Skip to content
Back to search

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.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/gotalab--cc-sdd/badge.svg)](/listings/gotalab--cc-sdd)

HTML

<a href="/listings/gotalab--cc-sdd"><img src="/api/listings/gotalab--cc-sdd/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

cd your-project
npx cc-sdd@latest

The default installs **Claude Code Skills** with English docs. To pick another agent or language:

npx cc-sdd@latest --codex-skills --lang ja      # Codex, Japanese
npx cc-sdd@latest --cursor-skills --lang zh-TW  # Cursor IDE, Traditional Chinese

Supports 8 AI coding agents (Claude Code and Codex stable; Cursor, Copilot, Devin Local / CLI, OpenCode, Gemini CLI, and Antigravity in beta) and 14 languages. See [Supported Agents](#supported-agents) for the full list.

Then, in your agent:

/kiro-discovery <idea>

Not sure where to start? Start with `kiro-discovery`. It routes your request and tells you what command to run next.

Common workflows

| You want to... | Skills mode | |---|---| | Start a new feature or product-sized idea | `kiro-discovery` → `kiro-spec-init` → `kiro-spec-requirements` → `kiro-spec-design` → `kiro-spec-tasks` → `kiro-impl` | | Extend an existing system | `kiro-steering` → `kiro-discovery` or `kiro-spec-init` → optional `kiro-validate-gap` → `kiro-spec-design` → `kiro-spec-tasks` → `kiro-impl` | | Break down a large initiative | `kiro-discovery` → `kiro-spec-batch` | | Implement a small change with no spec | `kiro-discovery` → direct implementation |

Legacy `/kiro:*` command modes are still available (`--claude`, `--cursor`, etc.) but are deprecated. See the [Migration Guide](docs/guides/migration-guide.md) for the upgrade path.

