[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-73743":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":15,"stars7d":17,"stars30d":18,"stars90d":16,"forks30d":16,"starsTrendScore":19,"compositeScore":20,"rankGlobal":10,"rankLanguage":10,"license":21,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":22,"hasPages":22,"topics":24,"createdAt":10,"pushedAt":10,"updatedAt":37,"readmeContent":38,"aiSummary":39,"trendingCount":16,"starSnapshotCount":16,"syncStatus":40,"lastSyncTime":41,"discoverSource":42},73743,"cc-sdd","gotalab\u002Fcc-sdd","gotalab","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.","",null,"TypeScript",3462,256,39,15,0,44,140,45,109.23,"MIT License",false,"main",[25,26,27,28,29,30,31,32,33,34,35,36],"agent-skills","claude-code","codex","cursor","gemini-cli","github-copilot","kiro","opencode","sdd","spec-driven-development","steering","subagents","2026-06-12 04:01:11","# cc-sdd: Long-running spec-driven implementation for AI coding agents\n\n\u003C!-- npm badges -->\n[![npm version](https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fv\u002Fcc-sdd?logo=npm)](https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fcc-sdd?activeTab=readme)\n[![install size](https:\u002F\u002Fpackagephobia.com\u002Fbadge?p=cc-sdd)](https:\u002F\u002Fpackagephobia.com\u002Fresult?p=cc-sdd)\n[![license: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-MIT-green.svg)](.\u002FLICENSE)\n\n\u003Cdiv align=\"center\" style=\"font-size: 1.1rem; margin-bottom: 1rem;\">\u003Csub>\nPackage README: \u003Ca href=\".\u002Ftools\u002Fcc-sdd\u002FREADME.md\">English\u003C\u002Fa> | \u003Ca href=\".\u002Ftools\u002Fcc-sdd\u002FREADME_ja.md\">日本語\u003C\u002Fa> | \u003Ca href=\".\u002Ftools\u002Fcc-sdd\u002FREADME_zh-TW.md\">繁體中文\u003C\u002Fa>\n\u003C\u002Fsub>\u003C\u002Fdiv>\n\n## Turn approved specs into long-running autonomous implementation\n\nOne command installs an agentic SDLC workflow as Agent Skills: discovery, requirements, design, tasks, and autonomous implementation with per-task independent review. Works across 8 AI coding agents, with the same 17-skill set on each.\n\n👻 **Kiro-inspired.** Similar spec-driven, agentic SDLC style as Kiro IDE. Existing Kiro specs remain compatible and portable.\n\n## What's new in v3.0\n\ncc-sdd v3.0 is a rework around Agent Skills and long-running autonomous implementation.\n\n- **`\u002Fkiro-discovery` as the new entry point.** Discovery routes new work into one of: extend an existing spec, implement directly with no spec, create one new spec, decompose into multiple specs, or mixed decomposition. It writes `brief.md` and, when needed, `roadmap.md`, so you can resume a workstream without re-explaining scope.\n- **`\u002Fkiro-impl` for long-running autonomous implementation.** Each task gets a fresh implementer running TDD (RED → GREEN) behind a feature flag, an independent reviewer, and an auto-debug pass that investigates root causes in a clean context when the implementer is blocked or the reviewer rejects twice. Learnings from earlier tasks propagate forward via `## Implementation Notes` in `tasks.md`. 1 task per iteration, safe to re-run after interruption.\n- **Boundary-first spec discipline.** `design.md` now includes a File Structure Plan that drives task boundaries. Tasks carry `_Boundary:_` and `_Depends:_` annotations. Review and validation look for boundary violations, not just style issues.\n- **`\u002Fkiro-spec-batch` for multi-spec initiatives.