Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Vinix24/vnx-orchestrationnpx agentmods add skills/vinix24/vnx-orchestration/orchestrateWrote 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.
[](https://agentmods.dev/skills/vinix24/vnx-orchestration/orchestrate)<a href="https://agentmods.dev/skills/vinix24/vnx-orchestration/orchestrate"><img src="https://agentmods.dev/badge/skills/vinix24/vnx-orchestration/orchestrate/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.
<a href="https://agentmods.dev/skills/vinix24/vnx-orchestration/orchestrate"><img src="https://agentmods.dev/badge/skills/vinix24/vnx-orchestration/orchestrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 151 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00000 | $0.01173 |
| Opus 5 | $0.00000 | $0.00587 |
| Sonnet 5 | $0.00000 | $0.00235 |
| Haiku 4.5 | $0.00000 | $0.00117 |
Grade A, and why
orchestrate 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.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
T0 Orchestrator — Detailed Workflow Reference
This is the extended reference for the headless T0 orchestrator.
The condensed identity is in agents/orchestrator/CLAUDE.md.
1. Receipt Review Protocol
Claim Verification (minimum 3 per receipt)
For each worker receipt, spot-check at least 3 specific claims:
# 1. Claimed file was modified
git log --oneline -1 -- <file>
# 2. Specific fix is present
grep -r "expected_pattern" <file>
# 3. Old problem no longer exists
grep -r "old_pattern" src/ # Must return 0 matches
Acceptance criteria:
- Automated test pass counts are acceptable evidence
- Code change descriptions are NOT acceptable without code verification
- Vague claims ("improved performance", "fixed bug") require concrete evidence
- If ANY claim fails verification: reject receipt, do not close items
Quality Advisory Interpretation
| Advisory | Risk | Action |
|---|---|---|
| approve | < 0.3 | Standard review |
| approve | 0.3-0.5 | Careful review of flagged areas |
| hold | > 0.5 | Critical review, likely follow-up dispatch |
| hold | > 0.8 | Block progression unless explicitly mitigated |
2. Open Items Lifecycle
Inspect
python3 scripts/open_items_manager.py digest
python3 scripts/open_items_manager.py list --status open
Resolve (only with evidence)
# Verify fix exists before closing
grep -r "old_pattern" src/ # Must return 0
grep -r "new_pattern" src/ # Must return expected matches
git log --oneline -1 -- <file> # Must show recent commit
# Then close
python3 scripts/open_items_manager.py close OI-XXX --reason "evidence: ..."
python3 scripts/open_items_manager.py defer OI-XXX --reason "non-blocking"
python3 scripts/open_items_manager.py wontfix OI-XXX --reason "out of scope"
Create new item
python3 scripts/open_items_manager.py add \
--title "<short risk title>" \
--severity warn \
--pr-id PR-X \
--description "<what was discovered>"
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 · 160 lines · 0 tokens per session scan A 5915c6d5184e
orchestrate is a skill published in the GitHub repository Vinix24/vnx-orchestration (61 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,173 tokens. 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.
Other skills, from other repositories
agent-teams
Coordinates Claude agent teams via filesystem protocol. Use when orchestrating parallel agents with task dependencies. Do not use for single-agent tasks.
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.…
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.
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.
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.
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…