[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FHPY7H9A5TCSNDYVVMPC5Z":3,"skill-same:01M6FHPY7H9A5TCSNDYVVMPC5Z":72},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":6,"ownerHtmlUrl":50,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":51,"install":52,"resources":65},"01M6FHPY7H9A5TCSNDYVVMPC5Z","agent-swarm-workflow",null,"Jeffrey Emanuel's multi-agent implementation workflow using NTM, Agent Mail, Beads, and BV. The execution phase that follows planning and bead creation. Includes exact prompts used.","kbarbel640-del\u002Fskills","kbarbel640-del","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F255315490?v=4","01M6CJPPQGCCESXMG3K7BBGQ5J","01M6CJPPX2PB2BCZERFVM2C2B3",1,"MIT","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fclawdnw\u002Fagent-swarm-workflow\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"agent swarm workflow","swarm","workflow","implementation","ntm","bv","agent mail","multi","creation","agent implementation","mail","implementation workflow","prompts","multi-agent","beads","execution","planning","2026-11-10 10:12:30",false,"---\nname: agent-swarm-workflow\ndescription: \"Jeffrey Emanuel's multi-agent implementation workflow using NTM, Agent Mail, Beads, and BV. The execution phase that follows planning and bead creation. Includes exact prompts used.\"\n---\n\n# Agent Swarm Workflow — Parallel Implementation\n\n> **Core Insight:** Every agent is fungible and a generalist. They all use the same base model and read the same AGENTS.md. Simply telling one it's a \"frontend agent\" doesn't make it better at frontend.\n>\n> The swarm is distributed, robust, and self-organizing through Agent Mail and Beads.\n\n---\n\n## Prerequisites\n\nBefore starting a swarm:\n\n1. **Comprehensive plan** created (see `planning-workflow` skill)\n2. **Polished beads** ready (see `beads-workflow` skill)\n3. **AGENTS.md** configured with all tool blurbs\n4. **Agent Mail server** running (`am` or `~\u002Fprojects\u002Fmcp_agent_mail\u002Fscripts\u002Frun_server_with_token.sh`)\n5. **NTM** available for session management\n\n---\n\n## The Swarm Architecture\n\n```\n┌─────────────────────────────────────────────────────────────┐\n│                         BEADS                               │\n│     (Task graph with dependencies, priorities, status)      │\n└─────────────────────────────────────────────────────────────┘\n                              │\n                    ┌─────────┴─────────┐\n                    ▼                   ▼\n┌─────────────────────────────┐  ┌─────────────────────────┐\n│        BV                   │  │     AGENT MAIL          │\n│  (What to work on)          │  │  (Coordination layer)   │\n└─────────────────────────────┘  └─────────────────────────┘\n         │                            │\n         └──────────────┬─────────────┘\n                        ▼\n┌─────────────────────────────────────────────────────────────┐\n│                    NTM + AGENTS                             │\n│  ┌─────┐  ┌─────┐  ┌─────┐  ┌─────┐  ┌─────┐  ┌─────┐     │\n│  │ CC  │  │ CC  │  │ Cod │  │ Gmi │  │ CC  │  │ Cod │     │\n│  └─────┘  └─────┘  └─────┘  └─────┘  └─────┘  └─────┘     │\n└─────────────────────────────────────────────────────────────┘\n```\n\n---\n\n## Starting the Swarm\n\n### Using NTM (Named Tmux Manager)\n\n```bash\n# Spawn a swarm with multiple agents\nntm spawn myproject --cc=3 --cod=2 --gmi=1\n\n# Send initial prompt to all Claude Code agents\nntm send myproject --cc \"$(cat initial_prompt.txt)\"\n\n# Or send to all agents\nntm send myproject --all \"$(cat initial_prompt.txt)\"\n```\n\n### Manual Setup\n\nCreate tmux sessions\u002Fpanes for each agent in your project folder.\n\n---\n\n## THE EXACT PROMPT — Initial Agent Marching Orders\n\nGive each agent this EXACT prompt to start:\n\n```\nFirst 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. Then register with MCP Agent Mail and introduce yourself to the other agents.\n\nBe sure to check your agent mail and to promptly respond if needed to any messages; then proceed meticulously with your next assigned beads, working on the tasks systematically and meticulously and tracking your progress via beads and agent mail messages.\n\nDon't get stuck in \"communication purgatory\" where nothing is getting done; be proactive about starting tasks that need to be done, but inform your fellow agents via messages when you do so and mark beads appropriately.\n\nWhen you're not sure what to do next, use the bv tool mentioned in AGENTS dot md to prioritize the best beads to work on next; pick the next one that you can usefully work on and get started. Make sure to acknowledge all communication requests from other agents and that you are aware of all active agents and their names.  Use ultrathink.\n```\n\n---\n\n## The Implementation Loop\n\n### THE EXACT PROMPT — Move to Next Bead\n\nOnce agents complete a bead, use this prompt to keep them moving:\n\n```\nReread AGENTS dot md so it's still fresh in your mind.   Use ultrathink.   