Vinix24/vnx-orchestration / skills/t0-orchestrator
t0-orchestrator
VerifiedMaster orchestration for the VNX multi-terminal system. Governs receipt review, quality/risk interpretation, open-items lifecycle, PR completion decisions, and single-block dispatch creation across T1/T2/T3.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.9 KB |
| references/_MAPPING.md | markdown | 241 B |
| references/dispatch-patterns.md | markdown | 2.7 KB |
| references/example-workflows.md | markdown | 2.9 KB |
| references/feature-plan.md | markdown | 1.3 KB |
| references/provider-matrix.md | markdown | 1.7 KB |
| scripts/dispatch_guard.shexecutable | script | 15.1 KB |
| scripts/intelligence.shexecutable | script | 10.1 KB |
| template.md | markdown | 4.8 KB |
references/provider-matrix.md
View on GitHub# Provider Capability Matrix (Runtime-Realistic)
## Policy First
- T0 runtime policy is currently **Claude Opus only**.
- Provider comparison below is for worker-terminal dispatch planning (mainly T1).
## How to Check Active Provider
```bash
jq -r '.T1.provider' .vnx-data/state/panes.json
```
## Capability Matrix
| Capability | claude_code | codex_cli | gemini_cli |
|---|---|---|---|
| Native skill invocation command | Yes | No guaranteed native slash-skill command | No guaranteed native slash-skill command |
| Fallback via inline role/context preamble | Supported (optional) | Supported (primary pattern) | Supported (primary pattern) |
| Context reset command | `/clear` | `/new` | `/clear` |
| Planning mode support | Yes | Limited (`/plan`, verify per version) | No |
| Thinking mode support | Yes | No | No |
| MCP support in worker runtime | Yes (provider/config dependent) | No | No |
## Dispatch Guidance by Provider
### Claude Code
- Use standard skill-first dispatch with `Workflow: [[@.claude/skills/<skill>/SKILL.md]]`.
- `Mode: planning` and `Mode: thinking` are available when appropriate.
### Codex CLI
- Do not assume native slash-skill invocation.
- Use explicit `Role`, `Workflow`, and `Context` fields in Manager Block.
- Avoid `Mode: thinking`; planning support must be validated in-session.
- Omit Claude-specific `Requires-Model` values unless confirmed compatible.
### Gemini CLI
- Do not assume native slash-skill invocation.
- Use explicit `Role`, `Workflow`, and `Context` fields in Manager Block.
- Avoid `Mode: thinking` and `Mode: planning`.
- Omit `Requires-Model` fields (single-model runtime behavior).
## MCP Routing Rule
If a task requires MCP-dependent capabilities, set `Requires-MCP: true` and route to T3.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |