[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-11203":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":9,"totalLinesOfCode":9,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":9,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":9,"rankLanguage":9,"license":9,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":22,"hasPages":22,"topics":9,"createdAt":9,"pushedAt":9,"updatedAt":24,"readmeContent":25,"aiSummary":26,"trendingCount":16,"starSnapshotCount":16,"syncStatus":27,"lastSyncTime":28,"discoverSource":29},11203,"aidlc-workflows","awslabs\u002Faidlc-workflows","awslabs","AI-Driven Life Cycle (AI-DLC) adaptive workflow steering rules for AI coding agents",null,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Faidlc-workflows","Python",2848,466,46,27,0,101,285,885,303,30.01,false,"main","2026-06-12 02:02:30","# AI-DLC (AI-Driven Development Life Cycle)\n\n> [!IMPORTANT]\n> Generative AI can make mistakes. You should consider reviewing all output and costs generated by your chosen AI model and agentic coding assistant. See [AWS Responsible AI Policy](https:\u002F\u002Faws.amazon.com\u002Fai\u002Fresponsible-ai\u002Fpolicy\u002F).\n\n\u003C!-- TODO: Replace this Amplify URL with a permanent\u002Fstable URL when available -->\nAI-DLC is an intelligent software development workflow that adapts to your needs, maintains quality standards, and keeps you in control of the process. For learning more about AI-DLC Methodology, read this [blog](https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fdevops\u002Fai-driven-development-life-cycle\u002F) and the [Method Definition Paper](https:\u002F\u002Fprod.d13rzhkk8cj2z0.amplifyapp.com\u002F) referred in it.\n\n## Table of Contents\n\n- [Common](#common)\n- [Platform-Specific Setup](#platform-specific-setup)\n- [Usage](#usage)\n- [Three-Phase Adaptive Workflow](#three-phase-adaptive-workflow)\n- [Key Features](#key-features)\n- [Extensions](#extensions)\n- [Tenets](#tenets)\n- [Prerequisites](#prerequisites)\n- [Troubleshooting](#troubleshooting)\n- [Version Control Recommendations](#version-control-recommendations)\n- [Additional Resources](#additional-resources)\n- [Generated aidlc-docs\u002F Reference](#generated-aidlc-docs-reference)\n- [Experimental: AI-Assisted Setup (Release Download)](#experimental-ai-assisted-setup-release-download)\n- [Contributing](#contributing)\n- [License](#license)\n\n---\n\n## Common\n\n1. Download the latest release zip file named `ai-dlc-rules-v\u003Crelease-number>.zip` from the [Releases page](..\u002F..\u002Freleases\u002Flatest) to a folder **outside** your project directory (e.g., `~\u002FDownloads`).\n2. Extract the zip. It contains an `aidlc-rules\u002F` folder with two subdirectories:\n   - `aws-aidlc-rules\u002F` — the core AI-DLC workflow rules\n   - `aws-aidlc-rule-details\u002F` — detailed rules conditionally referenced by the core rules\n3. Follow the setup instructions for your coding agent and platform below.\n\n---\n\n## Platform-Specific Setup\n\n- [Kiro](#kiro)\n- [Amazon Q Developer IDE Plugin](#amazon-q-developer-ide-pluginextension)\n- [Cursor IDE](#cursor-ide)\n- [Cline](#cline)\n- [Claude Code](#claude-code)\n- [GitHub Copilot](#github-copilot)\n- [OpenAI Codex](#openai-codex)\n- [Other Agents](#other-agents)\n\n---\n\n### Kiro\n\nAI-DLC uses [Kiro Steering Files](https:\u002F\u002Fkiro.dev\u002Fdocs\u002Fcli\u002Fsteering\u002F) within your project workspace.  \n\nThe commands below assume you extracted the zip to your `Downloads` folder. If you used a different location, replace `Downloads` with your actual folder path.\n\nOn macOS\u002FLinux:\n\n```bash\nmkdir -p .kiro\u002Fsteering\ncp -R ~\u002FDownloads\u002Faidlc-rules\u002Faws-aidlc-rules .kiro\u002Fsteering\u002F\ncp -R ~\u002FDownloads\u002Faidlc-rules\u002Faws-aidlc-rule-details .kiro\u002F\n```\n\nOn Windows (PowerShell):\n\n```powershell\nNew-Item -ItemType Directory -Force -Path \".kiro\\steering\"\nCopy-Item -Recurse \"$env:USERPROFILE\\Downloads\\aidlc-rules\\aws-aidlc-rules\" \".kiro\\steering\\\"\nCopy-Item -Recurse \"$env:USERPROFILE\\Downloads\\aidlc-rules\\aws-aidlc-rule-details\" \".kiro\\\"\n```\n\nOn Windows (CMD):\n\n```cmd\nmkdir .kiro\\steering\nxcopy %USERPROFILE%\\Downloads\\aidlc-rules\\aws-aidlc-rules .kiro\\steering\\aws-aidlc-rules\\ \u002FE \u002FI\nxcopy %USERPROFILE%\\Downloads\\aidlc-rules\\aws-aidlc-rule-details .kiro\\aws-aidlc-rule-details\\ \u002FE \u002FI\n```\n\nYour project should look like:\n\n```text\n\u003Cproject-root>\u002F\n    ├── .kiro\u002F\n    │     ├── steering\u002F\n    │     │      ├── aws-aidlc-rules\u002F\n    │     ├── aws-aidlc-rule-details\u002F\n```\n\nTo verify the rules are loaded:\n\n#### Verify in Kiro IDE\n\nOpen the steering files panel and confirm you see an entry for `core-workflow` under `Workspace` as shown in the screenshot below.\n\n\u003Cimg src=\".\u002Fassets\u002Fimages\u002Fkiro-ide-aidlc-rules-loaded.png?raw=true\" alt=\"AI-DLC Rules in Kiro IDE\" width=\"700\" height=\"450\">\n\nWe use Kiro IDE in Vibe mode to run the AI-DLC workflow. This ensures that AI-DLC workflow guides the development workflow in Kiro. At times, Kiro may nudge you to switch to spec mode. Select `No` to such prompts to stay in Vibe mode.\n\n\u003Cimg src=\".\u002Fassets\u002Fimages\u002Fkiro-sdd-nudge.png?raw=true\" alt=\"Staying in Kiro Vibe mode\" width=\"500\" height=\"175\">\n\n#### Verify in Kiro CLI\n\nRun `kiro-cli`, then `\u002Fcontext show`, and confirm entries for `.kiro\u002Fsteering\u002Faws-aidlc-rules`.\n\n\u003Cimg src=\".\u002Fassets\u002Fimages\u002Fkiro-cli-aidlc-rules-loaded.png?raw=true\" alt=\"AI-DLC Rules in Kiro CLI\" width=\"700\" height=\"660\">\n\n---\n\n### Amazon Q Developer IDE Plugin\u002FExtension\n\nAI-DLC uses [Amazon Q Rules](https:\u002F\u002Fdocs.aws.amazon.com\u002Famazonq\u002Flatest\u002Fqdeveloper-ug\u002Fcontext-project-rules.html) within your project workspace.\n\nThe commands below assume you extracted the zip to your `Downloads` folder. If you used a different location, replace `Downloads` with your actual folder path.\n\nOn macOS\u002FLinux:\n\n```bash\nmkdir -p .amazonq\u002Frules\ncp -R ~\u002FDownloads\u002Faidlc-rules\u002Faws-aidlc-rules .amazonq\u002Frules\u002F\ncp -R ~\u002FDownloads\u002Faidlc-rules\u002Faws-aidlc-rule-details .amazonq\u002F\n```\n\nOn Windows (PowerShell):\n\n```powershell\nNew-Item -ItemType Directory -Force -Path \".amazonq\\rules\"\nCopy-Item -Recurse \"$env:USERPROFILE\\Downloads\\aidlc-rules\\aws-aidlc-rules\" \".amazonq\\rules\\\"\nCopy-Item -Recurse \"$env:USERPROFILE\\Downloads\\aidlc-rules\\aws-aidlc-rule-details\" \".amazonq\\\"\n```\n\nOn Windows (CMD):\n\n```cmd\nmkdir .amazonq\\rules\nxcopy %USERPROFILE%\\Downloads\\aidlc-rules\\aws-aidlc-rules .amazonq\\rules\\aws-aidlc-rules\\ \u002FE \u002FI\nxcopy %USERPROFILE%\\Downloads\\aidlc-rules\\aws-aidlc-rule-details .amazonq\\aws-aidlc-rule-details\\ \u002FE \u002FI\n```\n\nYour project should look like:\n\n```text\n\u003Cproject-root>\u002F\n    ├── .amazonq\u002F\n    │     ├── rules\u002F\n    │     │     ├── aws-aidlc-rules\u002F\n    │     ├── aws-aidlc-rule-details\u002F\n```\n\nTo verify the rules are loaded:\n\n1. In the Amazon Q Chat window, click the `Rules` button in the lower right corner.\n2. Confirm you see entries for `.amazonq\u002Frules\u002Faws-aidlc-rules`.\n\n\u003Cimg src=\".\u002Fassets\u002Fimages\u002Fq-ide-aidlc-rules-loaded.png?raw=true\" alt=\"AI-DLC Rules in Q Developer IDE plugin\" width=\"700\" height=\"400\">\n\n---\n\n### Cursor IDE\n\nAI-DLC uses [Cursor Rules](https:\u002F\u002Fcursor.com\u002Fdocs\u002Fcontext\u002Frules) to implement its intelligent workflow.\n\nThe commands below assume you extracted the zip to your `Downloads` folder. If you used a different location, replace `Downloads` with your actual folder path.\n\n#### Option 1: Project Rules (Recommended)\n\n**Unix\u002FLinux\u002FmacOS:**\n\n```bash\nmkdir -p .cursor\u002Frules\n\ncat > .cursor\u002Frules\u002Fai-dlc-workflow.mdc \u003C\u003C 'EOF'\n---\ndescription: \"AI-DLC (AI-Driven Development Life Cycle) adaptive workflow for software development\"\nalwaysApply: true\n---\n\nEOF\ncat ~\u002FDownloads\u002Faidlc-rules\u002Faws-aidlc-rules\u002Fcore-workflow.md >> .cursor\u002Frules\u002Fai-dlc-workflow.mdc\n\nmkdir -p .aidlc-rule-details\ncp -R ~\u002FDownloads\u002Faidlc-rules\u002Faws-aidlc-rule-details\u002F* .aidlc-rule-details\u002F\n```\n\n**Windows PowerShell:**\n\n```powershell\nNew-Item -ItemType Directory -Force -Path \".cursor\\rules\"\n\n$frontmatter = @\"\n---\ndescription: \"AI-DLC (AI-Driven Development Life Cycle) adaptive workflow for software development\"\nalwaysApply: true\n---\n\n\"@\n$frontmatter | Out-File -FilePath \".cursor\\rules\\ai-dlc-workflow.mdc\" -Encoding utf8\n\nGet-Content \"$env:USERPROFILE\\Downloads\\aidlc-rules\\aws-aidlc-rules\\core-workflow.md\" | Add-Content \".cursor\\rules\\ai-dlc-workflow.mdc\"\n\nNew-Item -ItemType Directory -Force -Path \".aidlc-rule-details\"\nCopy-Item \"$env:USERPROFILE\\Downloads\\aidlc-rules\\aws-aidlc-rule-details\\*\" \".aidlc-rule-details\\\" -Recurse\n```\n\n**Windows CMD:**\n\n```cmd\nmkdir .cursor\\rules\n\n(\necho ---\necho description: \"AI-DLC (AI-Driven Development Life Cycle) adaptive workflow for software development\"\necho alwaysApply: true\necho ---\necho.\n) > .cursor\\rules\\ai-dlc-workflow.mdc\n\ntype \"%USERPROFILE%\\Downloads\\aidlc-rules\\aws-aidlc-rules\\core-workflow.md\" >> .cursor\\rules\\ai-dlc-workflow.mdc\n\nmkdir .aidlc-rule-details\nxcopy \"%USERPROFILE%\\Downloads\\aidlc-rules\\aws-aidlc-rule-details\" \".aidlc-rule-details\\\" \u002FE \u002FI\n```\n\n#### Option 2: AGENTS.md (Simple Alternative)\n\n**Unix\u002FLinux\u002FmacOS:**\n\n```bash\ncp ~\u002FDownloads\u002Faidlc-rules\u002Faws-aidlc-rules\u002Fcore-workflow.md .