For larger approved task sets, run `kiro-impl`. Native subagents provide per-task implementation, independent review, and auto-debug when available; otherwise the workflow runs in the main context with inline review.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 211 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # cc-sdd: Long-running spec-driven implementation for AI coding agents
  2. <!-- npm badges -->
  3. [![npm version](https://img.shields.io/npm/v/cc-sdd?logo=npm)](https://www.npmjs.com/package/cc-sdd?activeTab=readme)
  4. [![install size](https://packagephobia.com/badge?p=cc-sdd)](https://packagephobia.com/result?p=cc-sdd)
  5. [![license: MIT](https://img.shields.io/badge/license-MIT-green.svg)](./LICENSE)
  6. <div align="center" style="font-size: 1.1rem; margin-bottom: 1rem;"><sub>
  7. Package README: <a href="./tools/cc-sdd/README.md">English</a> | <a href="./tools/cc-sdd/README_ja.md">日本語</a> | <a href="./tools/cc-sdd/README_zh-TW.md">繁體中文</a>
  8. </sub></div>
  9. ## Turn approved specs into long-running autonomous implementation
  10. One command installs an agentic SDLC workflow as Agent Skills: discovery, requirements, design, tasks, and autonomous implementation with per-task independent review on hosts with native subagents. Works across 8 AI coding agents, with the same 17-skill set on each.
  11. 👻 **Kiro-inspired.** Similar spec-driven, agentic SDLC style as Kiro IDE. Existing Kiro specs remain compatible and portable.
  12. ## What's new in v3.0
  13. cc-sdd v3.0 is a rework around Agent Skills and long-running autonomous implementation.
  14. - **`/kiro-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.
  15. - **`/kiro-impl` for long-running autonomous implementation.** When native subagents are available, each task gets a fresh implementer running TDD (RED → GREEN) behind a feature flag, an independent reviewer, and an auto-debug pass when blocked or after repeated review rejection. Otherwise, implementation and review run inline. Learnings propagate via `## Implementation Notes` in `tasks.md`. Each iteration handles one task; recorded task state supports resumption after checking unfinished work and active workers.
  16. - **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.
  17. - **`/kiro-spec-batch` for multi-spec initiatives.** Turn a roadmap into multiple specs by dependency wave, in parallel when native subagents are available, with cross-spec review to catch contradictions, duplicated responsibilities, and interface mismatches.
  18. - **Agent Skills across 8 coding agents.** 17 skills per install, loaded on demand (progressive disclosure). Claude Code and Codex are stable; Cursor, Copilot, Devin Local / CLI, OpenCode, Gemini CLI, and Antigravity are in beta. Native subagents are used when available; hosts without them execute sequentially with inline review.
  19. Full skills-mode workflow and `/kiro-impl` internals: [Skill Reference](docs/guides/skill-reference.md).
  20. Upgrading from v1.x or v2.x? See the [Migration Guide](docs/guides/migration-guide.md#5-v2x-to-v30).
  21. ## Why cc-sdd?
  22. cc-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.
  23. The 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.
  24. Boundaries are not overhead. They are what lets you move freely inside while protecting the outside.
  25. Full rationale, trade-offs, and when-to-use / when-not-to-use: [Why cc-sdd? A philosophy note](docs/guides/why-cc-sdd.md).
  26. ## Quick Start
  27. ```bash
  28. cd your-project
  29. npx cc-sdd@latest
  30. ```
  31. The default installs **Claude Code Skills** with English docs. To pick another agent or language:
  32. ```bash
  33. npx cc-sdd@latest --codex-skills --lang ja # Codex, Japanese
  34. npx cc-sdd@latest --cursor-skills --lang zh-TW # Cursor IDE, Traditional Chinese
  35. ```
  36. Supports 8 AI coding agents (Claude Code and Codex stable; Cursor, Copilot, Devin Local / CLI, OpenCode, Gemini CLI, and Antigravity in beta) and 14 languages. See [Supported Agents](#supported-agents) for the full list.
  37. Then, in your agent:
  38. ```bash
  39. /kiro-discovery <idea>
  40. ```
  41. Not sure where to start? Start with `kiro-discovery`. It routes your request and tells you what command to run next.
  42. ### Common workflows
  43. | You want to... | Skills mode |
  44. |---|---|
  45. | Start a new feature or product-sized idea | `kiro-discovery` → `kiro-spec-init` → `kiro-spec-requirements` → `kiro-spec-design` → `kiro-spec-tasks` → `kiro-impl` |
  46. | Extend an existing system | `kiro-steering` → `kiro-discovery` or `kiro-spec-init` → optional `kiro-validate-gap` → `kiro-spec-design` → `kiro-spec-tasks` → `kiro-impl` |
  47. | Break down a large initiative | `kiro-discovery` → `kiro-spec-batch` |
  48. | Implement a small change with no spec | `kiro-discovery` → direct implementation |
  49. Legacy `/kiro:*` command modes are still available (`--claude`, `--cursor`, etc.) but are deprecated. See the [Migration Guide](docs/guides/migration-guide.md) for the upgrade path.
  50. For larger approved task sets, run `kiro-impl`. Native subagents provide per-task implementation, independent review, and auto-debug when available; otherwise the workflow runs in the main context with inline review.
  51. ## See It In Action
  52. Example: build a new Photo Albums feature.
  53. ```bash
  54. /kiro-discovery Photo albums with upload, tagging, and sharing
  55. # discovery writes brief.md (and roadmap.md when multi-spec) and suggests the next command
  56. /kiro-spec-init photo-albums
  57. /kiro-spec-requirements photo-albums
  58. /kiro-spec-design photo-albums
  59. /kiro-spec-tasks photo-albums
  60. /kiro-impl photo-albums
  61. # autonomous: fresh implementer/reviewer when subagents are available; inline otherwise
  62. ```
  63. Typical spec outputs (under 10 minutes):
  64. - `requirements.md`: EARS-format requirements with acceptance criteria.
  65. - `design.md`: architecture with Mermaid diagrams and a File Structure Plan.
  66. - `tasks.md`: implementation tasks with boundaries and dependency annotations.
  67. On a host with native subagents, `/kiro-impl` runs tasks with TDD (RED → GREEN) behind feature flags, independent review, and auto-debug on failure. Inline execution follows the same review protocol in the main context.
  68. ![Example: design.md System Flow](assets/design-system_flow.png)
