polyhedral-workflow-mesh

Coordinate sub-agent communication, relay workflows, n8n-style automations, triggers, and cross-surface handoffs as one governed mesh. Use when a goal spans multiple agents, browser and terminal surfaces, automation hooks, or periodic and aperiodic work loops that need packets, scoreboards, relays, and proof-backed checkpoints instead of loose AI-to-AI chat.

6 stars

Best use case

polyhedral-workflow-mesh is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Coordinate sub-agent communication, relay workflows, n8n-style automations, triggers, and cross-surface handoffs as one governed mesh. Use when a goal spans multiple agents, browser and terminal surfaces, automation hooks, or periodic and aperiodic work loops that need packets, scoreboards, relays, and proof-backed checkpoints instead of loose AI-to-AI chat.

Teams using polyhedral-workflow-mesh 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/polyhedral-workflow-mesh/SKILL.md --create-dirs "https://raw.githubusercontent.com/issdandavis/SCBE-AETHERMOORE/main/external/codex-skills-live/polyhedral-workflow-mesh/SKILL.md"

Manual Installation

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

How polyhedral-workflow-mesh Compares

Feature / Agentpolyhedral-workflow-meshStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Coordinate sub-agent communication, relay workflows, n8n-style automations, triggers, and cross-surface handoffs as one governed mesh. Use when a goal spans multiple agents, browser and terminal surfaces, automation hooks, or periodic and aperiodic work loops that need packets, scoreboards, relays, and proof-backed checkpoints instead of loose AI-to-AI chat.

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.

Related Guides

SKILL.md Source

# Polyhedral Workflow Mesh

Use this skill when one task is really many connected tasks moving across faces of the same system:

- browser
- terminal
- repo
- automation
- review
- publish

Treat each face as a local work surface. Treat edges as handoffs. Treat relays, triggers, and automations as pulleys and cranes that move work between faces without losing state.

## Core model

- Face: one operating surface or role
- Edge: a handoff path between surfaces
- Relay: a packet transfer that preserves intent and proof
- Trigger: an automation wake-up point
- Periodic loop: heartbeat, schedule, or review cadence
- Aperiodic loop: event-driven arrival, interrupt, or opportunistic follow-on
- Rendezvous: the buffer where periodic and aperiodic lanes meet safely

## Workflow

1. Frame the goal as a mesh, not one action.
- Define the faces involved.
- Define which face owns the final decision.

2. Choose the relay shape.
- Small baton handoff: use cross-talk packets.
- Multi-lane push: use a goal race.
- Triggered automation: use n8n-style or webhook nodes as supporting pulleys, not as the source of truth.

3. Generate the visible race/relay scaffold.
- `python C:\Users\issda\SCBE-AETHERMOORE\scripts\system\goal_race_loop.py --goal "<goal>" --mode <mode>`

4. Emit and verify packets.
- `python C:\Users\issda\SCBE-AETHERMOORE\scripts\system\crosstalk_relay.py emit --sender <agent> --recipient <agent> --intent <intent> --task-id <task> --summary "<summary>"`
- `python C:\Users\issda\SCBE-AETHERMOORE\scripts\system\crosstalk_relay.py verify --packet-id <id>`
- `python C:\Users\issda\SCBE-AETHERMOORE\scripts\system\crosstalk_relay.py ack --packet-id <id> --agent <agent>`

5. Add automation only where it carries weight.
- n8n/Zapier/webhooks should move or wake work, not replace the ledger.
- Keep the packet or scoreboard as the canonical state.

6. Join periodic and aperiodic flows through a rendezvous buffer.
- Scheduled loop owns cadence.
- Event loop owns interrupts and arrivals.
- Hand off through one shared checkpoint instead of forcing one lane to match the other's timing.

7. Verify mesh health.
- `python C:\Users\issda\SCBE-AETHERMOORE\scripts\system\crosstalk_reliability_manager.py`

## When to use which pattern

### Goal race

Use when:

- the work is sequential but multi-lane
- you want a scoreboard
- you want checkpoint visibility

### Direct relay

Use when:

- one agent needs to pass one bounded packet to another
- proof and next action matter more than orchestration

### Trigger mesh

Use when:

- a human or agent event should wake a connector, webhook, or automation
- the automation is a support system, not the whole workflow brain

### Cadence join

Use when:

- one team/lane runs on a recurring schedule
- another arrives irregularly
- both need a common drop zone

## Operator rules

- Never rely on freeform AI-to-AI chat when a packet, relay, or scoreboard will do.
- Keep one canonical state artifact per mesh:
  - scoreboard
  - packet lane
  - or both
- Keep automations downstream of the ledger, not upstream of it.
- Keep proof attached to each handoff.
- Treat repair as part of the mesh, not as an exception.

## Output contract

Return:

- faces
- relays
- trigger points
- checkpoint artifacts
- owner of final decision
- next action

## Resources

Load these only when needed:

- `references/flow-surface-map.md`
  - Load when deciding which surfaces, scripts, and logs belong in the mesh.
- `references/relay-and-cadence-patterns.md`
  - Load when shaping periodic, aperiodic, n8n-style, or cross-agent flows into one governed loop.

Related Skills

scbe-internet-workflow-synthesis

6
from issdandavis/SCBE-AETHERMOORE

Synthesize and operate SCBE end-to-end internet workflows by discovering local and GitHub architecture templates, generating a baseline web pipeline profile, running ingestion and governance scans, and tuning system variables after the first run. Use when users ask to build, repair, or optimize internet workflow pipelines, workflow architecture maps, n8n or agent orchestration flows, or post-baseline threshold and concurrency tuning.

scbe-gh-powershell-workflow

6
from issdandavis/SCBE-AETHERMOORE

Manage GitHub workflows and SCBE-AETHERMOORE repository operations from PowerShell 7 preview. Use for authenticated gh CLI actions, PR and branch workflows, CI triage, and SCBE code-aware repository inspections.

scbe-docker-workflow

6
from issdandavis/SCBE-AETHERMOORE

Coordinate SCBE Docker workflows from build to runtime. Use for SCBE container commands, docker-compose service startup, health checks, and troubleshooting of image/build failures, port conflicts, and container startup issues in SCBE repos.

scbe-claude-crosstalk-workflow

6
from issdandavis/SCBE-AETHERMOORE

Use when two AI lanes (Codex and Claude) work in parallel and need deterministic handoff packets with session IDs, lane-bus appends, and repairable delivery checks.

hf-publish-workflow

6
from issdandavis/SCBE-AETHERMOORE

Automate Hugging Face model/dataset/space publishing from PowerShell with one-time auth, README card generation, `hf upload` commands, and optional `--create-pr` review flow. Use when users ask to log in to Hugging Face CLI, publish artifacts, add or update model/dataset/space cards, wire a reusable profile publish function (for example `scbe-hf-publish`), or troubleshoot common `hf` command usage.

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.