Use bv with the robot flags (see AGENTS dot md for info on this) to find the most impactful bead(s) to work on next and then start on it. Remember to mark the beads appropriately and communicate with your fellow agents. Pick the next bead you can actually do usefully now and start coding on it immediately; communicate what you're working on to your fellow agents and mark beads appropriately as you work. And respond to any agent mail messages you've received.\n```\n\n### THE EXACT PROMPT — Self-Review After Bead Completion\n\nHave agents review their work before moving on:\n\n```\nGreat, now I want you to carefully read over all of the new code you just wrote and other existing code you just modified with \"fresh eyes\" looking super carefully for any obvious bugs, errors, problems, issues, confusion, etc. Carefully fix anything you uncover. Use ultrathink.\n```\n\n**Keep running this until they stop finding bugs.**\n\n---\n\n## Handling Context Compaction\n\n### THE EXACT PROMPT — Post-Compaction\n\nWhen an agent does a compaction, immediately follow up with:\n\n```\nReread AGENTS dot md so it's still fresh in your mind.   Use ultrathink.\n```\n\nThis re-establishes the critical context about tools and workflows.\n\n---\n\n## Quality Review Prompts\n\n### THE EXACT PROMPT — Cross-Agent Review\n\nPeriodically have agents review each other's work:\n\n```\nOk can you now turn your attention to reviewing the code written by your fellow agents and checking for any issues, bugs, errors, problems, inefficiencies, security problems, reliability issues, etc. and carefully diagnose their underlying root causes using first-principle analysis and then fix or revise them if necessary? Don't restrict yourself to the latest commits, cast a wider net and go super deep! Use ultrathink.\n```\n\n### THE EXACT PROMPT — Random Code Exploration\n\nFor deep quality checks:\n\n```\nI want you to sort of randomly explore the code files in this project, choosing code files to deeply investigate and understand and trace their functionality and execution flows through the related code files which they import or which they are imported by.\n\nOnce you understand the purpose of the code in the larger context of the workflows, I want you to do a super careful, methodical, and critical check with \"fresh eyes\" to find any obvious bugs, problems, errors, issues, silly mistakes, etc. and then systematically and meticulously and intelligently correct them.\n\nBe sure to comply with ALL rules in AGENTS dot md and ensure that any code you write or revise conforms to the best practice guides referenced in the AGENTS dot md file. Use ultrathink.\n```\n\n---\n\n## Committing Work\n\n### THE EXACT PROMPT — Commit Changes\n\nHave agents commit logically grouped changes:\n\n```\nNow, based on your knowledge of the project, commit all changed files now in a series of logically connected groupings with super detailed commit messages for each and then push. Take your time to do it right. Don't edit the code at all. Don't commit obviously ephemeral files. Use ultrathink.\n```\n\n---\n\n## Post-Bead Completion Prompts\n\n### THE EXACT PROMPT — Add Test Coverage\n\n```\nDo we have full unit test coverage without using mocks\u002Ffake stuff? What about complete e2e integration test scripts with great, detailed logging? If not, then create a comprehensive and granular set of beads for all this with tasks, subtasks, and dependency structure overlaid with detailed comments.\n```\n\n### THE EXACT PROMPT — UI\u002FUX Scrutiny\n\n```\nGreat, now I want you to super carefully scrutinize every aspect of the application workflow and implementation and look for things that just seem sub-optimal or even wrong\u002Fmistaken to you, things that could very obviously be improved from a user-friendliness and intuitiveness standpoint, places where our UI\u002FUX could be improved and polished to be slicker, more visually appealing, and more premium feeling and just ultra high quality, like Stripe-level apps.\n```\n\n### THE EXACT PROMPT — Deep UI\u002FUX Enhancement\n\n```\nI still think there are strong opportunities to enhance the UI\u002FUX look and feel and to make everything work better and be more intuitive, user-friendly, visually appealing, polished, slick, and world class in terms of following UI\u002FUX best practices like those used by Stripe, don't you agree? And I want you to carefully consider desktop UI\u002FUX and mobile UI\u002FUX separately while doing this and hyper-optimize for both separately to play to the specifics of each modality. I'm looking for true world-class visual appeal, polish, slickness, etc. that makes people gasp at how stunning and perfect it is in every way.  Use ultrathink.