** Turn a roadmap into multiple specs in parallel, with cross-spec review to catch contradictions, duplicated responsibilities, and interface mismatches.\n- **Agent Skills across 8 coding agents.** 17 skills per install, loaded on demand (progressive disclosure). Claude Code and Codex are stable; Cursor, Copilot, Windsurf, OpenCode, Gemini CLI, and Antigravity are in beta. No external dependencies; subagents are spawned through each platform's native primitive.\n\nFull skills-mode workflow and `\u002Fkiro-impl` internals: [Skill Reference](docs\u002Fguides\u002Fskill-reference.md).\n\nUpgrading from v1.x or v2.x? See the [Migration Guide](docs\u002Fguides\u002Fmigration-guide.md#5-v2x-to-v30).\n\n## Why cc-sdd?\n\ncc-sdd treats the spec as a contract between parts of the system, not a master command document handed to the agent. Code remains the source of truth. Specs make the boundaries between parts of the code explicit so humans and agents can work in parallel without constant synchronization.\n\nThe bet: explicit contracts at the right granularity let AI-driven development at team scale move faster, not slower. Agents write the spec, humans approve the contract at phase gates, code is what ships.\n\nBoundaries are not overhead. They are what lets you move freely inside while protecting the outside.\n\nFull rationale, trade-offs, and when-to-use \u002F when-not-to-use: [Why cc-sdd? A philosophy note](docs\u002Fguides\u002Fwhy-cc-sdd.md).\n\n## Quick Start\n\n```bash\ncd your-project\nnpx cc-sdd@latest\n```\n\nThe default installs **Claude Code Skills** with English docs. To pick another agent or language:\n\n```bash\nnpx cc-sdd@latest --codex-skills --lang ja      # Codex, Japanese\nnpx cc-sdd@latest --cursor-skills --lang zh-TW  # Cursor IDE, Traditional Chinese\n```\n\nSupports 8 AI coding agents (Claude Code and Codex stable; Cursor, Copilot, Windsurf, OpenCode, Gemini CLI, and Antigravity in beta) and 13 languages. See [Supported Agents](#supported-agents) for the full list.\n\nThen, in your agent:\n\n```bash\n\u002Fkiro-discovery \u003Cidea>\n```\n\nNot sure where to start? Start with `kiro-discovery`. It routes your request and tells you what command to run next.\n\n### Common workflows\n\n| You want to... | Skills mode |\n|---|---|\n| Start a new feature or product-sized idea | `kiro-discovery` → `kiro-spec-init` → `kiro-spec-requirements` → `kiro-spec-design` → `kiro-spec-tasks` → `kiro-impl` |\n| Extend an existing system | `kiro-steering` → `kiro-discovery` or `kiro-spec-init` → optional `kiro-validate-gap` → `kiro-spec-design` → `kiro-spec-tasks` → `kiro-impl` |\n| Break down a large initiative | `kiro-discovery` → `kiro-spec-batch` |\n| Implement a small change with no spec | `kiro-discovery` → direct implementation |\n\nLegacy `\u002Fkiro:*` command modes are still available (`--claude`, `--cursor`, etc.) but are deprecated. See the [Migration Guide](docs\u002Fguides\u002Fmigration-guide.md) for the upgrade path.\n\nFor larger approved task sets, run `kiro-impl` to start autonomous implementation with per-task subagent spawn, independent review, and auto-debug on failure.\n\n## See It In Action\n\nExample: build a new Photo Albums feature.