What is fabric-reference?

A read-only reference guide to the VNX software system’s internal workflow. It explains where project state lives, how work is dispatched, how checks and planning interact, and which recurring setup problems to avoid.

Use it when looking up state resolution, dispatch entry points, gate checks, planning layers, or known VNX workflow issues. It is for reference and troubleshooting, not for making orchestration decisions or changing code.

It gives developers a reliable source for understanding how the system actually operates instead of guessing from individual project files. This helps prevent split project state, incorrect dispatches, and failures caused by environment or command-line setup.

How Vinix24/vnx-orchestration configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Vinix24/vnx-orchestration. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Vinix24/vnx-orchestration/main/.claude/skills/fabric-reference/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Vinix24/vnx-orchestration

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vinix24/vnx-orchestration/fabric-reference/github.svg)](https://agentmods.dev/skills/vinix24/vnx-orchestration/fabric-reference)

Your own site

<a href="https://agentmods.dev/skills/vinix24/vnx-orchestration/fabric-reference"><img src="https://agentmods.dev/badge/skills/vinix24/vnx-orchestration/fabric-reference/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/vinix24/vnx-orchestration/fabric-reference"><img src="https://agentmods.dev/badge/skills/vinix24/vnx-orchestration/fabric-reference.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,078 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00116	$0.02078
Opus 5	$0.00058	$0.01039
Sonnet 5	$0.00023	$0.00416
Haiku 4.5	$0.00012	$0.00208

Measured 9d ago against content hash 09f94ce1e01d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

fabric-reference scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/fabric-reference/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VNX Fabric Reference

How the fabric works, as runbooks. This is lookup, not judgment — the t0-orchestrator skill owns orchestration decisions; vnx-manager owns infra maintenance. When a T0 rediscovers the same mechanism a third time, it belongs here.

Master-rule (see role-orchestrator.md): project files describe the project; the fabric describes itself. Fabric mechanism lives in the canonical role and here, never copied into a consumer's CLAUDE.md.

Runbook: state resolution

Tracks, objectives, receipts, and coordination state live in the central store, never repo-local.

Central store: ~/.vnx-data/<project_id>/state/ (resolved by the vnx runtime, not hardcoded).
Never pin VNX_STATE_DIR=.vnx-data/state in a role or script — a repo-local pin forks state from central = split-brain.
Resolution helpers: Python scripts/lib/project_root.py; Bash scripts/lib/vnx_resolve_root.sh.
project_id never silently defaults to vnx-dev (ADR-007) — it resolves from VNX_PROJECT_ID / .vnx-project-id / git remote, else it rejects.

vnx status                 # situational awareness from central state
cat .vnx-data/state/t0_state.json | python3 -m json.tool   # SessionStart projection
vnx fabric-audit           # store-hygiene: split-brain stores, per-project ledgers, hash-chain

Runbook: the single-entry dispatch door

Every dispatch goes through the one door, which decides the lane. Calling a lane script directly is a side door.

vnx dispatch <pending-id>          # the door; decides lane, runs phantom-guard

Provider→lane (hard): claude/Opus/Sonnet route via the tmux-spawn lane (scripts/lib/tmux_interactive_dispatch.py, interactive, subscription-preserving) — NEVER provider_dispatch, NEVER headless claude -p (API-metered after 2026-06-15). kimi/glm/deepseek route via provider_dispatch.py.
Default build-worker model: kimi-k3 (worker-provider-kimi-flip, 2026-07-23; kimi-only, no fallback). Claude/sonnet only via an explicit provider=claude override — VNX_OVERRIDE_WORKERS_KIMI_PINNED=1 only downgrades the warning, it does not change routing.
Rollback to legacy routing: VNX_DISPATCH_LEGACY=1 (per terminal).
Autonomous staging flow (no template): track → central stage_spec_bundle → dry-run → fire → post-merge link-pr. Full rule: docs/core/DISPATCH_RULES.md (§12 for autonomous).
No Claude Code subagents (Task tool) for dispatch work — governed lanes only.

Read the full file on GitHub · 101 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

9d ago First seen · 101 lines · 116 tokens per session scan A 09f94ce1e01d

Subscribe to this mod's changes

fabric-reference is a skill published in the GitHub repository Vinix24/vnx-orchestration (61 stars, last pushed today), licensed MIT. It adds 116 tokens to every session and 2,078 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Multi-Agent ai-orchestration devtools governance tmux

agent-teams

Coordinates Claude agent teams via filesystem protocol. Use when orchestrating parallel agents with task dependencies. Do not use for single-agent tasks.

athola/claude-night-market · 30 tokens

relocate-claude-vm

Move the Claude Desktop "Computer Use" sandbox VM bundle (typically 11-13 GB at %APPDATA%\Claude\vmbundles on Windows) off the system drive to a roomier disk via a directory junction. Transparent to Claude Desktop, reversible. Use when the system drive is low on space and a disk scan shows vmbundles as a top consumer.…

ibrews/claude-fleet · 98 tokens

crew

Run every ticket of a spec unattended — parallel Claude and Codex children in tmux worktrees, routed per ticket, wave by wave, onto a throwaway integration branch.

okqixiaobao727-design/agentcrew-dev-skills · 37 tokens

route

Classify a run's tickets — workflow, executor, model, effort, review lane — and stage the run directory /crew starts from; takes a parent ticket number, an explicit ticket list, or a spec whose tickets are not cut yet.

okqixiaobao727-design/agentcrew-dev-skills · 52 tokens

aoi

Govern material engineering work in any AOI-configured repository through the installed AOI CLI. Use when AOI hooks report an active project, before edits or external actions, and when planning, claiming, delegating, verifying, checkpointing, delivering, or closing AOI tasks.

Ryan529616/aoi-orgware · 59 tokens

aoi-bootstrap

Inspect an existing Git repository and turn the user's project requirements into a conservative, reviewable AOI organization profile. Use when the user asks to initialize AOI, create or review aoi.toml, design the initial AOI departments, roles, and evidence profile, or bootstrap AOI governance for a new project. Do…

Ryan529616/aoi-orgware · 85 tokens

vnx-orchestration: Skill for Claude Code