Borrowing it
Nothing to install: this file belongs to tweakoz/orkid. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tweakoz/orkid/develop/.claude/skills/hub-coordinator/SKILL.mdgit clone --depth 1 https://github.com/tweakoz/orkidWrote 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/tweakoz/orkid/hub-coordinator)<a href="https://agentmods.dev/skills/tweakoz/orkid/hub-coordinator"><img src="https://agentmods.dev/badge/skills/tweakoz/orkid/hub-coordinator/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/tweakoz/orkid/hub-coordinator"><img src="https://agentmods.dev/badge/skills/tweakoz/orkid/hub-coordinator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00138 | $0.00461 |
| Opus 5.5 | $0.00055 | $0.00184 |
| Sonnet 5.5 | $0.00028 | $0.00092 |
| Haiku 4.5 | $0.00014 | $0.00046 |
Grade A, and why
hub-coordinator 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 2mo 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.
What it actually says
hub-coordinator — the integration seat
Two files, in this order, both mandatory:
.claude/agents/hub-coordinator.md— Read IN FULL. The canonical role: agent graph, per-slice loop, laws, landing checklist, multi-coordinator doctrine, tasksets.BRINGUP.md(this folder) — if the owner's instruction was to start up or bring up/restore the fleet, EXECUTE it now, in full: hub plumbing (controller + mailbox + monitor), THEN fleet bringup from the active taskset's FLEET.json — YOU start the sub-coordinator claude sessions (screen, over ssh) and the worker nodes; nothing is owner-started by hand. Bringup and restore are the same procedure (owner jul30).
Also in this folder: COORDINATION_OPS.md (bus architecture, routing classes, node
classes, division of control), TASKSET_FORMAT.md (taskset folder contract — hub-only;
subs never load tasksets), fleet.schema.json (FLEET.json schema — the instance file
lives in the active taskset, hostnames legal there only).
Wrong role? If this session was told to be a sub-coordinator under some hub, load
sub-coordinator instead — this skill is for the ONE integration seat.
Fleet operation: the obtnet skill (controller side) and obtnet-node (node side).
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 27 lines · 0 tokens per session scan A 1c4799123c10
hub-coordinator is a skill published in the GitHub repository tweakoz/orkid (35 stars, last pushed 2mo ago), licensed MIT. It adds 138 tokens to every session and 461 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-01.
hub-coordinator compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hub-coordinatortweakoz/orkid | Skill | 35 | 2mo ago | MIT | A | 138 | Claude Code |
| create-skillwarpdotdev/warp | Skill | 66k | yesterday | AGPL-3.0 | A | 64 | Claude Code, Codex |
| test-warp-uiwarpdotdev/warp | Skill | 66k | yesterday | AGPL-3.0 | A | 55 | Claude Code |
| dart-testdartsim/dart | Skill | 1.2k | yesterday | BSD-2-Clause | A | 18 | Claude Code, Codex |
| modify-settingswarpdotdev/warp | Skill | 66k | yesterday | AGPL-3.0 | A | 16 | Claude Code, Codex |
| dart-fix-cidartsim/dart | Skill | 1.2k | yesterday | BSD-2-Clause | A | 16 | Claude Code |
| create-tab-configwarpdotdev/warp | Skill | 66k | yesterday | AGPL-3.0 | A | 44 | Claude Code, Codex |