\n\n```bash\n\u002Fkiro-discovery Photo albums with upload, tagging, and sharing\n# discovery writes brief.md (and roadmap.md when multi-spec) and suggests the next command\n\u002Fkiro-spec-init photo-albums\n\u002Fkiro-spec-requirements photo-albums\n\u002Fkiro-spec-design photo-albums\n\u002Fkiro-spec-tasks photo-albums\n\u002Fkiro-impl photo-albums\n# autonomous: fresh implementer, independent reviewer, and auto-debug per task\n```\n\nTypical spec outputs (under 10 minutes):\n\n- `requirements.md`: EARS-format requirements with acceptance criteria.\n- `design.md`: architecture with Mermaid diagrams and a File Structure Plan.\n- `tasks.md`: implementation tasks with boundaries and dependency annotations.\n\nThen `\u002Fkiro-impl` runs the tasks autonomously with TDD (RED → GREEN) behind feature flags, an independent reviewer pass, and auto-debug on failure.\n\n![Example: design.md System Flow](assets\u002Fdesign-system_flow.png)\n\n## Supported Agents\n\nAll 8 skills variants ship the same 17-skill set. The difference is how much real-world usage each platform integration has seen.\n\n| Agent | Skills mode | Stability | Legacy mode |\n|---|---|---|---|\n| **Claude Code** | `--claude-skills` | Stable | `--claude` \u002F `--claude-agent` (deprecated) |\n| **Codex** | `--codex-skills` | Stable | `--codex` (blocked) |\n| **Cursor IDE** | `--cursor-skills` | Beta | `--cursor` (deprecated) |\n| **GitHub Copilot** | `--copilot-skills` | Beta | `--copilot` (deprecated) |\n| **Windsurf IDE** | `--windsurf-skills` | Beta | `--windsurf` (deprecated) |\n| **OpenCode** | `--opencode-skills` | Beta | `--opencode` \u002F `--opencode-agent` (deprecated) |\n| **Gemini CLI** | `--gemini-skills` | Beta | `--gemini` (deprecated) |\n| **Antigravity** | `--antigravity` | Beta (experimental) | — |\n| **Qwen Code** | — | — | `--qwen` |\n\n\"Beta\" does not mean \"missing features\", the 17 skills and templates are identical across all 8 platforms. It means the platform integration (subagent spawn behavior, ergonomics, `SKILL.md` loading) has had less real-world usage than Claude Code and Codex, and edge cases may still surface. Please [report issues](https:\u002F\u002Fgithub.com\u002Fgotalab\u002Fcc-sdd\u002Fissues) if you hit any.\n\n## Advanced Installation\n\n### Skills mode (recommended)\n\n```bash\nnpx cc-sdd@latest                     # Claude Code Skills (default)\nnpx cc-sdd@latest --claude-skills     # Claude Code Skills\nnpx cc-sdd@latest --codex-skills      # Codex Skills\nnpx cc-sdd@latest --cursor-skills     # Cursor IDE Skills (beta)\nnpx cc-sdd@latest --copilot-skills    # GitHub Copilot Skills (beta)\nnpx cc-sdd@latest --windsurf-skills   # Windsurf IDE Skills (beta)\nnpx cc-sdd@latest --opencode-skills   # OpenCode Skills (beta)\nnpx cc-sdd@latest --gemini-skills     # Gemini CLI Skills (beta)\nnpx cc-sdd@latest --antigravity       # Antigravity Skills (beta, experimental)\n```\n\n### Legacy modes (deprecated)\n\n```bash\nnpx cc-sdd@latest --claude         # Claude Code commands (use --claude-skills)\nnpx cc-sdd@latest --claude-agent   # Claude Code subagents (use --claude-skills)\nnpx cc-sdd@latest --cursor         # Cursor IDE commands (use --cursor-skills)\nnpx cc-sdd@latest --copilot        # GitHub Copilot prompts (use --copilot-skills)\nnpx cc-sdd@latest --windsurf       # Windsurf IDE workflows (use --windsurf-skills)\nnpx cc-sdd@latest --opencode       # OpenCode commands (use --opencode-skills)\nnpx cc-sdd@latest --opencode-agent # OpenCode subagents (use --opencode-skills)\nnpx cc-sdd@latest --gemini         # Gemini CLI commands (use --gemini-skills)\nnpx cc-sdd@latest --codex          # Codex (blocked, use --codex-skills)\nnpx