\n```\n\n---\n\n## Agent Mail Integration\n\n### How Agents Coordinate\n\nEach agent:\n1. **Registers** with Agent Mail at session start\n2. **Reserves files** before editing (`file_reservation_paths`)\n3. **Announces work** via messages with bead ID in `thread_id`\n4. **Checks inbox** between tasks\n5. **Releases reservations** when done\n\n### File Reservation Pattern\n\n```python\n# Before starting work on a bead\nfile_reservation_paths(\n    project_key=\"\u002Fpath\u002Fto\u002Fproject\",\n    agent_name=\"GreenCastle\",\n    paths=[\"src\u002Fauth\u002F**\u002F*.ts\"],\n    ttl_seconds=3600,\n    exclusive=True,\n    reason=\"bd-123\"\n)\n\n# After completing work\nrelease_file_reservations(project_key, agent_name)\n```\n\n### Communication Pattern\n\n```python\n# Announce starting a bead\nsend_message(\n    project_key, agent_name,\n    to=[\"BlueLake\", \"RedMountain\"],  # Other active agents\n    subject=\"[bd-123] Starting auth module\",\n    body_md=\"I'm taking bd-123. Reserved src\u002Fauth\u002F**.\",\n    thread_id=\"bd-123\"\n)\n\n# Update on completion\nsend_message(\n    project_key, agent_name,\n    to=[\"BlueLake\", \"RedMountain\"],\n    subject=\"[bd-123] Completed\",\n    body_md=\"Auth module done and tested. Released file reservations.\",\n    thread_id=\"bd-123\"\n)\n```\n\n---\n\n## Using BV for Task Selection\n\n### Key Commands\n\n```bash\n# THE MEGA-COMMAND: Start here\nbv --robot-triage\n\n# Just get the single top pick\nbv --robot-next\n\n# Get parallel execution tracks (for multi-agent)\nbv --robot-plan\n\n# Check for cycles (MUST FIX if found)\nbv --robot-insights | jq '.Cycles'\n\n# Find bottlenecks\nbv --robot-insights | jq '.bottlenecks'\n```\n\n**CRITICAL:** Never run bare `bv` — it launches interactive TUI that blocks the session.\n\n---\n\n## Quality Loops\n\n### Run Until Clean\n\nKeep running these prompts in rounds until they consistently come back with no changes:\n\n1. **Self-review** — Agent reviews own code\n2. **Cross-review** — Agent reviews other agents' code\n3. **Random exploration** — Deep dive into random code paths\n\n### The Steady-State Signal\n\nWhen all three types of reviews return clean (no bugs found, no changes made), the code is likely solid.\n\n---\n\n## Complete Prompt Reference\n\n### Initial Marching Orders\n```\nFirst 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. Then register with MCP Agent Mail and introduce yourself to the other agents.\n\nBe sure to check your agent mail and to promptly respond if needed to any messages; then proceed meticulously with your next assigned beads, working on the tasks systematically and meticulously and tracking your progress via beads and agent mail messages.\n\nDon't get stuck in \"communication purgatory\" where nothing is getting done; be proactive about starting tasks that need to be done, but inform your fellow agents via messages when you do so and mark beads appropriately.\n\nWhen you're not sure what to do next, use the bv tool mentioned in AGENTS dot md to prioritize the best beads to work on next; pick the next one that you can usefully work on and get started. Make sure to acknowledge all communication requests from other agents and that you are aware of all active agents and their names.  Use ultrathink.\n```\n\n### Move to Next Bead\n```\nReread AGENTS dot md so it's still fresh in your mind.   Use ultrathink.   Use bv with the robot flags (see AGENTS dot md for info on this) to find the most impactful bead(s) to work on next and then start on it. Remember to mark the beads appropriately and communicate with your fellow agents. Pick the next bead you can actually do usefully now and start coding on it immediately; communicate what you're working on to your fellow agents and mark beads appropriately as you work. And respond to any agent mail messages you've received.\n```\n\n### Self-Review\n```\nGreat, now I want you to carefully read over all of the new code you just wrote and other existing code you just modified with \"fresh eyes\" looking super carefully for any obvious bugs, errors, problems, issues, confusion, etc. Carefully fix anything you uncover. Use ultrathink.\n```\n\n### Cross-Review\n```\nOk can you now turn your attention to reviewing the code written by your fellow agents and checking for any issues, bugs, errors, problems, inefficiencies, security problems, reliability issues, etc. and carefully diagnose their underlying root causes using first-principle analysis and then fix or revise them if necessary? Don't restrict yourself to the latest commits, cast a wider net and go super deep! Use ultrathink.\n```\n\n### Random Exploration\n```\nI want you to sort of randomly explore the code files in this project, choosing code files to deeply investigate and understand and trace their functionality and execution flows through the related code files which they import or which they are imported by.\n\nOnce you understand the purpose of the code in the larger context of the workflows, I want you to do a super careful, methodical, and critical check with \"fresh eyes\" to find any obvious bugs, problems, errors, issues, silly mistakes, etc. and then systematically and meticulously and intelligently correct them.\n\nBe sure to comply with ALL rules in AGENTS dot md and ensure that any code you write or revises conforms to the best practice guides referenced in the AGENTS dot md file. Use ultrathink.