orkid: Skill for Claude Code

.claude/skills/obtnet-node/SKILL.md

obtnet-node is a skill for Claude Code from tweakoz/orkid. It costs 77 tokens per session (1,634 once invoked), scanned A, original, MIT.

Instructions for running one computer as a worker in an obtnet fleet. The worker daemon receives relayed jobs from a controller and runs them in the project’s prepared build environment.

In plain words
What is it for?
Use it when setting up, launching, or troubleshooting an obtnet node that executes remote builds, tests, checkouts, or file synchronisation.
Why use it?
It prevents confusing remote failures caused by starting the worker without the environment and staging setup it needs.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is tweakoz/orkid's own configuration. It tells Claude Code how to work on orkid itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything orkid configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/tweakoz/orkid/develop/.claude/skills/obtnet-node/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/tweakoz/orkid

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.

agentmods badge for obtnet-node

README.md
[![agentmods](https://agentmods.dev/badge/skills/tweakoz/orkid/obtnet-node/github.svg)](https://agentmods.dev/skills/tweakoz/orkid/obtnet-node)
Your own site
<a href="https://agentmods.dev/skills/tweakoz/orkid/obtnet-node"><img src="https://agentmods.dev/badge/skills/tweakoz/orkid/obtnet-node/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.

agentmods 80×15 button for obtnet-node

Your own site · 80×15
<a href="https://agentmods.dev/skills/tweakoz/orkid/obtnet-node"><img src="https://agentmods.dev/badge/skills/tweakoz/orkid/obtnet-node.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,634 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00077 $0.01634
Opus 5.5 $0.00031 $0.00654
Sonnet 5.5 $0.00015 $0.00327
Haiku 4.5 $0.00008 $0.00163

Measured 2mo ago against content hash e26508c75dc6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

obtnet-node 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.

.claude/skills/obtnet-node/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

obtnet-node — this machine as a fleet node

A node is a small daemon (obt.net.node.py) that registers with the controller, heartbeats, and executes relayed work. Its terminal console is a first-class UI: one compact line per event (connect, run→/done rc+duration+bytes, uploads, job state changes) — run it somewhere you can watch.

The launch law (non-negotiable)

Nodes ALWAYS run inside an obt shell. Jobs inherit the node's environment verbatim — the obt shell is what makes bare tools (ork.build.py, obt.dep.*, ork.cpp.db.*) resolve and what points them at THIS machine's staging + project checkout.

# inside an obt shell (obt.env.launch.py --stagedir <stage> [--project <checkout>]):
obt.net.node.py --controller <controller-host>     # port defaults to 7461

Name defaults to the hostname. Never launch a node "naked" (plain ssh session): a partial environment produces confusing distant failures — ModuleNotFoundError: obt, empty $OBT_STAGE — instead of a loud local one. Temp/extra nodes go through obt.env.launch.py --stagedir <stage> --command obt.net.node.py too.

Two kinds of node on this machine (never conflate)

  • WORKER node — everything else in this file: executes jobs in this machine's staging and checkout. Normally HUB-started from FLEET.json during fleet bringup (owner jul30); hand-start only on direct instruction. Agents outside the hub's bringup flow never start one — they print the launch line.
  • MAILBOX node — obt.net.node.py … --name coord-<seat> --restrict msg,sync: a coordinator seat's mail endpoint. It executes NO work: --restrict msg,sync allows only the message-deposit tool and git (so sync/gitsync still work), and everything else comes back as restricted node <name> refuses …. It belongs to that seat's COORDINATOR, who starts and restarts it unprompted; the launch line lives in that seat's bringup procedure (.claude/skills/hub-coordinator/BRINGUP.md / .claude/skills/sub-coordinator/BRINGUP.md), not here. Placement rule: a HUB's mailbox joins the hub's OWN controller; a SUB's mailbox joins the HUB's controller — that is how hub-to-sub mail arrives.

Read the full file on GitHub · 96 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.

  1. 2mo ago First seen · 96 lines · 77 tokens per session scan A e26508c75dc6

Subscribe to this mod's changes

obtnet-node is a skill published in the GitHub repository tweakoz/orkid (35 stars, last pushed 2mo ago), licensed MIT. It adds 77 tokens to every session and 1,634 once invoked, about $0.0003 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.

Related

obtnet-node compared with skills from other repositories

obtnet-node next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
obtnet-nodetweakoz/orkidSkill352mo agoMITA77Claude Code
create-skillwarpdotdev/warpSkill66kyesterdayAGPL-3.0A64Claude Code, Codex
test-warp-uiwarpdotdev/warpSkill66kyesterdayAGPL-3.0A55Claude Code
dart-testdartsim/dartSkill1.2kyesterdayBSD-2-ClauseA18Claude Code, Codex
modify-settingswarpdotdev/warpSkill66kyesterdayAGPL-3.0A16Claude Code, Codex
dart-fix-cidartsim/dartSkill1.2kyesterdayBSD-2-ClauseA16Claude Code
create-tab-configwarpdotdev/warpSkill66kyesterdayAGPL-3.0A44Claude Code, Codex