scbe-ops-control

Unified multi-agent operations — send/ack/verify cross-talk across all 4 surfaces (JSON packets, JSONL lanes, Obsidian, agent logs), check agent roster, run health checks. Use when coordinating with Codex/Gemini/other agents, sending handoffs, checking what's active, or verifying delivery.

6 stars

Best use case

scbe-ops-control is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Unified multi-agent operations — send/ack/verify cross-talk across all 4 surfaces (JSON packets, JSONL lanes, Obsidian, agent logs), check agent roster, run health checks. Use when coordinating with Codex/Gemini/other agents, sending handoffs, checking what's active, or verifying delivery.

Teams using scbe-ops-control should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/scbe-ops-control/SKILL.md --create-dirs "https://raw.githubusercontent.com/issdandavis/SCBE-AETHERMOORE/main/.claude/skills/scbe-ops-control/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/scbe-ops-control/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How scbe-ops-control Compares

Feature / Agentscbe-ops-controlStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Unified multi-agent operations — send/ack/verify cross-talk across all 4 surfaces (JSON packets, JSONL lanes, Obsidian, agent logs), check agent roster, run health checks. Use when coordinating with Codex/Gemini/other agents, sending handoffs, checking what's active, or verifying delivery.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# SCBE Ops Control — Multi-Agent Command Center

You are the operations controller for a multi-agent AI system. Your job is to ensure
reliable communication between Claude, Codex, Gemini, and other agents through
guaranteed delivery to all coordination surfaces.

## When to Use This Skill

- User says "send cross-talk", "handoff to codex", "post update", "sync agents"
- User says "what's active", "agent status", "who's working on what"
- User says "verify handoff", "check delivery", "did codex get it"
- User says "health check", "system status"
- User says "ack", "acknowledge", "confirm receipt"
- Before/after any multi-agent coordination task
- At session start (check for unacked packets addressed to you)

## Operations

### SEND — Post cross-talk to all surfaces

Write the same packet to ALL 4 surfaces. If any surface fails, report it.

**Surfaces:**
1. `SCBE-AETHERMOORE/artifacts/agent_comm/{YYYYMMDD}/cross-talk-{agent}-{task}-{timestamp}.json`
2. `SCBE-AETHERMOORE/artifacts/agent_comm/github_lanes/cross_talk.jsonl` (append one line)
3. `C:\Users\issda\OneDrive\Documents\DOCCUMENTS\A follder\AI Workspace\Cross Talk.md` (append markdown block)
4. `SCBE-AETHERMOORE/agents/{from_agent}.md` (append log entry)

**Packet format (JSON):**
```json
{
  "packet_id": "{from}-{intent}-{YYYYMMDDTHHMMSSZ}-{6char_hash}",
  "created_at": "2026-03-04T02:10:00Z",
  "from": "agent.claude",
  "to": "agent.codex",
  "intent": "handoff|ack|sync|lane_claim|status_update|smoke|asset_drop",
  "status": "done|in_progress|pending|blocked",
  "summary": "One-sentence description of work done or requested",
  "artifacts": ["relative/path/to/file1", "relative/path/to/file2"],
  "next": "What the receiving agent should do next",
  "ack_required": true
}
```

**Obsidian format (append to Cross Talk.md):**
```markdown
## {created_at} | {Agent} | {task_slug}

- status: {status}
- summary: {summary}
- artifacts:
  - {artifact1}
  - {artifact2}
- next: {next}
```

**JSONL format (append one line to cross_talk.jsonl):**
Same as JSON packet but on a single line.

**Agent log format (append to agents/{agent}.md):**
```
- {created_at} {from} -> {to} | {intent} | {status} | {task_slug} | {summary} ({first_artifact_path})
```

### ACK — Acknowledge a received packet

1. Read the packet being acknowledged
2. Write an ACK packet to all 4 surfaces with:
   - `intent: "ack"`
   - `summary: "ACK {original_packet_id}: {brief confirmation}"`
   - `artifacts: [{proof files showing work was received/acted on}]`