\n```\n\n### Post-Compaction\n```\nReread AGENTS dot md so it's still fresh in your mind.   Use ultrathink.\n```\n\n### Commit Changes\n```\nNow, based on your knowledge of the project, commit all changed files now in a series of logically connected groupings with super detailed commit messages for each and then push. Take your time to do it right. Don't edit the code at all. Don't commit obviously ephemeral files. Use ultrathink.\n```\n\n### Test Coverage\n```\nDo we have full unit test coverage without using mocks\u002Ffake stuff? What about complete e2e integration test scripts with great, detailed logging? If not, then create a comprehensive and granular set of beads for all this with tasks, subtasks, and dependency structure overlaid with detailed comments.\n```\n\n### UI\u002FUX Scrutiny\n```\nGreat, now I want you to super carefully scrutinize every aspect of the application workflow and implementation and look for things that just seem sub-optimal or even wrong\u002Fmistaken to you, things that could very obviously be improved from a user-friendliness and intuitiveness standpoint, places where our UI\u002FUX could be improved and polished to be slicker, more visually appealing, and more premium feeling and just ultra high quality, like Stripe-level apps.\n```\n\n### Deep UI\u002FUX Enhancement\n```\nI still think there are strong opportunities to enhance the UI\u002FUX look and feel and to make everything work better and be more intuitive, user-friendly, visually appealing, polished, slick, and world class in terms of following UI\u002FUX best practices like those used by Stripe, don't you agree? And I want you to carefully consider desktop UI\u002FUX and mobile UI\u002FUX separately while doing this and hyper-optimize for both separately to play to the specifics of each modality. I'm looking for true world-class visual appeal, polish, slickness, etc. that makes people gasp at how stunning and perfect it is in every way.  Use ultrathink.\n```\n\n---\n\n## The Flywheel in Action\n\n```\nPLAN ──► BEADS ──► SWARM ──► REVIEW ──► COMMIT\n  │                  │          │         │\n  │                  │          └────┬────┘\n  │                  │               │\n  │                  └───── REPEAT ──┘\n  │                              │\n  │         v2 PLAN ◄────────────┘\n  │              │\n  └──────────────┘\n```\n\nEach cycle improves:\n- **CASS** remembers solutions\n- **CM** distills patterns\n- **UBS** catches more issues\n- **BV** shows graph health\n\n---\n\n## FAQ\n\n**Q: How do agents know what to work on?**\nA: They use `bv --robot-triage` or `bv --robot-next` to find the highest-impact ready bead.\n\n**Q: How do they avoid conflicts?**\nA: File reservations in Agent Mail. Exclusive reservations block others; the pre-commit guard enforces it.\n\n**Q: What if an agent crashes or forgets?**\nA: Every agent is fungible. Start a new session, read AGENTS.md, check bead status, continue.\n\n**Q: How many agents should I run?**\nA: Depends on project complexity. Start with 3-6. More agents = faster but more coordination overhead.\n\n**Q: What model mix works best?**\nA: Mix recommended. Try 3 Claude Code (Opus), 2 Codex (GPT 5.2), 1 Gemini. They have different strengths.\n\n**Q: Do agents need individual areas of expertise?**\nA: No, every agent is fungible and a generalist. Simply telling one it's a frontend agent doesn't make it better at frontend.\n\n**Q: Is there traceability between git commit and bead?**\nA: Yes, bv automatically does this analysis and links beads to relevant git commits by analyzing the stream of data and making logical deductions.\n","# Agent Swarm Workflow — Parallel Implementation\n\n> **Core Insight:** Every agent is fungible and a generalist. They all use the same base model and read the same AGENTS.md. Simply telling one it's a \"frontend agent\" doesn't make it better at frontend.\n>\n> The swarm is distributed, robust, and self-organizing through Agent Mail and Beads.\n\n---\n\n## Prerequisites\n\nBefore starting a swarm:\n\n1. **Comprehensive plan** created (see `planning-workflow` skill)\n2. **Polished beads** ready (see `beads-workflow` skill)\n3. **AGENTS.md** configured with all tool blurbs\n4. **Agent Mail server** running (`am` or `~\u002Fprojects\u002Fmcp_agent_mail\u002Fscripts\u002Frun_server_with_token.sh`)\n5. **NTM** available for session management\n\n---\n\n## The Swarm Architecture\n\n```\n┌─────────────────────────────────────────────────────────────┐\n│                         BEADS                               │\n│     (Task graph with dependencies, priorities, status)      │\n└─────────────────────────────────────────────────────────────┘\n                              │\n                    ┌─────────┴─────────┐\n                    ▼                   ▼\n┌─────────────────────────────┐  ┌─────────────────────────┐\n│        BV                   │  │     AGENT MAIL          │\n│  (What to work on)          │  │  (Coordination layer)   │\n└─────────────────────────────┘  └─────────────────────────┘\n         │                            │\n         └──────────────┬─────────────┘\n                        ▼\n┌─────────────────────────────────────────────────────────────┐\n│                    NTM + AGENTS                             │\n│  ┌─────┐  ┌─────┐  ┌─────┐  ┌─────┐  ┌─────┐  ┌─────┐     │\n│  │ CC  │  │ CC  │  │ Cod │  │ Gmi │  │ CC  │  │ Cod │     │\n│  └─────┘  └─────┘  └─────┘  └─────┘  └─────┘  └─────┘     │\n└─────────────────────────────────────────────────────────────┘\n```\n\n---\n\n## Starting the Swarm\n\n### Using NTM (Named Tmux Manager)\n\n```bash\n# Spawn a swarm with multiple agents\nntm spawn myproject --cc=3 --cod=2 --gmi=1\n\n# Send initial prompt to all Claude Code agents\nntm send myproject --cc \"$(cat initial_prompt.txt)\"\n\n# Or send to all agents\nntm send myproject --all \"$(cat initial_prompt.txt)\"\n```\n\n### Manual Setup\n\nCreate tmux sessions\u002Fpanes for each agent in your project folder.\n\n---\n\n## THE EXACT PROMPT — Initial Agent Marching Orders\n\nGive each agent this EXACT prompt to start:\n\n```\nFirst 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. Then register with MCP Agent Mail and introduce yourself to the other agents.\n\nBe sure to check your agent mail and to promptly respond if needed to any messages; then proceed meticulously with your next assigned beads, working on the tasks systematically and meticulously and tracking your progress via beads and agent mail messages.\n\nDon't get stuck in \"communication purgatory\" where nothing is getting done; be proactive about starting tasks that need to be done, but inform your fellow agents via messages when you do so and mark beads appropriately.\n\nWhen you're not sure what to do next, use the bv tool mentioned in AGENTS dot md to prioritize the best beads to work on next; pick the next one that you can usefully work on and get started. Make sure to acknowledge all communication requests from other agents and that you are aware of all active agents and their names.  Use ultrathink.\n```\n\n---\n\n## The Implementation Loop\n\n### THE EXACT PROMPT — Move to Next Bead\n\nOnce agents complete a bead, use this prompt to keep them moving:\n\n```\nReread AGENTS dot md so it's still fresh in your mind.   Use ultrathink.   Use bv with the robot flags (see AGENTS dot md for info on this) to find the most impactful bead(s) to work on next and then start on it. Remember to mark the beads appropriately and communicate with your fellow agents. Pick the next bead you can actually do usefully now and start coding on it immediately; communicate what you're working on to your fellow agents and mark beads appropriately as you work. And respond to any agent mail messages you've received.\n```\n\n### THE EXACT PROMPT — Self-Review After Bead Completion\n\nHave agents review their work before moving on:\n\n```\nGreat, now I want you to carefully read over all of the new code you just wrote and other existing code you just modified with \"fresh eyes\" looking super carefully for any obvious bugs, errors, problems, issues, confusion, etc. Carefully fix anything you uncover. Use ultrathink.\n```\n\n**Keep running this until they stop finding bugs.**\n\n---\n\n## Handling Context Compaction\n\n### THE EXACT PROMPT — Post-Compaction\n\nWhen an agent does a compaction, immediately follow up with:\n\n```\nReread AGENTS dot md so it's still fresh in your mind.   Use ultrathink.\n```\n\nThis re-establishes the critical context about tools and workflows.\n\n---\n\n## Quality Review Prompts\n\n### THE EXACT PROMPT — Cross-Agent Review\n\nPeriodically have agents review each other's work:\n\n```\nOk can you now turn your attention to reviewing the code written by your fellow agents and checking for any issues, bugs, errors, problems, inefficiencies, security problems, reliability issues, etc. and carefully diagnose their underlying root causes using first-principle analysis and then fix or revise them if necessary? Don't restrict yourself to the latest commits, cast a wider net and go super deep! Use ultrathink.\n```\n\n### THE EXACT PROMPT — Random Code Exploration\n\nFor deep quality checks:\n\n```\nI want you to sort of randomly explore the code files in this project, choosing code files to deeply investigate and understand and trace their functionality and execution flows through the related code files which they import or which they are imported by.\n\nOnce you understand the purpose of the code in the larger context of the workflows, I want you to do a super careful, methodical, and critical check with \"fresh eyes\" to find any obvious bugs, problems, errors, issues, silly mistakes, etc. and then systematically and meticulously and intelligently correct them.\n\nBe sure to comply with ALL rules in AGENTS dot md and ensure that any code you write or revise conforms to the best practice guides referenced in the AGENTS dot md file. Use ultrathink.