[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-73568":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":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":33,"readmeContent":34,"aiSummary":35,"trendingCount":16,"starSnapshotCount":16,"syncStatus":36,"lastSyncTime":37,"discoverSource":38},73568,"Backlog.md","MrLesk\u002FBacklog.md","MrLesk","Backlog.md - A tool for managing project collaboration between humans and AI Agents in a git ecosystem","https:\u002F\u002Fbacklog.md",null,"TypeScript",5723,342,18,39,0,34,70,195,102,113.61,"MIT License",false,"main",[26,27,28,29,30,31,32],"agent","agentic-ai","management","markdown","project","task-manager","tasks","2026-06-12 04:01:10","\u003Ch1 align=\"center\">Backlog.md\u003C\u002Fh1>\n\u003Cp align=\"center\">Markdown‑native Task Manager & Kanban visualizer for any Git repository\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n\u003Ccode>npm i -g backlog.md\u003C\u002Fcode> or \u003Ccode>bun add -g backlog.md\u003C\u002Fcode> or \u003Ccode>brew install backlog-md\u003C\u002Fcode> or \u003Ccode>nix run github:MrLesk\u002FBacklog.md\u003C\u002Fcode>\n\u003C\u002Fp>\n\n![Backlog demo GIF using: backlog board](.\u002F.github\u002Fbacklog-v1.40.gif)\n\n\n---\n\n> **Backlog.md** turns any folder with a Git repo into a **self‑contained project board**\n> powered by plain Markdown files and a zero‑config CLI.\n> Built for **spec‑driven AI development** — structure your tasks so AI agents deliver predictable results.\n\n## Features\n\n* 📝 **Markdown-native tasks** -- manage every issue as a plain `.md` file\n\n* 🤖 **AI-Ready** -- Works with Claude Code, Gemini CLI, Codex, Kiro & any other MCP or CLI compatible AI assistants\n\n* 📊 **Instant terminal Kanban** -- `backlog board` paints a live board in your shell\n\n* 🌐 **Modern web interface** -- `backlog browser` launches a sleek web UI for visual task management\n\n* 🔍 **Powerful search** -- fuzzy search across tasks, docs & decisions with `backlog search`\n\n* 📋 **Rich query commands** -- view, list, filter, or archive tasks with ease\n* ✅ **Definition of Done defaults** -- add a reusable checklist to every new task\n\n* 📤 **Board export** -- `backlog board export` creates shareable markdown reports\n\n* 🔒 **100 % private & offline** -- backlog lives entirely inside your repo and you can manage everything locally\n\n* 💻 **Cross-platform** -- runs on macOS, Linux, and Windows\n\n* 🆓 **MIT-licensed & open-source** -- free for personal or commercial use\n\n\n---\n\n## \u003Cimg src=\".\u002F.github\u002F5-minute-tour-256.png\" alt=\"Getting started\" width=\"28\" height=\"28\" align=\"center\"> Getting started\n\n```bash\n# Install\nbun i -g backlog.md\n# or: npm i -g backlog.md\n# or: brew install backlog-md\n\n# Initialize in any Git repo\nbacklog init \"My Awesome Project\"\n\n# Or initialize without Git for local\u002Fnon-code projects\nbacklog init \"Personal Planning\" --no-git\n```\n\nThe init wizard will ask how you want to connect AI tools:\n- **MCP connector** (recommended) — auto-configures Claude Code, Codex, Gemini CLI, Kiro or Cursor and adds workflow instructions for your agents.\n- **CLI commands** — creates instruction files (CLAUDE.md, AGENTS.md, etc.) so agents use Backlog via CLI.\n- **Skip** — no AI setup; use Backlog.md purely as a task manager.\n\nBacklog data is stored in a project-local backlog folder such as `backlog\u002F`, `.backlog\u002F`, or a custom project-relative path configured through `backlog.config.yml`. Tasks remain human-readable Markdown files (e.g. `task-10 - Add core search functionality.md`). Git is optional: `backlog init --no-git` creates a filesystem-only project and disables cross-branch checks, remote operations, and auto-commit.