-driven development (RED to GREEN) behind a feature flag, an independent reviewer subagent, and an auto-debug pass when the implementer is blocked or rejected twice. The tool targets Claude Code as its stable primary integration, with Codex also stable and six others including Cursor, Copilot, and Gemini CLI in beta. A standout structural detail is that `design.md` includes a File Structure Plan that enforces explicit task boundaries via `_Boundary:_` and `_Depends:_` annotations. Development teams and solo engineers adopting AI-assisted workflows benefit most, particularly those managing multi-spec initiatives or parallel workstreams.
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
git clone https://github.com/gotalab/cc-sdd && cp cc-sdd/*.md ~/.claude/agents/18 items in this repository
Add or extend coding-agent support in cc-sdd by executing the SOP in docs/cc-sdd/sop-new-agent.md end-to-end. Use when introducing a new agent, adding a subagent-capable variant, or evaluating migration of an existing supported agent to skills-based templates.
Investigate implementation failures using root-cause-first debugging. Use when an implementer is blocked, verification fails, or repeated remediation does not converge.
Entry point for new work. Determines the best action path or work decomposition (update existing spec, create new spec, mixed decomposition, or no spec needed) and refines ideas through structured dialogue.
Implement approved tasks using TDD with subagent dispatch. Runs all pending tasks autonomously or selected tasks manually.
Review a task implementation against approved specs, task boundaries, and verification evidence. Use after an implementer finishes a task, after remediation, or before accepting a task as complete.
Create complete specs (requirements, design, tasks) for all features in roadmap.md using parallel sub-agent dispatch by dependency wave.
Validate feature-level integration after all tasks are implemented. Checks cross-task consistency, full test suite, and overall spec coverage.
Verify completion and success claims with fresh evidence. Use before claiming a task is complete, a fix works, tests pass, or a feature is ready for GO.
Subagents overview
What people ask about cc-sdd
What is gotalab/cc-sdd?
+
gotalab/cc-sdd is subagents for the Claude AI ecosystem. Turn approved specs into long-running autonomous implementation. A minimal, adaptable SDD harness with Agent Skills for Claude Code, Codex, Cursor, Copilot, Windsurf, OpenCode, Gemini CLI, and Antigravity. It has 3.5k GitHub stars and was last updated 23d ago.
How do I install cc-sdd?
+
You can install cc-sdd by cloning the repository (https://github.com/gotalab/cc-sdd) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is gotalab/cc-sdd safe to use?
+
Our security agent has analyzed gotalab/cc-sdd and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains gotalab/cc-sdd?
+
gotalab/cc-sdd is maintained by gotalab. The last recorded GitHub activity is from 23d ago, with 20 open issues.
Are there alternatives to cc-sdd?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy cc-sdd to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/gotalab-cc-sdd)<a href="https://claudewave.com/repo/gotalab-cc-sdd"><img src="https://claudewave.com/api/badge/gotalab-cc-sdd" alt="Featured on ClaudeWave: gotalab/cc-sdd" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Production-ready platform for agentic workflow development.
The agent engineering platform.
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.