\u002FAGENTS.md\nmkdir -p .aidlc-rule-details\ncp -R ~\u002FDownloads\u002Faidlc-rules\u002Faws-aidlc-rule-details\u002F* .aidlc-rule-details\u002F\n```\n\n**Windows PowerShell:**\n\n```powershell\nCopy-Item \"$env:USERPROFILE\\Downloads\\aidlc-rules\\aws-aidlc-rules\\core-workflow.md\" \".\\AGENTS.md\"\nNew-Item -ItemType Directory -Force -Path \".aidlc-rule-details\"\nCopy-Item \"$env:USERPROFILE\\Downloads\\aidlc-rules\\aws-aidlc-rule-details\\*\" \".aidlc-rule-details\\\" -Recurse\n```\n\n**Windows CMD:**\n\n```cmd\ncopy \"%USERPROFILE%\\Downloads\\aidlc-rules\\aws-aidlc-rules\\core-workflow.md\" \".\\AGENTS.md\"\nmkdir .aidlc-rule-details\nxcopy \"%USERPROFILE%\\Downloads\\aidlc-rules\\aws-aidlc-rule-details\" \".aidlc-rule-details\\\" \u002FE \u002FI\n```\n\n**Verify Setup:**\n\n1. Open **Cursor Settings → Rules, Commands**\n2. Under **Project Rules**, you should see `ai-dlc-workflow` listed\n3. For `AGENTS.md`, it will be automatically detected and applied\n\n![AI-DLC Rules in Cursor](.\u002Fassets\u002Fimages\u002Fcursor-ide-aidlc-rules-loaded.png?raw=true \"AI-DLC Rules in Cursor\")\n\n**Directory Structure (Option 1):**\n\n```text\n\u003Cmy-project>\u002F\n├── .cursor\u002F\n│   └── rules\u002F\n│       └── ai-dlc-workflow.mdc\n└── .aidlc-rule-details\u002F\n    ├── common\u002F\n    ├── inception\u002F\n    ├── construction\u002F\n    ├── extensions\u002F\n    └── operations\u002F\n```\n\n---\n\n### Cline\n\nAI-DLC uses Cline Rules to implement its intelligent workflow.\n\nThe commands below assume you extracted the zip to your `Downloads` folder. If you used a different location, replace `Downloads` with your actual folder path.\n\n#### Option 1: .clinerules Directory (Recommended)\n\n**Unix\u002FLinux\u002FmacOS:**\n\n```bash\nmkdir -p .clinerules\ncp ~\u002FDownloads\u002Faidlc-rules\u002Faws-aidlc-rules\u002Fcore-workflow.md .clinerules\u002F\nmkdir -p .aidlc-rule-details\ncp -R ~\u002FDownloads\u002Faidlc-rules\u002Faws-aidlc-rule-details\u002F* .aidlc-rule-details\u002F\n```\n\n**Windows PowerShell:**\n\n```powershell\nNew-Item -ItemType Directory -Force -Path \".clinerules\"\nCopy-Item \"$env:USERPROFILE\\Downloads\\aidlc-rules\\aws-aidlc-rules\\core-workflow.md\" \".clinerules\\\"\nNew-Item -ItemType Directory -Force -Path \".aidlc-rule-details\"\nCopy-Item \"$env:USERPROFILE\\Downloads\\aidlc-rules\\aws-aidlc-rule-details\\*\" \".aidlc-rule-details\\\" -Recurse\n```\n\n**Windows CMD:**\n\n```cmd\nmkdir .clinerules\ncopy \"%USERPROFILE%\\Downloads\\aidlc-rules\\aws-aidlc-rules\\core-workflow.md\" \".clinerules\\\"\nmkdir .aidlc-rule-details\nxcopy \"%USERPROFILE%\\Downloads\\aidlc-rules\\aws-aidlc-rule-details\" \".aidlc-rule-details\\\" \u002FE \u002FI\n```\n\n#### Option 2: AGENTS.md (Alternative)\n\n**Unix\u002FLinux\u002FmacOS:**\n\n```bash\ncp ~\u002FDownloads\u002Faidlc-rules\u002Faws-aidlc-rules\u002Fcore-workflow.md .\u002FAGENTS.md\nmkdir -p .aidlc-rule-details\ncp -R ~\u002FDownloads\u002Faidlc-rules\u002Faws-aidlc-rule-details\u002F* .aidlc-rule-details\u002F\n```\n\n**Windows PowerShell:**\n\n```powershell\nCopy-Item \"$env:USERPROFILE\\Downloads\\aidlc-rules\\aws-aidlc-rules\\core-workflow.md\" \".\\AGENTS.md\"\nNew-Item -ItemType Directory -Force -Path \".aidlc-rule-details\"\nCopy-Item \"$env:USERPROFILE\\Downloads\\aidlc-rules\\aws-aidlc-rule-details\\*\" \".aidlc-rule-details\\\" -Recurse\n```\n\n**Windows CMD:**\n\n```cmd\ncopy \"%USERPROFILE%\\Downloads\\aidlc-rules\\aws-aidlc-rules\\core-workflow.md\" \".\\AGENTS.md\"\nmkdir .aidlc-rule-details\nxcopy \"%USERPROFILE%\\Downloads\\aidlc-rules\\aws-aidlc-rule-details\" \".aidlc-rule-details\\\" \u002FE \u002FI\n```\n\n**Verify Setup:**\n\n1. In Cline's chat interface, look for the Rules popover under the chat input field\n2. Verify that `core-workflow.md` is listed and active\n3. You can toggle the rule file on\u002Foff as needed\n\n![AI-DLC Rules in Cline](.\u002Fassets\u002Fimages\u002Fcline-ide-aidlc-rules-loaded.png?raw=true \"AI-DLC Rules in Cline\")\n\n**Directory Structure (Option 1):**\n\n```text\n\u003Cmy-project>\u002F\n├── .clinerules\u002F\n│   └── core-workflow.md\n└── .aidlc-rule-details\u002F\n    ├── common\u002F\n    ├── inception\u002F\n    ├── construction\u002F\n    ├── extensions\u002F\n    └── operations\u002F\n```\n\n---\n\n### Claude Code\n\nAI-DLC uses Claude Code's project memory file (`CLAUDE.md`) to implement its intelligent workflow.\n\nThe commands below assume you extracted the zip to your `Downloads` folder. If you used a different location, replace `Downloads` with your actual folder path.\n\n#### Option 1: Project Root (Recommended)\n\n**Unix\u002FLinux\u002FmacOS:**\n\n```bash\ncp ~\u002FDownloads\u002Faidlc-rules\u002Faws-aidlc-rules\u002Fcore-workflow.md .\u002FCLAUDE.md\nmkdir -p .aidlc-rule-details\ncp -R ~\u002FDownloads\u002Faidlc-rules\u002Faws-aidlc-rule-details\u002F* .aidlc-rule-details\u002F\n```\n\n**Windows PowerShell:**\n\n```powershell\nCopy-Item \"$env:USERPROFILE\\Downloads\\aidlc-rules\\aws-aidlc-rules\\core-workflow.md\" \".