\n\n---\n\n### Working with AI agents\n\nThis is the recommended flow for Claude Code, Codex, Gemini CLI, Kiro and similar tools — following the **spec‑driven AI development** approach.\nAfter running `backlog init` and choosing the MCP or CLI integration, work in this loop:\n\n**Step 1 — Describe your idea.** Tell the agent what you want to build and ask it to split the work into small tasks with clear descriptions and acceptance criteria.\n\n**🤖 Ask your AI Agent:**\n> I want to add a search feature to the web view that searches tasks, docs, and decisions. Please decompose this into small Backlog.md tasks.\n\n> [!NOTE]\n> **Review checkpoint #1** — read the task descriptions and acceptance criteria.\n\n**Step 2 — One task at a time.** Work on a single task per agent session, one PR per task. Good task splitting means each session can work independently without conflicts. Make sure each task is small enough to complete in a single conversation. You want to avoid running out of context window.\n\n**Step 3 — Plan before coding.** Ask the agent to research and write an implementation plan in the task. Do this right before implementation so the plan reflects the current state of the codebase.\n\n**🤖 Ask your AI Agent:**\n> Work on BACK-10 only. Research the codebase and write an implementation plan in the task. Wait for my approval before coding.\n\n> [!NOTE]\n> **Review checkpoint #2** — read the plan. Does the approach make sense? Approve it or ask the agent to revise.\n\n**Step 4 — Implement and verify.** Let the agent implement the task.\n\n> [!NOTE]\n> **Review checkpoint #3** — review the code, run tests, check linting, and verify the results match your expectations.\n\nIf the output is not good enough: clear the plan\u002Fnotes\u002Ffinal summary, refine the task description and acceptance criteria, and run the task again in a fresh session.\n\n---\n\n### Working without AI agents\n\nUse Backlog.md as a standalone task manager from the terminal or browser.\n\n```bash\n# Create and refine tasks\nbacklog task create \"Render markdown as kanban\"\nbacklog task edit BACK-1 -d \"Detailed context\" --ac \"Clear acceptance criteria\"\n\n# Track work\nbacklog task list -s \"To Do\"\nbacklog search \"kanban\"\nbacklog board\n\n# Work visually in the browser\nbacklog browser\n```\n\nYou can switch between AI-assisted and manual workflows at any time — both operate on the same Markdown task files. It is recommended to modify tasks via Backlog.md commands (CLI\u002FMCP\u002FWeb) rather than editing task files manually, so field types and metadata stay consistent. Tasks can record project-root-relative modified files and later be found with `backlog search --modified-file src\u002Fpath.ts --plain`.\n\n**Learn more:** [CLI reference](CLI-INSTRUCTIONS.md) | [Advanced configuration](ADVANCED-CONFIG.md)\n\n---\n\n## \u003Cimg src=\".\u002F.github\u002Fweb-interface-256.png\" alt=\"Web Interface\" width=\"28\" height=\"28\" align=\"center\"> Web Interface\n\nLaunch a modern, responsive web interface for visual task management:\n\n```bash\n# Start the web server (opens browser automatically)\nbacklog browser\n\n# Custom port\nbacklog browser --port 8080\n\n# Don't open browser automatically\nbacklog browser --no-open\n```\n\n**Features:**\n- Interactive Kanban board with drag-and-drop\n- Task creation and editing with rich forms\n- Interactive acceptance criteria editor with checklists\n- Real-time updates across all views\n- Responsive design for desktop and mobile\n- Task archiving with confirmation dialogs\n- Seamless CLI integration - all changes sync with markdown files\n\n![Web Interface Screenshot](.