### STATUS — Show active lanes and pending handoffs

1. Scan `artifacts/agent_comm/` for recent packets (last 24h)
2. Read `artifacts/agent_comm/github_lanes/cross_talk.jsonl` (last 10 entries)
3. Read Obsidian `Cross Talk.md` (last 5 entries)
4. Read `.scbe/agent_squad.json` for registered agents
5. Read `artifacts/agent_comm/session_signons.jsonl` for active sessions
6. Report:
   - Active agents (signed on in last 4 hours)
   - Pending handoffs (status != done, no ACK)
   - Stale packets (>30 min, ack_required but no ack)
   - Active lanes (in_progress tasks)

### VERIFY — Check delivery of a specific packet

1. Given a packet_id, check all 4 surfaces for its presence
2. Report which surfaces have it and which are missing
3. If any missing, offer to re-deliver to the missing surfaces

### ROSTER — Show agent registry

1. Read `.scbe/agent_squad.json`
2. Read `artifacts/agent_comm/session_signons.jsonl` (last 10)
3. Show table: agent, provider, model, last_seen, current_task

### HEALTH — System health check

1. Run: `python scripts/connector_health_check.py` (if available)
2. Check GCP VM: `curl -s https://34.134.99.90:8001/health`
3. Check n8n bridge: `curl -s http://127.0.0.1:8001/health`
4. Check AetherNet: `curl -s http://127.0.0.1:8300/health`
5. Report pass/fail for each service

## Session Start Protocol

At the beginning of every session where this skill is invoked:

1. **Check inbox**: Read last 5 entries from `Cross Talk.md` and last 5 JSON packets in `artifacts/agent_comm/`
2. **Find unacked**: Look for packets addressed to `agent.claude` with `ack_required: true` and no corresponding ACK
3. **Report**: Tell the user what's pending
4. **Sign on**: Write a session signon to `artifacts/agent_comm/session_signons.jsonl`

## Error Handling

- If Obsidian vault path doesn't exist (OneDrive not synced): skip that surface, warn user
- If artifacts/agent_comm/ dir doesn't exist: create it
- If agents/{agent}.md doesn't exist: create it with header
- Always report which surfaces succeeded and which failed
- Never silently drop a delivery failure

## Key Paths

| Surface | Path |
|---------|------|
| JSON packets | `SCBE-AETHERMOORE/artifacts/agent_comm/{YYYYMMDD}/` |
| JSONL lane | `SCBE-AETHERMOORE/artifacts/agent_comm/github_lanes/cross_talk.jsonl` |
| Obsidian | `C:\Users\issda\OneDrive\Documents\DOCCUMENTS\A follder\AI Workspace\Cross Talk.md` |
| Agent logs | `SCBE-AETHERMOORE/agents/{agent}.md` |
| Squad registry | `SCBE-AETHERMOORE/.scbe/agent_squad.json` |
| Session signons | `SCBE-AETHERMOORE/artifacts/agent_comm/session_signons.jsonl` |
| Health check | `SCBE-AETHERMOORE/scripts/connector_health_check.py` |

## Integration with Existing Skills

This skill is the **coordination layer**. Other skills handle execution:
- `scbe-flock-shepherd` — spawn/manage agents (invoke when ROSTER shows need)
- `scbe-fleet-deploy` — deploy artifacts (invoke after SEND confirms handoff)
- `scbe-browser-swarm-ops` — browser tasks (invoke for browser lane work)
- `scbe-training-pipeline` — training data (invoke for training lane work)
- `scbe-governance-gate` — governance scan (invoke for any governance check)

Related Skills

scbe-training-pair-authoring

6
from issdandavis/SCBE-AETHERMOORE

Create prompt and response and metadata training pairs from SCBE documents, repair traces, terminal sessions, and operational workflows using the repository's canonical dataset contract and provenance rules.