\\CLAUDE.md\"\nNew-Item -ItemType Directory -Force -Path \".aidlc-rule-details\"\nCopy-Item \"$env:USERPROFILE\\Downloads\\aidlc-rules\\aws-aidlc-rule-details\\*\" \".aidlc-rule-details\\\" -Recurse\n```\n\n**Windows CMD:**\n\n```cmd\ncopy \"%USERPROFILE%\\Downloads\\aidlc-rules\\aws-aidlc-rules\\core-workflow.md\" \".\\CLAUDE.md\"\nmkdir .aidlc-rule-details\nxcopy \"%USERPROFILE%\\Downloads\\aidlc-rules\\aws-aidlc-rule-details\" \".aidlc-rule-details\\\" \u002FE \u002FI\n```\n\n#### Option 2: .claude Directory\n\n**Unix\u002FLinux\u002FmacOS:**\n\n```bash\nmkdir -p .claude\ncp ~\u002FDownloads\u002Faidlc-rules\u002Faws-aidlc-rules\u002Fcore-workflow.md .claude\u002FCLAUDE.md\nmkdir -p .aidlc-rule-details\ncp -R ~\u002FDownloads\u002Faidlc-rules\u002Faws-aidlc-rule-details\u002F* .aidlc-rule-details\u002F\n```\n\n**Windows PowerShell:**\n\n```powershell\nNew-Item -ItemType Directory -Force -Path \".claude\"\nCopy-Item \"$env:USERPROFILE\\Downloads\\aidlc-rules\\aws-aidlc-rules\\core-workflow.md\" \".claude\\CLAUDE.md\"\nNew-Item -ItemType Directory -Force -Path \".aidlc-rule-details\"\nCopy-Item \"$env:USERPROFILE\\Downloads\\aidlc-rules\\aws-aidlc-rule-details\\*\" \".aidlc-rule-details\\\" -Recurse\n```\n\n**Windows CMD:**\n\n```cmd\nmkdir .claude\ncopy \"%USERPROFILE%\\Downloads\\aidlc-rules\\aws-aidlc-rules\\core-workflow.md\" \".claude\\CLAUDE.md\"\nmkdir .aidlc-rule-details\nxcopy \"%USERPROFILE%\\Downloads\\aidlc-rules\\aws-aidlc-rule-details\" \".aidlc-rule-details\\\" \u002FE \u002FI\n```\n\n**Verify Setup:**\n\n1. Start Claude Code in your project directory (CLI: `claude` or VS Code extension)\n2. Use the `\u002Fconfig` command to view current configuration\n3. Ask Claude: \"What instructions are currently active in this project?\"\n\n**Directory Structure (Option 1):**\n\n```text\n\u003Cmy-project>\u002F\n├── CLAUDE.md\n└── .aidlc-rule-details\u002F\n    ├── common\u002F\n    ├── inception\u002F\n    ├── construction\u002F\n    ├── extensions\u002F\n    └── operations\u002F\n```\n\n---\n\n### GitHub Copilot\n\nAI-DLC uses [GitHub Copilot custom instructions](https:\u002F\u002Fcode.visualstudio.com\u002Fdocs\u002Fcopilot\u002Fcustomization\u002Fcustom-instructions) to implement its intelligent workflow. The `.github\u002Fcopilot-instructions.md` file is automatically detected and applied to all chat requests in the workspace.\n\nThe commands below assume you extracted the zip to your `Downloads` folder. If you used a different location, replace `Downloads` with your actual folder path.\n\n**Unix\u002FLinux\u002FmacOS:**\n\n```bash\nmkdir -p .github\ncp ~\u002FDownloads\u002Faidlc-rules\u002Faws-aidlc-rules\u002Fcore-workflow.md .github\u002Fcopilot-instructions.md\nmkdir -p .aidlc-rule-details\ncp -R ~\u002FDownloads\u002Faidlc-rules\u002Faws-aidlc-rule-details\u002F* .aidlc-rule-details\u002F\n```\n\n**Windows PowerShell:**\n\n```powershell\nNew-Item -ItemType Directory -Force -Path \".github\"\nCopy-Item \"$env:USERPROFILE\\Downloads\\aidlc-rules\\aws-aidlc-rules\\core-workflow.md\" \".github\\copilot-instructions.md\"\nNew-Item -ItemType Directory -Force -Path \".aidlc-rule-details\"\nCopy-Item \"$env:USERPROFILE\\Downloads\\aidlc-rules\\aws-aidlc-rule-details\\*\" \".aidlc-rule-details\\\" -Recurse\n```\n\n**Windows CMD:**\n\n```cmd\nmkdir .github\ncopy \"%USERPROFILE%\\Downloads\\aidlc-rules\\aws-aidlc-rules\\core-workflow.md\" \".github\\copilot-instructions.md\"\nmkdir .aidlc-rule-details\nxcopy \"%USERPROFILE%\\Downloads\\aidlc-rules\\aws-aidlc-rule-details\" \".aidlc-rule-details\\\" \u002FE \u002FI\n```\n\n**Verify Setup:**\n\n1. Open VS Code with your project folder\n2. Open the Copilot Chat panel (Cmd\u002FCtrl+Shift+I)\n3. Select **Configure Chat** (gear icon) > **Chat Instructions** and verify that `copilot-instructions` is listed\n4. Alternatively, type `\u002Finstructions` in the chat input to view active instructions\n\n**Directory Structure:**\n\n```text\n\u003Cmy-project>\u002F\n├── .github\u002F\n│   └── copilot-instructions.md\n└── .aidlc-rule-details\u002F\n    ├── common\u002F\n    ├── inception\u002F\n    ├── construction\u002F\n    ├── extensions\u002F\n    └── operations\u002F\n```\n\n---\n\n### OpenAI Codex\n\nAI-DLC supports OpenAI Codex as a supported coding agent, using the [Codex AGENTS.md](https:\u002F\u002Fdevelopers.openai.com\u002Fcodex\u002Fguides\u002Fagents-md) convention to deliver its intelligent workflow. Codex automatically discovers and loads `AGENTS.md` from your project root when you start a session.\n\nThe commands below assume you extracted the zip to your `Downloads` folder. If you used a different location, replace `Downloads` with your actual folder path.\n\n**Unix\u002FLinux\u002FmacOS:**\n\n```bash\ncp ~\u002FDownloads\u002Faidlc-rules\u002Faws-aidlc-rules\u002Fcore-workflow.md .\u002FAGENTS.md\nmkdir -p .aidlc-rule-details\ncp -R ~\u002FDownloads\u002Faidlc-rules\u002Faws-aidlc-rule-details\u002F* .aidlc-rule-details\u002F\n```\n\n**Windows PowerShell:**\n\n```powershell\nCopy-Item \"$env:USERPROFILE\\Downloads\\aidlc-rules\\aws-aidlc-rules\\core-workflow.md\" \".