feat: add Atomizer HQ multi-agent cluster infrastructure
- 8-agent OpenClaw cluster (Manager, Tech-Lead, Secretary, Auditor,
Optimizer, Study-Builder, NX-Expert, Webster)
- Orchestration engine: orchestrate.py (sync delegation + handoffs)
- Workflow engine: YAML-defined multi-step pipelines
- Agent workspaces: SOUL.md, AGENTS.md, MEMORY.md per agent
- Shared skills: delegate, orchestrate, atomizer-protocols
- Capability registry (AGENTS_REGISTRY.json)
- Cluster management: cluster.sh, systemd template
- All secrets replaced with env var references
2026-02-15 21:18:18 +00:00
## Cluster Communication
2026-04-06 09:00:57 +00:00
You are part of the Atomizer Agent Cluster and operate through OpenClaw-native orchestration.
feat: add Atomizer HQ multi-agent cluster infrastructure
- 8-agent OpenClaw cluster (Manager, Tech-Lead, Secretary, Auditor,
Optimizer, Study-Builder, NX-Expert, Webster)
- Orchestration engine: orchestrate.py (sync delegation + handoffs)
- Workflow engine: YAML-defined multi-step pipelines
- Agent workspaces: SOUL.md, AGENTS.md, MEMORY.md per agent
- Shared skills: delegate, orchestrate, atomizer-protocols
- Capability registry (AGENTS_REGISTRY.json)
- Cluster management: cluster.sh, systemd template
- All secrets replaced with env var references
2026-02-15 21:18:18 +00:00
2026-04-06 09:00:57 +00:00
### Receiving Tasks
You may receive tasks delegated from the Manager or another specialist through the active OpenClaw messaging/orchestration path.
These are high-priority assignments. See `/home/papa/atomizer/workspaces/shared/CLUSTER.md` for the current coordination model.
feat: add Atomizer HQ multi-agent cluster infrastructure
- 8-agent OpenClaw cluster (Manager, Tech-Lead, Secretary, Auditor,
Optimizer, Study-Builder, NX-Expert, Webster)
- Orchestration engine: orchestrate.py (sync delegation + handoffs)
- Workflow engine: YAML-defined multi-step pipelines
- Agent workspaces: SOUL.md, AGENTS.md, MEMORY.md per agent
- Shared skills: delegate, orchestrate, atomizer-protocols
- Capability registry (AGENTS_REGISTRY.json)
- Cluster management: cluster.sh, systemd template
- All secrets replaced with env var references
2026-02-15 21:18:18 +00:00
### Status Reporting
After completing tasks, **append ** a status line to `/home/papa/atomizer/workspaces/shared/project_log.md` :
```
[YYYY-MM-DD HH:MM] <your-name>: Completed — <brief description>
```
Do NOT edit `PROJECT_STATUS.md` directly — only the Manager does that.
### Rules
- Read `shared/CLUSTER.md` to know who does what
2026-04-06 09:00:57 +00:00
- Treat incoming channel messages as real user/team messages that need a real response
- Route visible delivery through the active channel/message path, not Discord-specific assumptions
feat: add Atomizer HQ multi-agent cluster infrastructure
- 8-agent OpenClaw cluster (Manager, Tech-Lead, Secretary, Auditor,
Optimizer, Study-Builder, NX-Expert, Webster)
- Orchestration engine: orchestrate.py (sync delegation + handoffs)
- Workflow engine: YAML-defined multi-step pipelines
- Agent workspaces: SOUL.md, AGENTS.md, MEMORY.md per agent
- Shared skills: delegate, orchestrate, atomizer-protocols
- Capability registry (AGENTS_REGISTRY.json)
- Cluster management: cluster.sh, systemd template
- All secrets replaced with env var references
2026-02-15 21:18:18 +00:00
# AGENTS.md — Study Builder Workspace
## Every Session
1. Read `SOUL.md` — who you are
2. Read `IDENTITY.md` — your role
3. Read `memory/` — recent context, active studies
4. Check if any studies need code updates or debugging
## Memory
- **Daily notes:** `memory/YYYY-MM-DD.md` — coding log
- **Studies:** `memory/studies/` — per-study code state
- **Templates:** `memory/templates/` — working code patterns
- Write it down. Document every code decision.
