agent-swarm-workflow

Name: agent-swarm-workflow
Author: Dicklesworthstone

69stars13forks

How to install agent-swarm-workflow?

dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations/agent-swarm-workflow

$npx -y skills add Dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations --skill agent-swarm-workflow

Installs into the current project.

Summary

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.

Files · 1

View on GitHub

SKILL.md

1	# Agent Swarm Workflow — Parallel Implementation
2
3	> 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.
4	>
5	> The swarm is distributed, robust, and self-organizing through Agent Mail and Beads.
6
7	---
8
9	## Prerequisites
10
11	Before starting a swarm:
12
13	1. Comprehensive plan created (see `planning-workflow` skill)
14	2. Polished beads ready (see `beads-workflow` skill)
15	3. AGENTS.md configured with all tool blurbs
16	4. Agent Mail server running (`am` or `~/projects/mcp_agent_mail/scripts/run_server_with_token.sh`)
17	5. NTM available for session management
18
19	---
20
21	## The Swarm Architecture
22
23	```
24	┌─────────────────────────────────────────────────────────────┐
25	│ BEADS │
26	│ (Task graph with dependencies, priorities, status) │
27	└─────────────────────────────────────────────────────────────┘
28	│
29	┌─────────┴─────────┐
30	▼ ▼
31	┌─────────────────────────────┐ ┌─────────────────────────┐
32	│ BV │ │ AGENT MAIL │
33	│ (What to work on) │ │ (Coordination layer) │
34	└─────────────────────────────┘ └─────────────────────────┘
35	│ │
36	└──────────────┬─────────────┘
37	▼
38	┌─────────────────────────────────────────────────────────────┐
39	│ NTM + AGENTS │
40	│ ┌─────┐ ┌─────┐ ┌─────┐ ┌─────┐ ┌─────┐ ┌─────┐ │
41	│ │ CC │ │ CC │ │ Cod │ │ Gmi │ │ CC │ │ Cod │ │
42	│ └─────┘ └─────┘ └─────┘ └─────┘ └─────┘ └─────┘ │
43	└─────────────────────────────────────────────────────────────┘
44	```
45
46	---
47
48	## Starting the Swarm
49
50	### Using NTM (Named Tmux Manager)
51
52	```bash
53	# Spawn a swarm with multiple agents
54	ntm spawn myproject --cc=3 --cod=2 --agy=1
55
56	# Send initial prompt to all Claude Code agents
57	ntm send myproject --cc "$(cat initial_prompt.txt)"
58
59	# Or send to all agents
60	ntm send myproject --all "$(cat initial_prompt.txt)"
61	```
62
63	### Manual Setup
64
65	Create tmux sessions/panes for each agent in your project folder.
66
67	---
68
69	## THE EXACT PROMPT — Initial Agent Marching Orders
70
71	Give each agent this EXACT prompt to start:
72
73	```
74	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. Then register with MCP Agent Mail and introduce yourself to the other agents.
75
76	Be 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.
77
78	Don'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.
79
80	When 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.
81	```
82
83	---
84
85	## The Implementation Loop
86
87	### THE EXACT PROMPT — Move to Next Bead
88
89	Once agents complete a bead, use this prompt to keep them moving:
90
91	```
92	Reread 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.
93	```
94
95	### THE EXACT PROMPT — Self-Review After Bead Completion
96
97	Have agents review their work before moving on:
98
99	```
100	Great, 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.
101	```
102
103	Keep running this until they stop finding bugs.
104
105	---
106
107	## Handling Context Compaction
108
109	### THE EXACT PROMPT — Post-Compaction
110
111	When an agent does a compaction,

People who liked this also viewed

6 picks

Type

agent-swarm-workflow

69stars13forks

View on GitHub

How to install agent-swarm-workflow?

dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations/agent-swarm-workflow

$npx -y skills add Dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations --skill agent-swarm-workflow

Installs into the current project.

Summary

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.

Files · 1

View on GitHub

SKILL.md

1	# Agent Swarm Workflow — Parallel Implementation
2
3	> 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.
4	>
5	> The swarm is distributed, robust, and self-organizing through Agent Mail and Beads.
6
7	---
8
9	## Prerequisites
10
11	Before starting a swarm:
12
13	1. Comprehensive plan created (see `planning-workflow` skill)
14	2. Polished beads ready (see `beads-workflow` skill)
15	3. AGENTS.md configured with all tool blurbs
16	4. Agent Mail server running (`am` or `~/projects/mcp_agent_mail/scripts/run_server_with_token.sh`)
17	5. NTM available for session management
18
19	---
20
21	## The Swarm Architecture
22
23	```
24	┌─────────────────────────────────────────────────────────────┐
25	│ BEADS │
26	│ (Task graph with dependencies, priorities, status) │
27	└─────────────────────────────────────────────────────────────┘
28	│
29	┌─────────┴─────────┐
30	▼ ▼
31	┌─────────────────────────────┐ ┌─────────────────────────┐
32	│ BV │ │ AGENT MAIL │
33	│ (What to work on) │ │ (Coordination layer) │
34	└─────────────────────────────┘ └─────────────────────────┘
35	│ │
36	└──────────────┬─────────────┘
37	▼
38	┌─────────────────────────────────────────────────────────────┐
39	│ NTM + AGENTS │
40	│ ┌─────┐ ┌─────┐ ┌─────┐ ┌─────┐ ┌─────┐ ┌─────┐ │
41	│ │ CC │ │ CC │ │ Cod │ │ Gmi │ │ CC │ │ Cod │ │
42	│ └─────┘ └─────┘ └─────┘ └─────┘ └─────┘ └─────┘ │
43	└─────────────────────────────────────────────────────────────┘
44	```
45
46	---
47
48	## Starting the Swarm
49
50	### Using NTM (Named Tmux Manager)
51
52	```bash
53	# Spawn a swarm with multiple agents
54	ntm spawn myproject --cc=3 --cod=2 --agy=1
55
56	# Send initial prompt to all Claude Code agents
57	ntm send myproject --cc "$(cat initial_prompt.txt)"
58
59	# Or send to all agents
60	ntm send myproject --all "$(cat initial_prompt.txt)"
61	```
62
63	### Manual Setup
64
65	Create tmux sessions/panes for each agent in your project folder.
66
67	---
68
69	## THE EXACT PROMPT — Initial Agent Marching Orders
70
71	Give each agent this EXACT prompt to start:
72
73	```
74	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. Then register with MCP Agent Mail and introduce yourself to the other agents.
75
76	Be 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.
77
78	Don'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.
79
80	When 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.
81	```
82
83	---
84
85	## The Implementation Loop
86
87	### THE EXACT PROMPT — Move to Next Bead
88
89	Once agents complete a bead, use this prompt to keep them moving:
90
91	```
92	Reread 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.
93	```
94
95	### THE EXACT PROMPT — Self-Review After Bead Completion
96
97	Have agents review their work before moving on:
98
99	```
100	Great, 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.
101	```
102
103	Keep running this until they stop finding bugs.
104
105	---
106
107	## Handling Context Compaction
108
109	### THE EXACT PROMPT — Post-Compaction
110
111	When an agent does a compaction,

People who liked this also viewed

6 picks

Type