\\AGENTS.md\"\nNew-Item -ItemType Directory -Force -Path \".aidlc-rule-details\"\nCopy-Item \"$env:USERPROFILE\\Downloads\\aidlc-rules\\aws-aidlc-rule-details\\*\" \".aidlc-rule-details\\\" -Recurse\n```\n\n**Windows CMD:**\n\n```cmd\ncopy \"%USERPROFILE%\\Downloads\\aidlc-rules\\aws-aidlc-rules\\core-workflow.md\" \".\\AGENTS.md\"\nmkdir .aidlc-rule-details\nxcopy \"%USERPROFILE%\\Downloads\\aidlc-rules\\aws-aidlc-rule-details\" \".aidlc-rule-details\\\" \u002FE \u002FI\n```\n\n**Verify Setup:**\n\n1. Start a Codex session in your project directory\n2. Ask Codex: For existing project - \"Using AIDLC analyze the project?\" or For new project \"Using Aidlc what workflow do you see\" .\n3. Codex should describe the AI-DLC three-phase workflow (Inception → Construction → Operations)\n\n> [!NOTE]\n> The `AGENTS.md` file is designed to fit within Codex's instruction budget under default settings. If you add substantial project-specific content and Codex reports that the project documentation exceeds its instruction limit, you can increase the limit in your Codex configuration (for example, by adjusting `project_doc_max_bytes` in your `config.toml` file):\n>\n> ```toml\n> project_doc_max_bytes = 65536  # Example value; choose a limit appropriate for your project\n> ```\n\n**Directory Structure:**\n\n```text\n\u003Cmy-project>\u002F\n├── AGENTS.md\n└── .aidlc-rule-details\u002F\n    ├── common\u002F\n    ├── inception\u002F\n    ├── construction\u002F\n    ├── extensions\u002F\n    └── operations\u002F\n```\n\n---\n\n### Other Agents\n\nAI-DLC works with any coding agent that supports project-level rules or steering files. The general approach:\n\n1. Place `aws-aidlc-rules\u002F` wherever your agent reads project rules from (consult your agent's documentation).\n2. Place `aws-aidlc-rule-details\u002F` at a sibling level so the rules can reference it.\n\nIf your agent has no convention for rules files, place both folders at your project root and point the agent to `aws-aidlc-rules\u002F` as its rules directory.\n\n---\n\n## Usage\n\n1. Start any software development project by stating your intent starting with the phrase **\"Using AI-DLC, ...\"** in the chat\n2. AI-DLC workflow automatically activates and guides you from there\n3. Answer structured questions that AI-DLC asks you\n4. Carefully review every plan that AI generates. Provide your oversight and validation\n5. Review the execution plan to see which stages will run\n6. Carefully review the artifacts and approve each stage to maintain control\n7. All the artifacts will be generated in the `aidlc-docs\u002F` directory\n\n---\n\n## Three-Phase Adaptive Workflow\n\nAI-DLC follows a structured three-phase approach that adapts to your project's complexity:\n\n### 🔵 INCEPTION PHASE\n\nDetermines **WHAT** to build and **WHY**\n\n- Requirements analysis and validation\n- User story creation (when applicable)\n- Application Design and creating units of work for parallel development\n- Risk assessment and complexity evaluation\n\n### 🟢 CONSTRUCTION PHASE\n\nDetermines **HOW** to build it\n\n- Detailed component design\n- Code generation and implementation\n- Build configuration and testing strategies\n- Quality assurance and validation\n\n### 🟡 OPERATIONS PHASE\n\nDeployment and monitoring (future)\n\n- Deployment automation and infrastructure\n- Monitoring and observability setup\n- Production readiness validation\n\n---\n\n## Key Features\n\n| Feature                   | Description                                                                                               |\n| ------------------------- | --------------------------------------------------------------------------------------------------------- |\n| **Adaptive Intelligence** | Only executes stages that add value to your specific request                                              |\n| **Context-Aware**         | Analyzes existing codebase and complexity requirements                                                    |\n| **Risk-Based**            | Complex changes get comprehensive treatment, simple changes stay efficient                                |\n| **Question-Driven**       | Structured multiple-choice questions in files, not chat                                                   |\n| **Always in Control**     | Review execution plans and approve each phase                                                             |\n| **Extensible**            | Layer custom rules e.g. security, compliance, and organization-specific rules on top of the core workflow |\n\n---\n\n## Extensions\n\nAI-DLC supports an extension system that lets you layer additional rules on top of the core workflow. Extensions are markdown files organized under `aws-aidlc-rule-details\u002Fextensions\u002F` and grouped by category (e.g., `security\u002F`, `testing\u002F`).