cc-sdd@latest --qwen           # Qwen Code\n```\n\n### Language\n\n```bash\nnpx cc-sdd@latest --lang ja        # Japanese\nnpx cc-sdd@latest --lang zh-TW     # Traditional Chinese\nnpx cc-sdd@latest --lang es        # Spanish\n# Supports: en, ja, zh-TW, zh, es, pt, de, fr, ru, it, ko, ar, el\n```\n\n### Advanced options\n\n```bash\n# Preview changes before applying\nnpx cc-sdd@latest --dry-run\n\n# Custom specs directory\nnpx cc-sdd@latest --kiro-dir docs\n```\n\n## Customization\n\nEdit templates and rules in `{{KIRO_DIR}}\u002Fsettings\u002F` to match your team's workflow.\n\n- `templates\u002F`: document structure for requirements, design, tasks.\n- `rules\u002F`: AI generation principles and judgment criteria.\n\nCommon use cases: PRD-style requirements, API and database schemas, approval gates, JIRA integration, domain-specific standards.\n\n[Customization Guide](docs\u002Fguides\u002Fcustomization-guide.md) has practical examples with copy-paste snippets.\n\n## Documentation\n\n| Guide | What you will learn | Links |\n|---|---|---|\n| **Skill Reference** | Skills-mode workflow, supporting skills, `\u002Fkiro-impl` subagent flow, Skills vs `--claude-agent` | [English](docs\u002Fguides\u002Fskill-reference.md) \\| [日本語](docs\u002Fguides\u002Fja\u002Fskill-reference.md) |\n| **Command Reference** | Legacy `\u002Fkiro:*` commands with detailed usage, parameters, and examples | [English](docs\u002Fguides\u002Fcommand-reference.md) \\| [日本語](docs\u002Fguides\u002Fja\u002Fcommand-reference.md) |\n| **Customization Guide** | Practical examples: PRD requirements, frontend\u002Fbackend designs, JIRA integration | [English](docs\u002Fguides\u002Fcustomization-guide.md) \\| [日本語](docs\u002Fguides\u002Fja\u002Fcustomization-guide.md) |\n| **Spec-Driven Guide** | Complete workflow methodology from requirements to implementation | [English](docs\u002Fguides\u002Fspec-driven.md) \\| [日本語](docs\u002Fguides\u002Fja\u002Fspec-driven.md) |\n| **Why cc-sdd?** | Design rationale, trade-offs, when the tool fits and when it does not | [English](docs\u002Fguides\u002Fwhy-cc-sdd.md) \\| [日本語](docs\u002Fguides\u002Fja\u002Fwhy-cc-sdd.md) |\n| **Claude Subagents** | Legacy `--claude-agent` install target and its spec-quick subagent flow | [English](docs\u002Fguides\u002Fclaude-subagents.md) \\| [日本語](docs\u002Fguides\u002Fja\u002Fclaude-subagents.md) |\n| **Migration Guide** | Upgrading from v1.x \u002F v2.x | [English](docs\u002Fguides\u002Fmigration-guide.md) \\| [日本語](docs\u002Fguides\u002Fja\u002Fmigration-guide.md) |\n\n## Related resources\n\n**Articles & presentations**\n\n- [Kiroの仕様書駆動開発プロセスをClaude Codeで徹底的に再現した](https:\u002F\u002Fzenn.dev\u002Fgotalab\u002Farticles\u002F3db0621ce3d6d2) (Zenn, Japanese)\n- [Claude Codeは仕様駆動の夢を見ない](https:\u002F\u002Fspeakerdeck.com\u002Fgotalab555\u002Fclaude-codehashi-yang-qu-dong-nomeng-wojian-nai) (Speaker Deck, Japanese)\n\n**External resources**\n\n- [Kiro IDE](https:\u002F\u002Fkiro.dev): enhanced spec management and team collaboration.\n- [Kiro's Spec Methodology](https:\u002F\u002Fkiro.dev\u002Fdocs\u002Fspecs\u002F): the original spec-driven development methodology.\n\n## License\n\nMIT License\n","cc-sdd 是一个将已批准的规范转化为长期自主实现的工具。它提供了一个最小化且可适应的SDD（Spec-Driven Development）框架，支持Claude Code、Codex、Cursor等8种AI编码代理，并赋予它们17项技能，如发现、需求分析、设计、任务分解和自主实现等。该项目特别适合需要根据具体规范进行持续开发与维护的软件项目场景，能够显著提升开发效率并保证代码质量。此外，cc-sdd还引入了边界优先的设计原则，确保各模块间职责清晰，减少接口不匹配等问题。",2,"2026-06-11 03:47:10","high_star"]