oo-subscribe

oo-subscribe is a skill for Claude Code, Codex from openonion/connectonion. It costs 37 tokens per session (956 once invoked), scanned A, original, Apache-2.0.

A workflow for following and managing published ConnectOnion skills with the `co sub` command. It fetches, verifies, and installs skills from publishers you follow.

In plain words
What is it for?
It helps follow a publisher, refresh subscribed skills, list subscriptions, and stop following a publisher.
Why use it?
It removes the need to copy published skills manually and helps ensure the publisher and revision are checked before installation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps follow a publisher, refresh subscribed skills, list subscriptions, and stop following a publisher.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/openonion/connectonion/oo-subscribe
About the project

ConnectOnion is an open-source, template-first toolkit for building, debugging, deploying, and operating AI agents. Developers use its command-line tools and Python runtime to create agents, add tools, connect services, deploy them, and make them callable by other agents, while the catalogue entries are related agents, skills, and instructions.

openonion/connectonion · 1,497 stars · on GitHub · docs.connectonion.com

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add openonion/connectonion --skill oo-subscribe
Clone the repo
git clone --depth 1 https://github.com/openonion/connectonion

Made for: Claude Code, Codex.

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 oo-subscribe

README.md
[![agentmods](https://agentmods.dev/badge/skills/openonion/connectonion/oo-subscribe/github.svg)](https://agentmods.dev/skills/openonion/connectonion/oo-subscribe)
Your own site
<a href="https://agentmods.dev/skills/openonion/connectonion/oo-subscribe"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/oo-subscribe/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 oo-subscribe

Your own site · 80×15
<a href="https://agentmods.dev/skills/openonion/connectonion/oo-subscribe"><img src="https://agentmods.dev/badge/skills/openonion/connectonion/oo-subscribe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 956 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00037 $0.00956
Opus 5.5 $0.00015 $0.00382
Sonnet 5.5 $0.00007 $0.00191
Haiku 4.5 $0.00004 $0.00096

Measured 21d ago against content hash de07f3cabb51, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

oo-subscribe scanned grade A with 1 finding 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 21d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

the relay protocol with `curl` or handwritten signing code; `co sub` owns the
connectonion/useful_skills/oo-subscribe/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Follow published ConnectOnion skills

Use the installed co sub commands. Read co sub --help and the selected subcommand's --help when syntax or behavior differs from this skill. The CLI fetches the profile and skill bodies, verifies the publisher's signature and revision, mirrors the public bodies, and installs them into detected coding agents. No subscriber key, co init, or publisher approval is required to follow public skills.

Goal Command
Follow a publisher for the first time co sub sync <full-0x-address>
Refresh one publisher already in the local list co sub sync <address-or-local-alias>
Refresh all local subscriptions co sub
See locally recorded subscriptions co sub list
Stop following one co sub remove <address-or-local-alias>

Choose and verify the publisher

First-time follow requires the publisher's complete address (0x plus 64 hex characters), obtained from the publisher or another trusted channel. A bare alias only works after that address has been pinned locally. If the user gives only an alias, run co sub list to see whether it is already pinned. Otherwise ask for the full address; do not guess it or resolve an untrusted alias through the relay.

Run co sub sync <full-0x-address> once. Read the entire result. A successful subscription records the address and signed alias in ~/.co/subscriptions.txt; published bodies are mirrored under ~/.co/subs/<alias>/skills/. The CLI verifies the profile-v2 signature and monotonic revision before installing, rejects unsigned or older content, and removes a remote skill's tools: grant. A signature identifies the publisher; it does not establish that the skill's instructions are safe or useful. Review the mirrored SKILL.md before using it for consequential work.

Check co sub list for the pinned address, alias, and profile version. Its Skills column counts profile entries, including entries whose bodies were not published; use the sync output's mirrored and installed counts to describe what became available. If an agent reports a positive installed count, tell the user to restart that coding agent. If nothing was installed, say so and do not ask for a restart. A publisher can list a skill's metadata while withholding its body; a later sync may pick it up if the publisher makes it public.

Read the full file on GitHub · 80 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. 21d ago First seen · 80 lines · 37 tokens per session scan A de07f3cabb51

Subscribe to this mod's changes

oo-subscribe is a skill published in the GitHub repository openonion/connectonion (1,497 stars, last pushed today), licensed Apache-2.0. It adds 37 tokens to every session and 956 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-26.

Related

Other skills, from other repositories

agentscope-java

Expert Java developer skill for AgentScope Java framework - a reactive, message-driven multi-agent system built on Project Reactor. Use when working with reactive programming, LLM integration, agent orchestration, multi-agent systems, or when the user mentions AgentScope, ReActAgent, Mono/Flux, Project Reactor, or…

agentscope-ai/agentscope-java · 91 tokens

apply-patch

Apply multi-file or tricky edits atomically with git apply instead of many fragile editfile calls. Use when changing several files at once or when editfile fails to match.

agentscope-ai/agentscope-java · 38 tokens

git-checkpoint

Use git as a safety net - create a checkpoint commit before risky or large changes and roll back cleanly if a change makes things worse. Use before multi-file refactors.

agentscope-ai/agentscope-java · 39 tokens

pptagent

Create and revise editable PowerPoint presentations from a brief using HTML slide sources, rendering, and visual review. Use when the requested deliverable is a PPTX deck. The host authors the slides; text-only hosts can use an external visual reviewer.

icip-cas/PPTAgent · 52 tokens

company-employee

The protocol every employee of a PenguinHarness organization follows — read the handbook first, act on [orgtrigger] work runs, schedule tickets from the desk session and do the work in ticket sessions, block instead of idling, ask the board in the all-hands channel before anything heavy, costly, irreversible or…

Prism-Shadow/penguin-harness · 85 tokens

web-design

Penguin visual language for generated web pages and app UIs — GitHub-style simplicity with a single blue accent, light and pure-black dark themes, design tokens, component and chat-interface recipes, plus an opt-in warm paper editorial theme.

Prism-Shadow/penguin-harness · 51 tokens