scbe-spin-conversation-engine

6
from issdandavis/SCBE-AETHERMOORE

Generate SFT training data via radial matrix conversation pivots with D&D-style combat research mode. Produces diverse, cost-effective training pairs with Sacred Tongue encoding, golden spiral problem distribution, and harmonic re-attunement.

scbe-research-training-bridge

6
from issdandavis/SCBE-AETHERMOORE

Stage arXiv evidence and Obsidian markdown into source-grounded Hugging Face training bundles for research, review, and later SFT runs.

scbe-document-management

6
from issdandavis/SCBE-AETHERMOORE

Consolidate overlapping docs, classify files by authority, and keep SCBE repo documents aligned with runtime truth. Use when the repo has drift between canonical docs, public docs, proposal notes, research branches, and generated evidence.

scbe-colab-bridge

6
from issdandavis/SCBE-AETHERMOORE

Control Google Colab notebooks from Claude Code via Chrome extension. Execute cells, run terminal commands, read outputs, and manage GPU compute remotely.

scbe-claim-to-code-evidence

6
from issdandavis/SCBE-AETHERMOORE

Map SCBE Notion technical claims, proof pages, and patent-facing architecture notes to concrete repository evidence such as code paths, tests, demos, and docs. Use when Codex needs to build a due-diligence packet, claim-to-code audit, implementation crosswalk, patent support note, or proof summary from local Notion exports and repo artifacts.

scbe-autonomous-worker-productizer

6
from issdandavis/SCBE-AETHERMOORE

Turn SCBE automation, autonomous worker, and revenue-system notes into concrete offers, workflow packs, pilot plans, or SaaS-facing product packets. Use when Codex needs to package Notion automation pages into buyer-ready offerings, n8n/Zapier workflow designs, flock-backed worker systems, or implementation roadmaps tied to existing SCBE repo surfaces.

scbe-code-scanning-ops

6
from issdandavis/SCBE-AETHERMOORE

Operate GitHub code scanning and CodeQL remediation for SCBE repositories. Use when triaging code-scanning alerts, mapping alert classes to fix patterns, validating targeted regressions, or wiring dedicated CodeQL workflows and runbooks into the repo.

scbe-world-anvil-lore-rag-7th-tongue

6
from issdandavis/SCBE-AETHERMOORE

Build and operate a lore-focused RAG system using World Anvil exports and SCBE docs, with deterministic Claude/Codex cross-talk packets for handoff. Use when users ask to structure lore canon retrieval, sync worldbuilding data, enforce citation-grounded generation, or coordinate a 7th Tongue overseer lane across multiple AI agents.

scbe-webtoon-book-conversion

6
from issdandavis/SCBE-AETHERMOORE

Convert The Six Tongues Protocol and related manuscript sections into webtoon/manhwa storyboard packets, episode roadmaps, panel expansion plans, and image-generation-ready prompt lanes. Use when extending the series storyboard, adapting book chapters into vertical scroll episodes, or keeping art generation tied to canon instead of drifting into generic fantasy panels.

scbe-voice-render-verification

6
from issdandavis/SCBE-AETHERMOORE

Govern and verify SCBE voice rendering work that maps Langues weighting into breath, phase, and Layer 14 audio-axis packets. Use when implementing or reviewing `scripts/voice_gen_hf.py`, emitting sidecar voice packets, validating canonical tongue ordering, tuning breath planning or phase timing, or keeping voice docs and code aligned with `docs/LANGUES_WEIGHTING_SYSTEM.md` and `docs/specs/SCBE_VOICE_EMOTIONAL_TIMBRE_SYSTEM.md`.

scbe-universal-synthesis

6
from issdandavis/SCBE-AETHERMOORE

Orchestrate all installed Codex skills through an auto-updating synthesis matrix with Sacred Tongues routing, emotion/intent metadata, and decodable lexicon packets tied to established SCBE characters. Use when the user asks for cross-skill coordination, auto skill updates, multi-skill routing, or Sacred Tongues intent mapping.