\u002F.github\u002Fweb.jpeg)\n\nTo keep the Web UI running as an auto-starting local service, see [Running Backlog.md as a Service](backlog\u002Fdocs\u002Fdoc-003%20-%20Running-Backlog-Browser-as-a-Service.md).\n\n---\n\n## 🔧 MCP Integration (Model Context Protocol)\n\nThe easiest way to connect Backlog.md to AI coding assistants like Claude Code, Codex, Gemini CLI and Kiro is via the MCP protocol.\nYou can run `backlog init` (even if you already initialized Backlog.md) to set up MCP integration automatically, or follow the manual steps below.\n\n### Client guides\n\n\u003Cdetails>\n  \u003Csummary>\u003Cstrong>Claude Code\u003C\u002Fstrong>\u003C\u002Fsummary>\n\n  ```bash\n  claude mcp add backlog --scope user -- backlog mcp start\n  ```\n\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n  \u003Csummary>\u003Cstrong>Codex\u003C\u002Fstrong>\u003C\u002Fsummary>\n\n  ```bash\n  codex mcp add backlog backlog mcp start\n  ```\n\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n  \u003Csummary>\u003Cstrong>Gemini CLI\u003C\u002Fstrong>\u003C\u002Fsummary>\n\n  ```bash\n  gemini mcp add backlog -s user backlog mcp start\n  ```\n\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n  \u003Csummary>\u003Cstrong>Kiro\u003C\u002Fstrong>\u003C\u002Fsummary>\n\n  ```bash\n  kiro-cli mcp add --scope global --name backlog --command backlog --args mcp,start\n  ```\n\n\u003C\u002Fdetails>\n\nUse the shared `backlog` server name everywhere – the MCP server auto-detects whether the current directory is initialized and falls back to `backlog:\u002F\u002Finit-required` when needed.\n\n### Manual config\n\n```json\n{\n  \"mcpServers\": {\n    \"backlog\": {\n      \"command\": \"backlog\",\n      \"args\": [\"mcp\", \"start\"],\n      \"env\": {\n        \"BACKLOG_CWD\": \"\u002Fabsolute\u002Fpath\u002Fto\u002Fyour\u002Fproject\"\n      }\n    }\n  }\n}\n```\n\nIf your IDE can't set the process working directory for MCP servers, set `BACKLOG_CWD` as shown above.\nIf your IDE supports custom args but not env vars, you can also use `[\"mcp\", \"start\", \"--cwd\", \"\u002Fabsolute\u002Fpath\u002Fto\u002Fyour\u002Fproject\"]`.\n\n> [!IMPORTANT]\n> When adding the MCP server manually, you should add some extra instructions in your CLAUDE.md\u002FAGENTS.md files to inform the agent about Backlog.md.\n> This step is not required when using `backlog init` as it adds these instructions automatically.\n> Backlog.md's instructions for agents are available at [`\u002Fsrc\u002Fguidelines\u002Fmcp\u002Fagent-nudge.md`](\u002Fsrc\u002Fguidelines\u002Fmcp\u002Fagent-nudge.md).\n\n\nOnce connected, agents can read the Backlog.md workflow instructions via the resource `backlog:\u002F\u002Fdocs\u002Ftask-workflow`.\nUse `\u002Fmcp` command in your AI tool (Claude Code, Codex, Kiro) to verify if the connection is working.\n\n---\n\n## \u003Cimg src=\".\u002F.github\u002Fcli-reference-256.png\" alt=\"CLI Reference\" width=\"28\" height=\"28\" align=\"center\"> CLI reference\n\nFull command reference — task management, search, board, docs, decisions, and more: **[CLI-INSTRUCTIONS.md](CLI-INSTRUCTIONS.md)**\n\nQuick examples: `backlog task create`, `backlog task list`, `backlog task edit`, `backlog search`, `backlog board`, `backlog browser`.