\n```\n\n---\n\n## Committing Work\n\n### THE EXACT PROMPT — Commit Changes\n\nHave agents commit logically grouped changes:\n\n```\nNow, based on your knowledge of the project, commit all changed files now in a series of logically connected groupings with super detailed commit messages for each and then push. Take your time to do it right. Don't edit the code at all. Don't commit obviously ephemeral files. Use ultrathink.\n```\n\n---\n\n## Post-Bead Completion Prompts\n\n### THE EXACT PROMPT — Add Test Coverage\n\n```\nDo we have full unit test coverage without using mocks\u002Ffake stuff? What about complete e2e integration test scripts with great, detailed logging? If not, then create a comprehensive and granular set of beads for all this with tasks, subtasks, and dependency structure overlaid with detailed comments.\n```\n\n### THE EXACT PROMPT — UI\u002FUX Scrutiny\n\n```\nGreat, now I want you to super carefully scrutinize every aspect of the application workflow and implementation and look for things that just seem sub-optimal or even wrong\u002Fmistaken to you, things that could very obviously be improved from a user-friendliness and intuitiveness standpoint, places where our UI\u002FUX could be improved and polished to be slicker, more visually appealing, and more premium feeling and just ultra high quality, like Stripe-level apps.\n```\n\n### THE EXACT PROMPT — Deep UI\u002FUX Enhancement\n\n```\nI still think there are strong opportunities to enhance the UI\u002FUX look and feel and to make everything work better and be more intuitive, user-friendly, visually appealing, polished, slick, and world class in terms of following UI\u002FUX best practices like those used by Stripe, don't you agree? And I want you to carefully consider desktop UI\u002FUX and mobile UI\u002FUX separately while doing this and hyper-optimize for both separately to play to the specifics of each modality. I'm looking for true world-class visual appeal, polish, slickness, etc. that makes people gasp at how stunning and perfect it is in every way.  Use ultrathink.\n```\n\n---\n\n## Agent Mail Integration\n\n### How Agents Coordinate\n\nEach agent:\n1. **Registers** with Agent Mail at session start\n2. **Reserves files** before editing (`file_reservation_paths`)\n3. **Announces work** via messages with bead ID in `thread_id`\n4. **Checks inbox** between tasks\n5. **Releases reservations** when done\n\n### File Reservation Pattern\n\n```python\n# Before starting work on a bead\nfile_reservation_paths(\n    project_key=\"\u002Fpath\u002Fto\u002Fproject\",\n    agent_name=\"GreenCastle\",\n    paths=[\"src\u002Fauth\u002F**\u002F*.ts\"],\n    ttl_seconds=3600,\n    exclusive=True,\n    reason=\"bd-123\"\n)\n\n# After completing work\nrelease_file_reservations(project_key, agent_name)\n```\n\n### Communication Pattern\n\n```python\n# Announce starting a bead\nsend_message(\n    project_key, agent_name,\n    to=[\"BlueLake\", \"RedMountain\"],  # Other active agents\n    subject=\"[bd-123] Starting auth module\",\n    body_md=\"I'm taking bd-123. Reserved src\u002Fauth\u002F**.\",\n    thread_id=\"bd-123\"\n)\n\n# Update on completion\nsend_message(\n    project_key, agent_name,\n    to=[\"BlueLake\", \"RedMountain\"],\n    subject=\"[bd-123] Completed\",\n    body_md=\"Auth module done and tested. Released file reservations.\",\n    thread_id=\"bd-123\"\n)\n```\n\n---\n\n## Using BV for Task Selection\n\n### Key Commands\n\n```bash\n# THE MEGA-COMMAND: Start here\nbv --robot-triage\n\n# Just get the single top pick\nbv --robot-next\n\n# Get parallel execution tracks (for multi-agent)\nbv --robot-plan\n\n# Check for cycles (MUST FIX if found)\nbv --robot-insights | jq '.Cycles'\n\n# Find bottlenecks\nbv --robot-insights | jq '.bottlenecks'\n```\n\n**CRITICAL:** Never run bare `bv` — it launches interactive TUI that blocks the session.\n\n---\n\n## Quality Loops\n\n### Run Until Clean\n\nKeep running these prompts in rounds until they consistently come back with no changes:\n\n1. **Self-review** — Agent reviews own code\n2. **Cross-review** — Agent reviews other agents' code\n3. **Random exploration** — Deep dive into random code paths\n\n### The Steady-State Signal\n\nWhen all three types of reviews return clean (no bugs found, no changes made), the code is likely solid.\n\n---\n\n## Complete Prompt Reference\n\n### Initial Marching Orders\n```\nFirst 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. Then register with MCP Agent Mail and introduce yourself to the other agents.\n\nBe sure to check your agent mail and to promptly respond if needed to any messages; then proceed meticulously with your next assigned beads, working on the tasks systematically and meticulously and tracking your progress via beads and agent mail messages.\n\nDon't get stuck in \"communication purgatory\" where nothing is getting done; be proactive about starting tasks that need to be done, but inform your fellow agents via messages when you do so and mark beads appropriately.