
beads-workflow
Convert markdown plans into beads with dependencies using br CLI. Use when creating task graphs, polishing beads before implementation, or bridging planning to agent swarm execution.
- Installs
- 90
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations --skill beads-workflow- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads beads-workflow automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Beads Workflow — From Plan to Actionable Tasks
Core Principle: "Check your beads N times, implement once" — where N is as many as you can stomach.
Beads are so detailed and polished that you can mechanically unleash a big swarm of agents to implement them, and it will come out just about perfectly.
Quick Start
# 1. Initialize beads in project
br init
# 2. Convert plan to beads (see THE EXACT PROMPT below)
# 3. Polish iteratively
# Run polish prompt 6-9 times until steady-state
# 4. Validate
br dep cycles # Must be empty
bv --robot-insights # Check graph health
# 5. Begin implementation
bv --robot-next # Get first bead
THE EXACT PROMPT — Plan to Beads Conversion
OK so now read ALL of [YOUR_PLAN_FILE].md; please take ALL of that and elaborate on it and use it to create a comprehensive and granular set of beads for all this with tasks, subtasks, and dependency structure overlaid, with detailed comments so that the whole thing is totally self-contained and self-documenting (including relevant background, reasoning/justification, considerations, etc.-- anything we'd want our "future self" to know about the goals and intentions and thought process and how it serves the over-arching goals of the project.). The beads should be so detailed that we never need to consult back to the original markdown plan document. Remember to ONLY use the `br` tool to create and modify the beads and add the dependencies. Use ultrathink.
Shorter Version
OK so please take ALL of that and elaborate on it more and then create a comprehensive and granular set of beads for all this with tasks, subtasks, and dependency structure overlaid, with detailed comments so that the whole thing is totally self-contained and self-documenting (including relevant background, reasoning/justification, considerations, etc.-- anything we'd want our "future self" to know about the goals and intentions and thought process and how it serves the over-arching goals of the project.) Use only the `br` tool to create and modify the beads and add the dependencies. Use ultrathink.
What This Creates
- Tasks and subtasks with clear scope
- Dependency links (what blocks what)
- Detailed descriptions with background, reasoning, considerations
- Self-contained (never need to consult original plan)
Polishing Beads
THE EXACT PROMPT — Polish (Standard)
Reread AGENTS dot md so it's still fresh in your mind. Check over each bead super carefully-- are you sure it makes sense? Is it optimal? Could we change anything to make the system work better for users? If so, revise the beads. It's a lot easier and faster to operate in "plan space" before we start implementing these things!
DO NOT OVERSIMPLIFY THINGS! DO NOT LOSE ANY FEATURES OR FUNCTIONALITY!
Also, make sure that as part of these beads, we include comprehensive unit tests and e2e test scripts with great, detailed logging so we can be sure that everything is working perfectly after implementation. Remember to ONLY use the `br` tool to create and modify the beads and to add the dependencies to beads. Use ultrathink.
Polishing Protocol
- Run polish prompt
- Review changes
- Repeat until steady-state (typically 6-9 rounds)
- If it flatlines, start a fresh CC session
- Optionally have Codex/GPT 5.5 do a final round
Fresh Session Technique
If polishing flatlines, start a new Claude Code session:
THE EXACT PROMPT — Re-establish Context
First read ALL of the AGENTS dot md file and README dot md file super carefully and understand ALL of both! Then use your code investigation agent mode to fully understand the code, and technical architecture and purpose of the project. Use ultrathink.
THE EXACT PROMPT — Then Review Beads
We recently transformed a markdown plan file into a bunch of new beads. I want you to very carefully review and analyze these using `br` and `bv`.
Then follow up with the standard polish prompt.
br Commands
Issue Lifecycle
br init # Initialize workspace
br create "Title" -t feature -p 1 # Create bead
br update <id> --status in_progress
br close <id> --reason "Done"
br reopen <id> # If needed
Dependencies
br dep add br-child br-parent # child depends on parent
br dep remove br-child br-parent
br dep list <id>
br dep tree <id>
br dep cycles # MUST be empty!
Querying
br list # All beads
br ready # Actionable (not blocked)
br blocked # Blocked beads
br search "authentication"
br list --json # Machine-readable
Sync to Git
br sync --flush-only # Export DB → JSONL
git add .beads/ && git commit -m "Update beads"
bd → br Migration (Docs)
Use this when you see legacy bd references in AGENTS.md or docs.
Behavioral difference (only one):
br syncnever runs git commands. Afterbr sync --flush-only, you mustgit add .beads/andgit commit(andgit push) yourself.
