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.
npx agentmods add instructions/supsub-ai/supsub-cli/claude-mdgit clone --depth 1 https://github.com/SupSub-AI/supsub-cliWrote 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/instructions/supsub-ai/supsub-cli/claude-md)<a href="https://agentmods.dev/instructions/supsub-ai/supsub-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/supsub-ai/supsub-cli/claude-md.svg" alt="Measured on agentmods" 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 | $0.04800 | $0.04800 |
| Opus 5 | $0.02400 | $0.02400 |
| Sonnet 5 | $0.00960 | $0.00960 |
| Haiku 4.5 | $0.00480 | $0.00480 |
Grade A, and why
supsub-cli CLAUDE.md 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 5d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
READ THIS FIRST if you are answering an end-user natural-language SupSub request. Many requests will look like "搜一下 X" / "查一下 X" — they are not about microblog accounts by default. Consult the routing table immediately below before doing anything else; do not skim source code in
src/commands/to guess the command.
End-user 意图 → 命令路由（最高优先级）
This section is the authoritative routing table for end-user-style natural-language requests about SupSub usage (登录 / 订阅 / 搜索 / 找公众号 …). The same mapping is encoded in skills/*/SKILL.md; this section exists so agents that don't pick up the marketplace skills (e.g. sub-agents inheriting CWD inside this repo) still route correctly. Match the user's intent against this table first; only then look at command source if you need flag-level detail.
| 用户意图 (中文) | Skill | 命令 |
|---|---|---|
| 登录 / 登出 / 查看登录状态 / 我现在用哪个账号 | supsub-auth |
supsub auth login / logout / status |
| 列出订阅 / 我订阅了哪些 / 添加订阅 / 取消订阅 / 看某个订阅里有哪些文章 | supsub-sub |
supsub sub list / add / remove / contents（订阅源类型 MP公众号 / WEBSITE网站 / X推特；contents 支持 --page / --page-size） |
| 我的关注点 / 关注点列表 / 我关注了哪些 / 看某个关注点里的内容（文章）/ 关注点有哪些未读 / 删除关注点 | supsub-focus |
supsub focus list / contents / remove（无新增；删除不可逆） |
| 我的分组 / 新建（重命名 / 删除）分组 / 把某订阅加进（移出）分组 / 某分组里有哪些订阅、还有多少未读 / 整理订阅 | supsub-group |
supsub group list / add / rename / remove / subs / add-sub / remove-sub（删除分组不可逆，先与用户确认；add-sub/remove-sub 是读-改-写全量覆盖，勿并发） |
| 我还有什么没读 / 有多少未读 / 未读概览 / 帮我清未读 / 这个号（这个关注点）我读完了 | supsub-unread |
supsub unread；supsub sub mark-read --all；supsub focus mark-read --all（只有整源/整关注点一档，无单篇已读；不可逆、无取消已读，执行前必须二次确认） |
| 搜文章 / 搜内容 / 关键词找文章 / 全文搜 / 「搜一下 X」 / 「搜 X 相关的内容」 | supsub-search |
supsub search <kw> [--type ALL|MP|WEBSITE|CONTENT] |
| 发现一个具体公众号账号 / 「找 XXX 这个公众号」 / 想订阅某公众号但不知道 ID | supsub-mp |
supsub mp search <name> → 拿 mpId → supsub sub add --mp-id <mpId> |
| 精读某一篇 / 「深读一下这篇」「帮我拆解这篇」「这篇靠不靠谱 / 有没有干货」「把这几篇都精读了出份简报」/ 「昨天那篇精读好了吗」 | supsub-deepread |
supsub deepread run --type <t> --content-id <cid>；deepread list / quota / share（扣月度额度，发起前必须确认；contentId 必须来自上下文） |
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.
- 5d ago First seen · 124 lines · 4,800 tokens per session scan A 5c947c1a06ec
supsub-cli CLAUDE.md is an instructions file published in the GitHub repository SupSub-AI/supsub-cli (5 stars, last pushed 1mo ago), licensed MIT. It adds 4,800 tokens to every session, about $0.0240 per session on Opus 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 2026-08-31.
Other instructions, from other repositories
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
FreshRSS _general.instructions.md
Instructions for FreshRSS/FreshRSS, covering freshrss general instructions, kiss principle: keep it simple, style and formatting and spelling.
bread CLAUDE.md
Instructions for tjakoen/bread, covering claude.md — start here, what this is, start here (reading order), this repo is the stack's control plane — run it and non-negotiables (see conventions for the full rules).
agentconfig.org AGENTS.md
Instructions for agentconfig/agentconfig.org, covering agent instructions for agentconfig.org, project overview, target audience, site structure and tech stack.
rosetta command-versions-vs-presence.instructions.md
Instructions for tikoci/rosetta, a project described as: MCP Server with RouterOS docs + commands + products + changelogs, using SQLite-as-RAG, sourced from MikroTik.
titen CLAUDE.md
Instructions for RamaAditya49/titen, covering claude.md, read agents.md first, commands, two runtimes, one core and publishing to npm.