supsub-group

supsub-group is a skill for Claude Code from SupSub-AI/supsub-cli. It costs 227 tokens per session (2,875 once invoked), scanned C, original, MIT.

A tool for organising SupSub subscriptions into groups, which work like folders for sources such as websites, public accounts, and Twitter/X accounts.

In plain words
What is it for?
Creating, renaming, deleting, and listing groups, viewing their unread counts, and adding or removing subscription sources.
Why use it?
It keeps related subscriptions together and makes them easier to browse without confusing source folders with topic-based feeds.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the supsub-cli plugin — 8 skills shipped together

Good fit Creating, renaming, deleting, and listing groups, viewing their unread counts, and adding or removing subscription sources.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/supsub-ai/supsub-cli/supsub-group
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 SupSub-AI/supsub-cli --skill supsub-group
Clone the repo
git clone --depth 1 https://github.com/SupSub-AI/supsub-cli

Made for: Claude Code.

Or install supsub-cli, the plugin that ships this one along with the rest of its 8 skills.

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 supsub-group

README.md
[![agentmods](https://agentmods.dev/badge/skills/supsub-ai/supsub-cli/supsub-group/github.svg)](https://agentmods.dev/skills/supsub-ai/supsub-cli/supsub-group)
Your own site
<a href="https://agentmods.dev/skills/supsub-ai/supsub-cli/supsub-group"><img src="https://agentmods.dev/badge/skills/supsub-ai/supsub-cli/supsub-group/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 supsub-group

Your own site · 80×15
<a href="https://agentmods.dev/skills/supsub-ai/supsub-cli/supsub-group"><img src="https://agentmods.dev/badge/skills/supsub-ai/supsub-cli/supsub-group.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 227 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,875 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. 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 $0.00227 $0.02875
Opus 5 $0.00113 $0.01437
Sonnet 5 $0.00045 $0.00575
Haiku 4.5 $0.00023 $0.00287

Measured 9d ago against content hash 4d7a0e7d2bce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

supsub-group scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

- 安装:`curl -fsSL https://raw.githubusercontent.com/SupSub-AI/supsub-cli/master/scripts/install.sh | bash`(native 安装,装到 `~/.local`、支持后台自动更新);或包管理器 `npm i -g @supsub/cli` / `pnpm add -g @supsub/cli`

Makes network callslowCapability

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

- 安装:`curl -fsSL https://raw.githubusercontent.com/SupSub-AI/supsub-cli/master/scripts/install.sh | bash`(native 安装,装到 `~/.local`、支持后台自动更新);或包管理器 `npm i -g @supsub/cli` / `pnpm add -g @supsub/cli`
skills/supsub-group/SKILL.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

supsub-group Skill

「分组」(group)是订阅源的文件夹:把已订阅的源(公众号 MP、网站 WEBSITE、推特 X 等)收纳到自定义分组里,便于归类浏览。本 skill 负责分组的增删改查与成员管理。

supsub-focus 的区别:group人工收纳订阅源的文件夹(成员是源);focusAI 按主题聚合的内容流(成员是文章)。「把量子位放进 AI 分组」→ 本 skill;「我的关注点里有什么」→ supsub-focus。 与 supsub-sub 的区别:sub 管订阅关系本身(订阅/退订/看文章);本 skill 只管"源放在哪个文件夹"。sub add --group <gid> 可在订阅时直接入组(见 supsub-sub)。

Prerequisites

  • 安装:curl -fsSL https://raw.githubusercontent.com/SupSub-AI/supsub-cli/master/scripts/install.sh | bash(native 安装,装到 ~/.local、支持后台自动更新);或包管理器 npm i -g @supsub/cli / pnpm add -g @supsub/cli
  • 已登录:supsub auth status 显示 Authenticated(首次使用先 supsub auth login
  • 未授权(exit 2 / UNAUTHORIZED)时不要止步于「你未登录」:直接运行 supsub auth login 为用户打开浏览器授权(命令会自动打开浏览器并阻塞等待授权,请用足够长的超时,如 10 分钟;用户只需在浏览器点确认,无需在终端输入任何内容),授权成功后重试原命令。无浏览器 / 无头环境再回退为提示用户 SUPSUB_NO_BROWSER=1 supsub auth login

Commands

List groups(分组列表)

supsub group list

无参数。每行字段:id, name

supsub group list
supsub group list -o json

JSON shape: {"success":true,"data":[{"id":1063,"name":"AI 周报"}, ...]}

id 目前是数字,但请当作不透明标识原样回传(不要做数学运算/格式假设),后端保留改用字符串 ID 的可能。


Create a group(创建分组)

supsub group add <name>

位置参数 <name> 为分组名称(空白名称报 INVALID_ARGS)。

supsub group add "AI 周报"
supsub group add 财经 -o json

JSON shape: {"success":true,"data":{"id":1182,"name":"AI 周报"}} —— 返回里直接带新分组 id,可立刻接 add-sub / sub add --group 使用(已实测)。

⚠️ 分组名不可重复:已存在同名分组时报 ResourceExists(409 → exit 1),不会返回已有分组的 id。

因此「把 X 订上并归到『效率』组里」这类请求的正确顺序是:group list 找同名分组, 命中就复用它的 id,没命中才 group add。上来就 group add 会在分组已存在时白白失败一次。 若 group list 没有该分组,直接建即可(建分组是无损操作,不用反问用户)——但建之前顺带说一句 「『效率』组不存在,我新建一个」,因为用户很可能只是把组名记错了。


Rename a group(重命名分组)

supsub group rename --id <gid> --name <newName>
Flag Required Description
--id yes 分组 ID(来自 group list
--name yes 新分组名称(非空)
supsub group rename --id 1063 --name "AI 深度"

Read the full file on GitHub · 187 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. 9d ago First seen · 187 lines · 227 tokens per session scan C 4d7a0e7d2bce

Subscribe to this mod's changes

supsub-group is a skill published in the GitHub repository SupSub-AI/supsub-cli (5 stars, last pushed 1mo ago), licensed MIT. It adds 227 tokens to every session and 2,875 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.