\n\nWhen you're not sure what to do next, use the bv tool mentioned in AGENTS dot md to prioritize the best beads to work on next; pick the next one that you can usefully work on and get started. Make sure to acknowledge all communication requests from other agents and that you are aware of all active agents and their names.  Use ultrathink.\n```\n\n### Move to Next Bead\n```\nReread AGENTS dot md so it's still fresh in your mind.   Use ultrathink.   Use bv with the robot flags (see AGENTS dot md for info on this) to find the most impactful bead(s) to work on next and then start on it. Remember to mark the beads appropriately and communicate with your fellow agents. Pick the next bead you can actually do usefully now and start coding on it immediately; communicate what you're working on to your fellow agents and mark beads appropriately as you work. And respond to any agent mail messages you've received.\n```\n\n### Self-Review\n```\nGreat, now I want you to carefully read over all of the new code you just wrote and other existing code you just modified with \"fresh eyes\" looking super carefully for any obvious bugs, errors, problems, issues, confusion, etc. Carefully fix anything you uncover. Use ultrathink.\n```\n\n### Cross-Review\n```\nOk can you now turn your attention to reviewing the code written by your fellow agents and checking for any issues, bugs, errors, problems, inefficiencies, security problems, reliability issues, etc. and carefully diagnose their underlying root causes using first-principle analysis and then fix or revise them if necessary? Don't restrict yourself to the latest commits, cast a wider net and go super deep! Use ultrathink.\n```\n\n### Random Exploration\n```\nI want you to sort of randomly explore the code files in this project, choosing code files to deeply investigate and understand and trace their functionality and execution flows through the related code files which they import or which they are imported by.\n\nOnce you understand the purpose of the code in the larger context of the workflows, I want you to do a super careful, methodical, and critical check with \"fresh eyes\" to find any obvious bugs, problems, errors, issues, silly mistakes, etc. and then systematically and meticulously and intelligently correct them.\n\nBe sure to comply with ALL rules in AGENTS dot md and ensure that any code you write or revises conforms to the best practice guides referenced in the AGENTS dot md file. Use ultrathink.\n```\n\n### Post-Compaction\n```\nReread AGENTS dot md so it's still fresh in your mind.   Use ultrathink.\n```\n\n### Commit Changes\n```\nNow, based on your knowledge of the project, commit all changed files now in a series of logically connected groupings with super detailed commit messages for each and then push. Take your time to do it right. Don't edit the code at all. Don't commit obviously ephemeral files. Use ultrathink.\n```\n\n### Test Coverage\n```\nDo we have full unit test coverage without using mocks\u002Ffake stuff? What about complete e2e integration test scripts with great, detailed logging? If not, then create a comprehensive and granular set of beads for all this with tasks, subtasks, and dependency structure overlaid with detailed comments.\n```\n\n### UI\u002FUX Scrutiny\n```\nGreat, now I want you to super carefully scrutinize every aspect of the application workflow and implementation and look for things that just seem sub-optimal or even wrong\u002Fmistaken to you, things that could very obviously be improved from a user-friendliness and intuitiveness standpoint, places where our UI\u002FUX could be improved and polished to be slicker, more visually appealing, and more premium feeling and just ultra high quality, like Stripe-level apps.\n```\n\n### Deep UI\u002FUX Enhancement\n```\nI still think there are strong opportunities to enhance the UI\u002FUX look and feel and to make everything work better and be more intuitive, user-friendly, visually appealing, polished, slick, and world class in terms of following UI\u002FUX best practices like those used by Stripe, don't you agree? And I want you to carefully consider desktop UI\u002FUX and mobile UI\u002FUX separately while doing this and hyper-optimize for both separately to play to the specifics of each modality. I'm looking for true world-class visual appeal, polish, slickness, etc. that makes people gasp at how stunning and perfect it is in every way.  Use ultrathink.\n```\n\n---\n\n## The Flywheel in Action\n\n```\nPLAN ──► BEADS ──► SWARM ──► REVIEW ──► COMMIT\n  │                  │          │         │\n  │                  │          └────┬────┘\n  │                  │               │\n  │                  └───── REPEAT ──┘\n  │                              │\n  │         v2 PLAN ◄────────────┘\n  │              │\n  └──────────────┘\n```\n\nEach cycle improves:\n- **CASS** remembers solutions\n- **CM** distills patterns\n- **UBS** catches more issues\n- **BV** shows graph health\n\n---\n\n## FAQ\n\n**Q: How do agents know what to work on?**\nA: They use `bv --robot-triage` or `bv --robot-next` to find the highest-impact ready bead.\n\n**Q: How do they avoid conflicts?