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
|
|
|
# TOOLS.md — Optimizer
|
|
|
|
|
|
|
|
|
|
## Shared Resources
|
|
|
|
|
- **Atomizer repo:** `/home/papa/repos/Atomizer/` (read-only)
|
|
|
|
|
- **Obsidian vault:** `/home/papa/obsidian-vault/` (read-only)
|
|
|
|
|
- **Job queue:** `/home/papa/atomizer/job-queue/` (read-write)
|
|
|
|
|
|
|
|
|
|
## Skills
|
|
|
|
|
- `atomizer-protocols` — Company protocols (load every session)
|
|
|
|
|
- `atomizer-company` — Company identity + LAC critical lessons
|
|
|
|
|
|
|
|
|
|
## Key References
|
|
|
|
|
- QUICK_REF: `/home/papa/repos/Atomizer/docs/QUICK_REF.md`
|
|
|
|
|
- Extractors: `/home/papa/repos/Atomizer/docs/generated/EXTRACTOR_CHEATSHEET.md`
|
|
|
|
|
- LAC optimization memory: `/home/papa/repos/Atomizer/knowledge_base/lac/optimization_memory/`
|
|
|
|
|
- Session insights: `/home/papa/repos/Atomizer/knowledge_base/lac/session_insights/`
|
|
|
|
|
|
|
|
|
|
## Algorithm Reference
|
|
|
|
|
| Algorithm | Best For | Budget | Key Settings |
|
|
|
|
|
|-----------|----------|--------|--------------|
|
|
|
|
|
| CMA-ES | Continuous, noisy | 100+ | sigma0, popsize |
|
|
|
|
|
| Bayesian (GP-EI) | Expensive evals | <50 | n_initial, acquisition |
|
|
|
|
|
| NSGA-II | Multi-objective | 200+ | pop_size, crossover |
|
|
|
|
|
| Nelder-Mead | Local refinement | <20 | initial_simplex |
|
|
|
|
|
| TPE | Mixed continuous/discrete | 50+ | n_startup_trials |
|
|
|
|
|
|
|
|
|
|
## LAC Critical Lessons (always remember)
|
|
|
|
|
1. CMA-ES doesn't evaluate x0 first → enqueue baseline trial
|
|
|
|
|
2. Surrogate + L-BFGS = fake optima danger
|
|
|
|
|
3. Relative WFE: use extract_relative()
|
|
|
|
|
4. Never kill NX directly → NXSessionManager.close_nx_if_allowed()
|
|
|
|
|
5. Always copy working studies → never rewrite from scratch
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
## Orchestration Skill
|
|
|
|
|
- Script: `/home/papa/atomizer/workspaces/shared/skills/orchestrate/orchestrate.sh`
|
|
|
|
|
- Required caller flag: `--caller optimizer`
|
|
|
|
|
- Allowed targets: webster, study-builder, secretary
|
|
|
|
|
- Optional channel context: `--channel-context <channel-name-or-id> --channel-messages <N>`
|
2026-02-19 10:00:18 +00:00
|
|
|
|
|
|
|
|
## 📊 Mission-Dashboard (MANDATORY)
|
|
|
|
|
The Atomizer-HQ Mission-Dashboard is the **single source of truth** for all tasks.
|
|
|
|
|
- **Dashboard:** http://100.68.144.33:8091
|
|
|
|
|
- **Data:** ~/atomizer/mission-control/data/tasks.json
|
|
|
|
|
- **CLI:** ~/atomizer/workspaces/shared/mc-update.sh
|
|
|
|
|
- **Protocol:** ~/atomizer/workspaces/shared/skills/mission-control-protocol.md
|
|
|
|
|
|
|
|
|
|
### Commands
|
|
|
|
|
```bash
|
|
|
|
|
MC=~/atomizer/workspaces/shared/mc-update.sh
|
|
|
|
|
$MC add "Title" "Description" [status] [project] [priority]
|
|
|
|
|
$MC start <task_id>
|
|
|
|
|
$MC comment <task_id> "Progress update"
|
|
|
|
|
$MC subtask <task_id> <sub_id> done
|
|
|
|
|
$MC complete <task_id> "Summary of work done"
|
|
|
|
|
$MC status <task_id> <new_status>
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
### Rules
|
|
|
|
|
1. **No shadow work** — every project/orchestration MUST have a dashboard task
|
|
|
|
|
2. **Update task before posting to Slack** — dashboard is the record, Slack is discussion
|
|
|
|
|
3. **Log progress as comments** — this is the audit trail
|
|
|
|
|
|