  69. ## Supported Agents
  70. Eight current integrations ship 17 skills each; the deprecated Cascade variant is retained for migration. Invocation, native subagent availability, and independent review depend on the execution surface and configuration.
  71. | Agent | Skills mode | Stability | Legacy mode |
  72. |---|---|---|---|
  73. | **Claude Code** | `--claude-skills` | Stable | `--claude` / `--claude-agent` (deprecated) |
  74. | **Codex** | `--codex-skills` | Stable | `--codex` (blocked) |
  75. | **Cursor IDE** | `--cursor-skills` | Beta | `--cursor` (deprecated) |
  76. | **GitHub Copilot** | `--copilot-skills` | Beta | `--copilot` (deprecated) |
  77. | **Devin Local / CLI** | `--devin` / `--devin-skills` | Beta | — |
  78. | **Windsurf / Cascade (legacy)** | `--windsurf-skills` | Deprecated | `--windsurf` (deprecated) |
  79. | **OpenCode** | `--opencode-skills` | Beta | `--opencode` / `--opencode-agent` (deprecated) |
  80. | **Gemini CLI** | `--gemini-skills` | Beta | `--gemini` (deprecated) |
  81. | **Antigravity** | `--antigravity` | Beta | — |
  82. | **Qwen Code** | — | — | `--qwen` |
  83. Stability describes integration maturity. Installing 17 skills does not verify that a host can run the full autonomous loop. Use `--devin` for Devin Local in Devin Desktop or Devin CLI. Installer checks and CLI skill discovery pass for the new beta adapter; authenticated task execution is still unverified. The Windsurf flags are deprecated Cascade migration options; Devin Cloud is outside the new adapter’s scope. Copilot subagents depend on the client. See [Agent compatibility](./docs/guides/agent-compatibility.md) for supported surfaces and Antigravity migration guidance.
  84. ## Advanced Installation
  85. ### Skills mode (recommended)
  86. ```bash
  87. npx cc-sdd@latest # Claude Code Skills (default)
  88. npx cc-sdd@latest --claude-skills # Claude Code Skills
  89. npx cc-sdd@latest --codex-skills # Codex Skills
  90. npx cc-sdd@latest --cursor-skills # Cursor IDE Skills (beta)
  91. npx cc-sdd@latest --copilot-skills # GitHub Copilot Skills (beta)
  92. npx cc-sdd@latest --devin # Devin Local / CLI Skills (beta)
  93. npx cc-sdd@latest --opencode-skills # OpenCode Skills (beta)
  94. npx cc-sdd@latest --gemini-skills # Gemini CLI Skills (beta)
  95. npx cc-sdd@latest --antigravity # Antigravity Skills (beta)
  96. ```
  97. ### Legacy modes (deprecated)
  98. ```bash
  99. npx cc-sdd@latest --claude # Claude Code commands (use --claude-skills)
  100. npx cc-sdd@latest --claude-agent # Claude Code subagents (use --claude-skills)
  101. npx cc-sdd@latest --cursor # Cursor IDE commands (use --cursor-skills)
  102. npx cc-sdd@latest --copilot # GitHub Copilot prompts (use --copilot-skills)
  103. npx cc-sdd@latest --windsurf # Legacy Cascade workflows (migrate to --devin)
  104. npx cc-sdd@latest --windsurf-skills # Deprecated Cascade skills; migrate to --devin
  105. npx cc-sdd@latest --opencode # OpenCode commands (use --opencode-skills)
  106. npx cc-sdd@latest --opencode-agent # OpenCode subagents (use --opencode-skills)
  107. npx cc-sdd@latest --gemini # Gemini CLI commands (use --gemini-skills)
  108. npx cc-sdd@latest --codex # Codex (blocked, use --codex-skills)
  109. npx cc-sdd@latest --qwen # Qwen Code
  110. ```
  111. ### Language
  112. ```bash
  113. npx cc-sdd@latest --lang ja # Japanese
  114. npx cc-sdd@latest --lang zh-TW # Traditional Chinese
  115. npx cc-sdd@latest --lang es # Spanish
  116. # Supports: en, ja, zh-TW, zh, es, pt, de, fr, ru, it, ko, ar, el, vi
  117. ```
  118. ### Advanced options
  119. ```bash
  120. # Preview changes before applying
  121. npx cc-sdd@latest --dry-run
  122. # Custom specs directory
  123. npx cc-sdd@latest --kiro-dir docs
  124. ```
  125. ## Customization
  126. Edit templates and rules in `{{KIRO_DIR}}/settings/` to match your team's workflow.
  127. - `templates/`: document structure for requirements, design, tasks.
  128. - `rules/`: AI generation principles and judgment criteria.
  129. Common use cases: PRD-style requirements, API and database schemas, approval gates, JIRA integration, domain-specific standards.
  130. [Customization Guide](docs/guides/customization-guide.md) has practical examples with copy-paste snippets.
  131. ## Documentation
  132. | Guide | What you will learn | Links |
  133. |---|---|---|
  134. | **Skill Reference** | Skills-mode workflow, supporting skills, `/kiro-impl` subagent flow, Skills vs `--claude-agent` | [English](docs/guides/skill-reference.md) \| [日本語](docs/guides/ja/skill-reference.md) |
  135. | **Command Reference** | Legacy `/kiro:*` commands with detailed usage, parameters, and examples | [English](docs/guides/command-reference.md) \| [日本語](docs/guides/ja/command-reference.md) |
  136. | **Customization Guide** | Practical examples: PRD requirements, frontend/backend designs, JIRA integration | [English](docs/guides/customization-guide.md) \| [日本語](docs/guides/ja/customization-guide.md) |
  137. | **Spec-Driven Guide** | Complete workflow methodology from requirements to implementation | [English](docs/guides/spec-driven.md) \| [日本語](docs/guides/ja/spec-driven.md) |
  138. | **Why cc-sdd?** | Design rationale, trade-offs, when the tool fits and when it does not | [English](docs/guides/why-cc-sdd.md) \| [日本語](docs/guides/ja/why-cc-sdd.md) |
  139. | **Claude Subagents** | Legacy `--claude-agent` install target and its spec-quick subagent flow | [English](docs/guides/claude-subagents.md) \| [日本語](docs/guides/ja/claude-subagents.md) |
  140. | **Migration Guide** | Upgrading from v1.x / v2.x | [English](docs/guides/migration-guide.md) \| [日本語](docs/guides/ja/migration-guide.md) |
  141. ## Related resources
  142. **Articles & presentations**
  143. - [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://zenn.dev/gotalab/articles/3db0621ce3d6d2) (Zenn, Japanese)
  144. - [Claude Codeは仕様駆動の夢を見ない](https://speakerdeck.com/gotalab555/claude-codehashi-yang-qu-dong-nomeng-wojian-nai) (Speaker Deck, Japanese)
  145. **External resources**
  146. - [Kiro IDE](https://kiro.dev): enhanced spec management and team collaboration.
  147. - [Kiro's Spec Methodology](https://kiro.dev/docs/specs/): the original spec-driven development methodology.
  148. ## License
  149. MIT License

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.