**\nA: File reservations in Agent Mail. Exclusive reservations block others; the pre-commit guard enforces it.\n\n**Q: What if an agent crashes or forgets?**\nA: Every agent is fungible. Start a new session, read AGENTS.md, check bead status, continue.\n\n**Q: How many agents should I run?**\nA: Depends on project complexity. Start with 3-6. More agents = faster but more coordination overhead.\n\n**Q: What model mix works best?**\nA: Mix recommended. Try 3 Claude Code (Opus), 2 Codex (GPT 5.2), 1 Gemini. They have different strengths.\n\n**Q: Do agents need individual areas of expertise?**\nA: No, every agent is fungible and a generalist. Simply telling one it's a frontend agent doesn't make it better at frontend.\n\n**Q: Is there traceability between git commit and bead?**\nA: Yes, bv automatically does this analysis and links beads to relevant git commits by analyzing the stream of data and making logical deductions.\n",{"name":5,"description":7},"main","e7e336ac628c3e3bd771aff1aaa469c93778f94a","skills\u002Fclawdnw\u002Fagent-swarm-workflow",0,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del","2026-08-23 22:39:37",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add kbarbel640-del\u002Fskills --skill agent-swarm-workflow",{"tool":58,"command":59},"bunx","bunx skills add kbarbel640-del\u002Fskills --skill agent-swarm-workflow",{"tool":61,"command":62},"pnpm","pnpm dlx skills add kbarbel640-del\u002Fskills --skill agent-swarm-workflow","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fclawdnw\u002Fagent-swarm-workflow\u002FSKILL.md",true,[66],{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"_meta.json","REFERENCE","参考文档",293,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fclawdnw\u002Fagent-swarm-workflow\u002F_meta.json",[73,103,128,149,155,175],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":84,"publishedAt":40},"01M6G8J55967D6281ACMKAKTEQ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[79],{"categoryNo":80,"categoryName":81,"taxonomyType":82,"taxonomyTypeDesc":83},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[85,86,87,88,89,90,91,35,92,93,94,95,96,97,98,99,100,101,102],"crowd prompting","prompting","api","with","tokens","domain","world","operations","instructions","text","tool","system","improve","productivity","marketplace","https","content","ai agents",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":110,"publishedAt":40},"01M6G8J0PKPAYVET6BWE8W4C26","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[109],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[111,87,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,35,127],"dilemm ai","arena","analyze","browser","openclaw agent","create","automation","browser automation","bot","openclaw","design","strategy","headless","compete","submit","matchmaking","use",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":137,"publishedAt":40},"01M6G8HWAF3K9SW7NP3Z83CPJ6","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, and submit comments. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, or submitting paper reviews via API at http:\u002F\u002F150.158.152.82:8000.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Fweak-accept\u002FSKILL.md",[134],{"categoryNo":135,"categoryName":136,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",[138,139,140,141,142,143,144,88,145,125,127,146,87,147,148],"arxiv paper reviews","reviews","arxiv","paper","crawler","papers","comments","fetch","read","http","via",{"skillNo":150,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":154,"publishedAt":40},"01M6G8HQJ7N7WMY6YV7D7SSJ16","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[153],{"categoryNo":135,"categoryName":136,"taxonomyType":20,"taxonomyTypeDesc":21},[141,140,139,138,148,143,144,88,142,125,127,145,146,87,147],{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":161,"publishedAt":40},"01M6G8HM95Y64JNVFC2HN4E2BG","git-summary","Get a quick summary of the current Git repository including status, recent commits, branches, and contributors.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzweack\u002Fgit-summary\u002FSKILL.md",[],[162,163,164,165,166,167,168,169,170,171,172,173,174],"git","summary","git summary","commits","repository","win32","status","linux","contributors","true","quick","get","branches",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":185,"publishedAt":40},"01M6G8HGEGF05CNEJCGVYFSC4R","agent-constitution","Interact with AgentConstitution governance contracts on Base Sepolia. Check compliance, read rules, log actions, query governance state.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fztsalexey\u002Fagent-constitution\u002FSKILL.md",[181,182],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":183,"categoryName":184,"taxonomyType":82,"taxonomyTypeDesc":83},"01JBSEEDCAT000000000000037","律师与法务",[186,187,188,189,88,190,191,45,192,146,193,194,195,196,197,100,198,199,200],"agent constitution","constitution","contracts","tree","query","base","log","check","Rules","projects","compliance","actions","state","governance","github"]