\n\nFull help: `backlog --help`\n\n---\n\n## \u003Cimg src=\".\u002F.github\u002Fconfiguration-256.png\" alt=\"Configuration\" width=\"28\" height=\"28\" align=\"center\"> Configuration\n\nBacklog.md merges the following layers (highest → lowest):\n\n1. CLI flags\n2. Project config file:\n   - `backlog.config.yml` when present\n   - otherwise `backlog\u002Fconfig.yml` or `.backlog\u002Fconfig.yml`\n3. Built‑ins\n\n### Interactive wizard (`backlog config`)\n\nRun `backlog config` with no arguments to launch the full interactive wizard. This is the same experience triggered from `backlog init` when you opt into advanced settings, and it walks through the complete configuration surface:\n- Cross-branch accuracy: `checkActiveBranches`, `remoteOperations`, and `activeBranchDays`.\n- Git workflow: `autoCommit` and `bypassGitHooks`.\n- ID formatting: enable or size `zeroPaddedIds`.\n- Editor integration: pick a `defaultEditor` with availability checks.\n- Definition of Done defaults: interactively add\u002Fremove\u002Freorder\u002Fclear project-level `definition_of_done` checklist items.\n- Web UI defaults: choose `defaultPort` and whether `autoOpenBrowser` should run.\n\nSkipping the wizard (answering \"No\" during init) applies the safe defaults that ship with Backlog.md:\n- `checkActiveBranches=true`, `remoteOperations=true`, `activeBranchDays=30`.\n- `autoCommit=false`, `bypassGitHooks=false`.\n- `zeroPaddedIds` disabled.\n- `defaultEditor` unset (falls back to your environment).\n- `defaultPort=6420`, `autoOpenBrowser=true`.\n\nFor filesystem-only projects, run `backlog init --no-git`. Backlog.md will not run `git init`, and the saved config forces `checkActiveBranches=false`, `remoteOperations=false`, and `autoCommit=false` so CLI, Web, and MCP local-file workflows do not depend on a Git repository.\n\nWhenever you revisit `backlog init` or rerun `backlog config`, the wizard pre-populates prompts with your current values so you can adjust only what changed.\n\n### Definition of Done defaults\n\nSet project-wide DoD items with `backlog config` (or during `backlog init` advanced setup), in the Web UI (Settings → Definition of Done Defaults), or by editing the project config file directly:\n\n```yaml\ndefinition_of_done:\n  - Tests pass\n  - Documentation updated\n  - No regressions introduced\n```\n\nWhen a project uses root config discovery, edit `backlog.config.yml` instead of `backlog\u002Fconfig.yml`.\n\nThese items are added to every new task by default. You can add more on create with `--dod`, or disable defaults per task with `--no-dod-defaults`.\n\nFor the full configuration reference (all options, commands, and detailed notes), see **[ADVANCED-CONFIG.md](ADVANCED-CONFIG.md)**.\n\n---\n\n## 🌐 Community Tools\n\n- **[vscode-backlog-md](https:\u002F\u002Fmarketplace.visualstudio.com\u002Fitems?itemName=ysamlan.vscode-backlog-md)** - VS Code extension with issues panel, kanban view, and editing. ([ysamlan\u002Fvscode-backlog-md](https:\u002F\u002Fgithub.com\u002Fysamlan\u002Fvscode-backlog-md))\n\n---\n\n### License\n\nBacklog.md is released under the **MIT License** – do anything, just give credit. See [LICENSE](LICENSE).\n","Backlog.md 是一个用于在 Git 生态系统中管理人类与 AI 代理之间项目协作的工具。它通过纯 Markdown 文件和零配置 CLI 将任何包含 Git 仓库的文件夹转换为自包含的项目看板，特别适合于规范驱动的 AI 开发场景。其核心功能包括基于 Markdown 的任务管理、即时终端 Kanban 视图以及现代网页界面等，支持多种 AI 助手如 Claude Code、Gemini CLI 等。此外，该工具还提供了强大的搜索功能、丰富的查询命令及定义完成默认设置等功能，并且完全私有化和离线运行，适用于 macOS、Linux 和 Windows 平台上的个人或商业用途。",2,"2026-06-11 03:46:11","high_star"]