Transform checklist (order matters):
bdcommands →brcommandsbd sync→br sync --flush-only+git add .beads/+git commit- Do NOT assume issue IDs must change
bd-*→br-*— the prefix is configurable (often remainsbd-*). - Remove daemon/auto-commit references
Verify:
grep -c '`bd ' file.md # must be 0
grep -c 'bd sync' file.md # must be 0
grep -c 'br sync --flush-only' file.md # must be > 0
BV Robot Mode
CRITICAL: Never run bare bv — it launches interactive TUI.
bv --robot-triage # Full triage
bv --robot-next # Single top pick
bv --robot-plan # Parallel execution tracks
bv --robot-insights | jq '.Cycles' # Check for cycles
bv --robot-insights | jq '.bottlenecks'
Quality Checklist
Before implementation, verify each bead:
- Self-contained — Understandable without external context
- Clear scope — One coherent piece of work
- Dependencies explicit — Links to blocking/blocked beads
- Testable — Clear success criteria
- Includes tests — Unit and e2e tests in scope
- Preserves features — Nothing from plan was lost
- Not oversimplified — Complexity preserved where needed
- No cycles —
br dep cyclesreturns empty
Integration with Agent Mail
Use bead ID as the coordination thread:
# Reserve files for bead
file_reservation_paths(..., reason="br-123")
# Announce work in thread
send_message(..., thread_id="br-123", subject="[br-123] Starting...")
# Close bead when done
br close br-123 --reason "Completed"
release_file_reservations(...)
When Beads Are Ready
Your beads are ready for implementation when:
- Steady-state reached — Multiple polish rounds yield minimal changes
- Cross-model reviewed — At least one alternative model reviewed
- No cycles —
br dep cyclesreturns empty - Tests included — Each feature has associated test beads
- Dependencies clean — Graph makes logical sense
References
| Topic | Reference |
|---|---|
| All prompts | PROMPTS.md |
| Bead structure | BEAD-ANATOMY.md |
| Troubleshooting | TROUBLESHOOTING.md |
| br command reference | See br --help or beads_rust README |
| BV integration | See bv-graph-triage skill |
Troubleshooting
Worktree Error Fix
If you get failed to create worktree: 'main' is already checked out:
git branch beads-sync main
git push -u origin beads-sync
br config set sync-branch beads-sync
Always use a dedicated sync branch that you never check out directly.
Quick Health Check
br config list # All settings
br dep cycles # Must be empty
which br # Verify br is installed
See TROUBLESHOOTING.md for full diagnostics.
Validation
# Check for cycles (must be empty)
br dep cycles
# Check graph health
bv --robot-insights | jq '.Cycles'
# Verify all beads have descriptions
br list --json | jq '.issues[]? | select(.description == "")'
FAQ
What does the beads-workflow skill do?
Convert markdown plans into beads with dependencies using br CLI. Use when creating task graphs, polishing beads before implementation, or bridging planning to agent swarm execution.
How do I install beads-workflow?
Run npx skills add https://github.com/dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations --skill beads-workflow in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/beads-workflow/ (personal) or .claude/skills/beads-workflow/ (project).
Which AI agents can use beads-workflow?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is beads-workflow safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains beads-workflow?
It is published by dicklesworthstone in dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations. It has 90 recorded installs.
More from dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations
ssh
dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations
SSH remote access - connections, tunnels, keys, file transfers. Use when connecting to servers, managing SSH keys, setting up port forwarding, or transferring files with scp/rsync.
ui-ux-polish
dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations
Open the skill to read its SKILL.md instructions.
gcloud
dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations
Google Cloud Platform CLI - manage GCP resources. Use when working with Compute Engine, Cloud Run, GKE, Cloud Functions, Storage, BigQuery, or other GCP services.
agent-swarm-workflow
dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations
Open the skill to read its SKILL.md instructions.
planning-workflow
dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations
Comprehensive markdown planning methodology for software projects. Use when starting a new project, creating implementation plans, or refining architecture before coding.
cass
dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations
Open the skill to read its SKILL.md instructions.
Popular productivity & automation skills
agent-browser
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
lark-doc
open.feishu.cn
飞书云文档(Docx / Wiki)内容操作:读取、创建、编辑文档,插入或下载图片附件,以及操作思维笔记。用户提供文档 URL/token(包括 doubao.com 的 /docx/、/wiki/)时使用;按 URL 路径/token 而非域名路由;/page/ 是妙搭应用,非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive;随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。
lark-base
open.feishu.cn
飞书多维表格(Base)操作:建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式(BaseApp/AppMode 页面与组件)、Workspace 目录、workflow、角色权限、模板中心(多维表格模板分类/列表/搜索);遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps;文件导入/导出转 lark-drive,认证/授权转 lark-shared。
lark-drive
open.feishu.cn
飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签(secure labels)和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用;doubao.com 云空间 URL/token 也按资源路径和 token 路由,不回退 WebFetch。不负责:文档内容编辑(走 lark-doc)、表格/Base 表内数据操作(走 lark-sheets/lark-base)、知识空间节点/成员管理(走 lark-wiki)、原生 Markdown 文件读写/patch/diff(走 lark-markdown)。
lark-shared
open.feishu.cn
Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.
lark-im
open.feishu.cn
飞书即时通讯:收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片(Interactive Card)、监听卡片按钮回调(card.action.trigger)。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶(添加/移除/查询置顶会话)、管理标签数据、处理卡片回调时使用。