# gotalab/cc-sdd

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.

Repository: https://github.com/gotalab/cc-sdd
Canonical: https://ross.abutalabs.com/products/cc-sdd
Language: TypeScript
License: MIT
License Family: permissive
Topics: steering, kiro, spec-driven-development, cursor, claude-code, codex, gemini-cli, github-copilot, subagents, opencode, agent-skills, sdd
Last push: 2026-05-20T08:45:14+00:00

## Health v2 (maintenance only)
Score: 71/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 83, release rhythm 79, longevity 29
- inputs: {"age_days": 412, "days_push": 105, "days_rel": 142, "gap_med": 2, "n_releases_24m": 18}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3640, forks 279 (observed 2026-08-28T04:08:12.810100+00:00)

## What it is
cc-sdd is an npm-distributed harness that installs a spec-driven development (SDD) workflow as 17 Agent Skills for AI coding agents like Claude Code, Codex, Cursor, Copilot, Windsurf, OpenCode, Gemini CLI, and Antigravity. It turns approved specs into long-running autonomous implementation with per-task TDD, independent review, and auto-debugging, inspired by Kiro IDE's spec-driven style.

## Use cases
- run spec-driven development with AI coding agents
- turn approved specs into autonomous implementation
- install agentic SDLC workflow skills for Claude Code
- decompose a roadmap into multiple specs in parallel
- run long-running TDD implementation with per-task review
- migrate existing Kiro specs to other AI coding agents
- orchestrate subagents for implementer and reviewer roles

## When to choose
- you use Claude Code, Codex, Cursor, or another supported AI coding agent and want a structured spec-to-implementation workflow
- you want Kiro-style spec-driven development without switching IDEs
- you need long-running autonomous task execution with independent review and auto-debugging
- you manage multi-spec initiatives and want cross-spec contradiction checks

## When to avoid
- you prefer ad-hoc prompting over structured spec-driven workflows
- you don't use any of the 8 supported AI coding agents
- you need support for agents beyond the beta-supported list like Cursor or Gemini CLI in production-critical settings
- you want a fully hands-off code generator without spec authoring and review discipline

## Facets
- artifact type: cli-tool
- maturity: active
- function: agent-framework, prompt-engineering, workflow-automation, cli, developer-tools
- domain: developer-tools
- platform: cli, cross-platform
- tags: spec-driven-development, agent-skills, kiro, claude-code, codex, cursor, gemini-cli, github-copilot, windsurf, opencode, subagents, tdd, agentic-sdlc, sdd, steering, ai-agents, automation, command-line, nodejs

## Member repositories
- gotalab/cc-sdd (main) score 71

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:12.810100+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:31:47.760542+00:00, confidence not recorded.
  - readme: https://github.com/gotalab/cc-sdd (fetched 2026-08-28T04:08:12.810100+00:00, sha 7b1394f7ff61)
  - registry_npm: https://registry.npmjs.org/cc-sdd (fetched 2026-08-29T09:26:20.400657+00:00, sha 0c9baf404a57)
- Data as of 2026-08-30T08:39:29.467469+00:00.