\n\n### How Extensions Work\n\nEach extension consists of two files placed in the same directory:\n\n- A **rules file** (e.g., `security-baseline.md`) containing the extension's rules.\n- An **opt-in file** (e.g., `security-baseline.opt-in.md`) containing a structured multiple-choice question presented to the user during Requirements Analysis.\n\nAt workflow start, AI-DLC scans the `extensions\u002F` directory and loads only `*.opt-in.md` files. During Requirements Analysis, it presents each opt-in prompt to the user. When the user opts in, the corresponding rules file is loaded (derived by naming convention: strip `.opt-in.md`, append `.md`). When the user opts out, the rules file is never loaded. Extensions without a matching `*.opt-in.md` file are always enforced.\n\nOnce enabled, extension rules are blocking constraints — at each stage, the model verifies compliance before allowing the stage to proceed.\n\n### Built-in Extensions\n\nThe `extensions\u002F` directory ships with the following (new extensions may be added over time):\n\n```text\naws-aidlc-rule-details\u002F\n└── extensions\u002F\n    ├── security\u002F                      # Extension category\n    │   └── baseline\u002F\n    │       ├── security-baseline.md          # Baseline security rules\n    │       └── security-baseline.opt-in.md   # Opt-in prompt\n    └── testing\u002F                       # Extension category\n        └── property-based\u002F\n            ├── property-based-testing.md          # Property-based testing rules\n            └── property-based-testing.opt-in.md   # Opt-in prompt\n```\n\n> [!IMPORTANT]\n> The security extension rules are provided as a directional reference for building effective security rules within AI-DLC workflows. Each organization should build, customize, and thoroughly test their own security rules before deploying in production workflows.\n\n### Adding Your Own Extensions\n\nYou can extend an existing category or create an entirely new one.\n\n1. Create a directory under `extensions\u002F` (e.g., `security\u002Fcompliance\u002F` or `performance\u002Fbaseline\u002F`).\n2. Add a **rules file** (e.g., `compliance.md`). Follow the same structure as `security-baseline.md`:\n   - Define each rule as a heading in the format `## Rule \u003CPREFIX-NN>: \u003CTitle>` where the prefix is a short category identifier and NN is a sequential number (e.g., `COMPLIANCE-01`, `COMPLIANCE-02`). These IDs are referenced in audit logs and compliance summaries, so they must be unique across all loaded extensions.\n   - Include a **Rule** section describing the requirement.\n   - Include a **Verification** section with concrete checks the model should evaluate.\n3. Add a matching **opt-in file** using the naming convention `\u003Cname>.opt-in.md` (e.g., `compliance.opt-in.md`). See `security-baseline.opt-in.md` for the expected format. Omitting this file means the extension is always enforced with no user opt-out.\n4. Rules are blocking by default — if verification criteria are not met, the stage cannot proceed until the finding is resolved.\n\n---\n\n## Tenets\n\nThese are our core principles to guide our decision making.\n\n- **No duplication**. The source of truth lives in one place. If we add support for new tools or formats that require specific files, we generate them from the source rather than maintaining separate copies.\n\n- **Methodology first**. AI-DLC is fundamentally a methodology, not a tool. Users shouldn't need to install anything to get started. That said, we're open to convenience tooling (scripts, CLIs) down the road if it helps users adopt or extend the methodology.\n\n- **Reproducible**. Rules should be clear enough that different models produce similar outcomes. We know models behave differently, but the methodology should minimize variance through explicit guidance.\n\n- **Agnostic**. The methodology works with any IDE, agent, or model. We don't tie ourselves to specific tools or vendors.\n\n- **Human in the loop**. Critical decisions require explicit user confirmation. The agent proposes, the human approves.\n\n---\n\n## Prerequisites\n\nHave one of our supported platforms\u002Ftools for Assisted AI Coding installed:\n\n| Platform                      | Installation Link                                                                                                                                               |\n| ----------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Kiro                          | [Install](https:\u002F\u002Fkiro.dev\u002F)                                                                                                                                    |\n| Kiro CLI                      | [Install](https:\u002F\u002Fkiro.dev\u002Fcli\u002F)                                                                                                                                |\n| Amazon Q Developer IDE Plugin | [Install](https:\u002F\u002Fdocs.aws.amazon.com\u002Famazonq\u002Flatest\u002Fqdeveloper-ug\u002Fq-in-IDE.html)                                                                               |\n| Cursor IDE                    | [Install](https:\u002F\u002Fcursor.com\u002F)                                                                                                                                  |\n| Cline VS Code Extension       | [Install](https:\u002F\u002Fmarketplace.visualstudio.com\u002Fitems?itemName=saoudrizwan.claude-dev)                                                                           |\n| Claude Code CLI               | [Install](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-code)                                                                                                            |\n| GitHub Copilot                | [Install](https:\u002F\u002Fmarketplace.visualstudio.com\u002Fitems?itemName=GitHub.copilot) + [Chat](https:\u002F\u002Fmarketplace.visualstudio.com\u002Fitems?itemName=GitHub.copilot-chat) |\n\n---\n\n## Troubleshooting\n\n### General Issues\n\n| Problem                      | Solution                                                    |\n| ---------------------------- | ----------------------------------------------------------- |\n| Rules not loading            | Check file exists in the correct location for your platform |\n| File encoding issues         | Ensure files are UTF-8 encoded                              |\n| Rules not applied in session | Start a new chat session after file changes                 |\n| Rule details not loading     | Verify `.aidlc-rule-details\u002F` exists with subdirectories    |\n\n### Platform-Specific Issues\n\n#### Kiro\n\n- Use `\u002Fcontext show` in Kiro CLI to verify rules are loaded\n- Check `.kiro\u002Fsteering\u002F` directory structure\n- Note: Kiro uses `aws-aidlc-rule-details` (not `.aidlc-rule-details\u002F`) under the `.kiro\u002F` directory\n\n#### Amazon Q Developer\n\n- Check `.amazonq\u002Frules\u002F` directory structure\n- Verify rules are listed in the Amazon Q Chat Rules panel\n- Note: Amazon Q uses `aws-aidlc-rule-details` (not `.aidlc-rule-details\u002F`) under the `.amazonq\u002F` directory\n\n#### Cursor\n\n- For \"Apply Intelligently\", ensure a description is defined in frontmatter\n- Check **Cursor Settings → Rules** to ensure the rule is enabled\n- If rule is too large (>500 lines), split into multiple focused rules\n\n#### Cline\n\n- Check the Rules popover under the chat input field\n- Toggle rule files on\u002Foff as needed using the popover UI\n\n#### Claude Code\n\n- Use `\u002Fconfig` command to view current configuration\n- Ask \"What instructions are currently active in this project?\"\n\n#### GitHub Copilot\n\n- Select **Configure Chat** (gear icon) > **Chat Instructions** to verify instructions are loaded\n- Type `\u002Finstructions` in the chat input to view active instruction files\n- Check that `.github\u002Fcopilot-instructions.md` exists in your workspace root\n\n### File Path Issues on Windows\n\n- Use forward slashes `\u002F` in file paths within markdown files\n- Windows paths with backslashes may not work correctly\n\n---\n\n## Version Control Recommendations\n\n**Commit to repository:**\n\n```gitignore\n# These should be version controlled\nCLAUDE.md\nAGENTS.md\n.amazonq\u002Frules\u002F\n.amazonq\u002Faws-aidlc-rule-details\u002F\n.kiro\u002Fsteering\u002F\n.kiro\u002Faws-aidlc-rule-details\u002F\n.cursor\u002Frules\u002F\n.clinerules\u002F\n.github\u002Fcopilot-instructions.md\n.aidlc-rule-details\u002F\n```\n\n**Optional - Add to `.gitignore` (if needed):**\n\n```gitignore\n# Local-only settings\n.claude\u002Fsettings.local.json\n```\n\n---\n\n## Generated aidlc-docs\u002F Reference\n\nFor the complete reference of all documentation artifacts generated by the AI-DLC workflow, see [docs\u002FGENERATED_DOCS_REFERENCE.md](docs\u002FGENERATED_DOCS_REFERENCE.md).\n\n---\n\n## Experimental: AI-Assisted Setup (Release Download)\n\n> Instead of manually copying files, let your AI agent handle the setup. This is an experimental workflow — currently validated with Kiro, Claude code, Cursor, Antigravity.\n>\n> **Note:** This approach requires your agent to have shell access (e.g., Kiro, Claude Code, Cline). For agents without shell access, follow the [Common](#common) setup above.\n\nPaste this prompt into your AI agent:\n\n```text\nSet up AI-DLC in this project by doing the following:\n\n1. Download the latest AI-DLC release:\n   - Use the GitHub API to find the latest release asset URL:\n     curl -sL https:\u002F\u002Fapi.github.com\u002Frepos\u002Fawslabs\u002Faidlc-workflows\u002Freleases\u002Flatest \\\n       | grep -o '\"browser_download_url\": *\"[^\"]*\"' \\\n       | head -1 \\\n       | cut -d'\"' -f4\n   - Download the zip from that URL to \u002Ftmp\u002Faidlc-rules.zip\n   - Extract it: unzip -o \u002Ftmp\u002Faidlc-rules.zip -d \u002Ftmp\u002Faidlc-release\n   - Copy the aidlc-rules\u002F folder from the extracted contents into .aidlc at the project root\n   - Clean up: rm -rf \u002Ftmp\u002Faidlc-rules.zip \u002Ftmp\u002Faidlc-release\n\n2. Create the appropriate rules\u002Fsteering file for your IDE using the options below.