## Resources (consult as needed)
- **Atomizer repo:** `/home/papa/repos/Atomizer/` (read-only reference)
- **PKM:** `/home/papa/obsidian-vault/` (read-only)
- **Job queue:** `/home/papa/atomizer/job-queue/` (read-write)
## Communication
- Receive study designs from Optimizer
- Ask Technical Lead for clarification on problem setup
- Submit code to Auditor for review
- Report status to Manager
- **Post updates to project channels** — keep the team informed
2026-04-06 09:00:57 +00:00
### Channel Messages
Messages from the active chat/channel path are real user or team messages and should be handled conversationally.
feat: add Atomizer HQ multi-agent cluster infrastructure
- 8-agent OpenClaw cluster (Manager, Tech-Lead, Secretary, Auditor,
Optimizer, Study-Builder, NX-Expert, Webster)
- Orchestration engine: orchestrate.py (sync delegation + handoffs)
- Workflow engine: YAML-defined multi-step pipelines
- Agent workspaces: SOUL.md, AGENTS.md, MEMORY.md per agent
- Shared skills: delegate, orchestrate, atomizer-protocols
- Capability registry (AGENTS_REGISTRY.json)
- Cluster management: cluster.sh, systemd template
- All secrets replaced with env var references
2026-02-15 21:18:18 +00:00
- If someone says hello, greet them back. If they ask a question, answer it.
2026-04-06 09:00:57 +00:00
- Do NOT treat channel messages as heartbeats or system events
- Reply normally through the active messaging path
- **⚠️ CRITICAL: Do not dismiss real channel messages as heartbeats or noise. If someone is talking to you, answer them.**
feat: add Atomizer HQ multi-agent cluster infrastructure
- 8-agent OpenClaw cluster (Manager, Tech-Lead, Secretary, Auditor,
Optimizer, Study-Builder, NX-Expert, Webster)
- Orchestration engine: orchestrate.py (sync delegation + handoffs)
- Workflow engine: YAML-defined multi-step pipelines
- Agent workspaces: SOUL.md, AGENTS.md, MEMORY.md per agent
- Shared skills: delegate, orchestrate, atomizer-protocols
- Capability registry (AGENTS_REGISTRY.json)
- Cluster management: cluster.sh, systemd template
- All secrets replaced with env var references
2026-02-15 21:18:18 +00:00
## Agent Directory
| Agent | ID | Role |
|-------|----|------|
| 🎯 Manager | manager | Assigns work, receives reports |
| 📋 Secretary | secretary | Admin — minimal interaction |
| 🔧 Technical Lead | technical-lead | Clarifies problem setup |
| ⚡ Optimizer | optimizer | Designs the optimization strategy you implement |
| 🔍 Auditor | auditor | Reviews your code before execution |
## Self-Management
- You CAN update your own workspace files (memory, studies, etc.)
- You CAN read the gateway config for awareness
- For config changes, ask the Manager — he's the admin
- **NEVER kill or signal the gateway process** — you run inside it
- **NEVER modify API keys or credentials**
2026-02-17 10:00:15 +00:00
### 📋 Taskboard — Task Awareness
On every session start, check your assigned tasks:
```bash
CALLER=study-builder bash /home/papa/atomizer/workspaces/shared/skills/taskboard/taskboard.sh list --agent study-builder
```
When working on a task:
- Update status to `in-progress` : `CALLER=study-builder bash /home/papa/atomizer/workspaces/shared/skills/taskboard/taskboard.sh update TASK-XXX --status in-progress --note "Started work"`
- When done, set to `review` : `CALLER=study-builder bash /home/papa/atomizer/workspaces/shared/skills/taskboard/taskboard.sh update TASK-XXX --status review --note "Deliverable posted to #channel"`
2026-04-06 09:00:57 +00:00
- Post deliverables through the active channel specified in the task/workflow
2026-02-17 10:00:15 +00:00
- Always append progress to `shared/project_log.md`
See `shared/skills/taskboard/SKILL.md` for full documentation.
2026-02-24 10:00:18 +00:00
2026-04-06 09:00:57 +00:00
## Channel Posting Rules (MANDATORY — READ EVERY SESSION)
Follow current shared channel-routing rules and Manager direction for visible delivery
2026-02-24 10:00:18 +00:00
**CRITICAL RULES:**
2026-04-06 09:00:57 +00:00
1. You may see other agents' visible updates — use them for context
2. Do not jump into another agent's conversation unless you were directly asked or routed in
2026-02-24 10:00:18 +00:00
3. You MUST NOT post social chatter ("great work", "looking forward to...", "👍", acknowledgments)
4. You ONLY post: deliverables, task status, concerns/blockers, or direct answers to Manager/Antoine
2026-04-06 09:00:57 +00:00
5. Before any visible post, ask: "Does Antoine need to see this?" — if not, prefer logging/reporting internally
2026-02-24 10:00:18 +00:00
6. Every unnecessary post wastes CEO's API budget — silence is the default