\n   Pick the one that matches the agent you are running in:\n\n   - Kiro IDE or Kiro CLI     → create `.kiro\u002Fsteering\u002Fai-dlc.md`\n   - Amazon Q Developer       → create `.amazonq\u002Frules\u002Fai-dlc.md`\n   - Antigravity              → create `.agent\u002Frules\u002Fai-dlc.md`\n   - Cursor                   → create `.cursor\u002Frules\u002Fai-dlc.mdc` with frontmatter:\n                                  ---\n                                  description: \"AI-DLC workflow\"\n                                  alwaysApply: true\n                                  ---\n   - Cline                    → create `.clinerules\u002Fai-dlc.md`\n   - Claude Code              → create `CLAUDE.md`\n   - GitHub Copilot           → create `.github\u002Fcopilot-instructions.md`\n   - Any other agent          → create `AGENTS.md`\n\n3. The file content should be:\n   When the user invokes AI-DLC, read and follow\n   `.aidlc\u002Faidlc-rules\u002Faws-aidlc-rules\u002Fcore-workflow.md` to start the workflow.\n\n4. Add `.aidlc` to `.gitignore` unless I explicitly ask you not to.\n\n5. Confirm what file you created and that `.aidlc` is gitignored.\n```\n\nThe agent will download the latest release, create the correct config file for your IDE, and gitignore the `.aidlc` directory automatically.\n\n**Updating AI-DLC** — Re-run the prompt above. The agent will download the latest release and overwrite the existing `.aidlc\u002F` folder.\n\n---\n\n## Additional Resources\n\n\u003C!-- TODO: Replace this Amplify URL with a permanent\u002Fstable URL when available -->\n| Resource                                            | Link                                                                                                                          |\n| --------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------- |\n| AI-DLC Method Definition Paper                      | [Paper](https:\u002F\u002Fprod.d13rzhkk8cj2z0.amplifyapp.com\u002F)                                                                          |\n| AI-DLC Methodology Blog                             | [AWS Blog](https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fdevops\u002Fai-driven-development-life-cycle\u002F)                                             |\n| AI-DLC Open-source Launch Blog                      | [AWS Blog](https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fdevops\u002Fopen-sourcing-adaptive-workflows-for-ai-driven-development-life-cycle-ai-dlc\u002F) |\n| AI-DLC Example Walkthrough Blog                     | [AWS Blog](https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fdevops\u002Fbuilding-with-ai-dlc-using-amazon-q-developer\u002F)                                |\n| Amazon Q Developer Documentation                    | [Docs](https:\u002F\u002Fdocs.aws.amazon.com\u002Famazonq\u002Flatest\u002Fqdeveloper-ug\u002Fq-in-IDE.html)                                                |\n| Kiro CLI Documentation                              | [Docs](https:\u002F\u002Fkiro.dev\u002Fdocs\u002Fcli\u002Fsteering\u002F)                                                                                   |\n| Cursor Rules Documentation                          | [Docs](https:\u002F\u002Fcursor.com\u002Fdocs\u002Fcontext\u002Frules)                                                                                 |\n| Claude Code Documentation                           | [GitHub](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-code)                                                                           |\n| GitHub Copilot Documentation                        | [Docs](https:\u002F\u002Fdocs.github.com\u002Fen\u002Fcopilot)                                                                                    |\n| Working with AI-DLC (interaction patterns and tips) | [docs\u002FWORKING-WITH-AIDLC.md](docs\u002FWORKING-WITH-AIDLC.md)                                                                      |\n| Contributing Guidelines                             | [CONTRIBUTING.md](CONTRIBUTING.md)                                                                                            |\n| Code of Conduct                                     | [CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md)                                                                                      |\n\n---\n\n## Contributing\n\nSee [CONTRIBUTING](CONTRIBUTING.md#security-issue-notifications) for more information.\n\n## License\n\nThis library is licensed under the MIT-0 License. See the [LICENSE](LICENSE) file.\n","awslabs\u002Faidlc-workflows 是一个基于AI的软件开发生命周期管理系统，旨在为AI编码助手提供自适应的工作流指导规则。项目采用Python编写，其核心功能包括智能适应开发者需求、维护代码质量标准以及确保用户对开发过程的控制权。它通过三阶段自适应工作流程来实现这些目标，并支持多种平台和编码代理工具，如Kiro、GitHub Copilot等。适用于希望提高开发效率同时保持高质量输出的软件开发团队或个人开发者，在使用生成式AI辅助编程时尤其有用。",2,"2026-06-11 03:31:21","trending"]