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 agents/supsub-ai/supsub-cli/scenariosgit 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/agents/supsub-ai/supsub-cli/scenarios)<a href="https://agentmods.dev/agents/supsub-ai/supsub-cli/scenarios"><img src="https://agentmods.dev/badge/agents/supsub-ai/supsub-cli/scenarios.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 | $0.00000 | $0.01844 |
| Opus 5 | $0.00000 | $0.00922 |
| Sonnet 5 | $0.00000 | $0.00369 |
| Haiku 4.5 | $0.00000 | $0.00184 |
Grade A, and why
scenarios 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
我可以这么说
下面按日常场景整理了一批说法,照着抄、或者换成你自己的话都行。助手能听懂的说法远不止这些,这里只是给你个感觉。
::: tip 先认三个词 往下看会反复出现这三个词,它们不一样:
- 订阅 —— 你追的某一个号(一个公众号、一个网站、一个推特账号)
- 关注点 —— 你在网页上设的主题方向,SupSub 会自动把各处相关内容聚过来
- 分组 —— 你给订阅建的文件夹,比如把几个号都归到「AI」里 :::
摸清自己有什么
我订阅了哪些?
我关注了哪些主题?
我一共分了几个组?
「AI」这个组里都有谁?
加一个新的号
帮我订阅「阮一峰的网络日志」
我想追「机器之心」,帮我加上
帮我找找有没有叫「量子位」的公众号
助手会先去找这个号。这一步要等一会儿(大概半分钟),是正常的。
找到的往往不止一个——搜「机器之心」会同时出来「机器之心PRO会员」「机器之心SOTA模型」,还夹杂着别的号。助手应该把候选列给你挑,确认之后再订。如果它没问就直接订了,记得核对一下订的是不是你要的那个。
网站和推特账号也能订,同样是报名字:
帮我订阅「阮一峰的网络日志」这个网站
订阅推特上的 ClaudeDevs
::: warning 不能直接丢一个网址进去
SupSub 只能订阅它已经收录的源,所以要按名字找,不能贴 https://... 让它去订。
贴网址的实际后果是:助手拿这串字符去搜,可能返回一个看着像、其实完全不相干的站,然后把那个订上。想确认某个站有没有被收录,直接问「SupSub 里有没有收录 XXX?」 :::
今天读点什么
我还有什么没看的?
每个号还剩多少没读?
「阮一峰的网络日志」最近发了什么?
「AI 行业动态」这个关注点这两天有什么新的?
::: tip 「最近」和「没看的」是两回事 问「最近发了什么」,助手会把最近的内容都列出来,并顺带告诉你哪几篇你还没看过。
问「还有什么没看的」,才只列没读过的。 :::
让助手帮你消化
这部分是自己敲命令做不到的,也是装 AI 助手最值的地方。
总结
这篇讲了什么,两句话说完
把这个号最近五篇的要点各总结一句
这个关注点今天的内容,整体讲的是什么趋势?
筛选
今天这些未读里,跟「客户增长」有关的挑出来
这批文章里有没有讲具体做法的?只讲概念的我不看
挑三篇最值得读的,说说为什么
对比
这几篇对同一件事的说法有什么不一样?
有没有观点互相矛盾的?
做简报
把我这周所有未读整理成一份摘要,按主题分类
给我一份今天的早报:每个主题挑一条,一句话说清
我要给同事转发,帮我写个三句话的推荐语
边读边清
这几篇我看完了,把这个号标成读过
找东西
搜一下最近关于 AI 的文章
帮我找找有没有讲「向量数据库」的内容
搜「大模型」,我要找的是公众号,不是文章
找找提到 Claude 的文章
::: tip 搜索是搜全站的 搜索会搜整个 SupSub,不只是你订阅的那些。所以能搜到你还没订阅的好内容——看到喜欢的,直接说「把这个号也订上」就行。 :::
整理收纳
建一个叫「AI」的组
把「量子位」放进 AI 组
把这个号从 AI 组里拿出来
「AI」这个组改名叫「AI 前沿」
这个号我不想追了,退订吧
::: tip 从组里拿出来 ≠ 退订 把一个号移出分组,只是不归在那个文件夹里了,你还是照样订阅着它。真想不再收到,要说「退订」。 :::
读完了,清一清
这个号我读完了
「AI 行业动态」这个关注点我都看过了,标成读过吧
把这几个号都标成读过
::: tip 别用「清掉」「清空」这种词 「把这个关注点清掉」既能理解成「标成读过」,也能理解成「把这个关注点删了」——而删掉的关注点建不回来(只能在网页上重新建)。
想标已读就说「标成读过 / 我读完了」,想删就说「删掉这个关注点」。 :::
::: warning 标成读过之后没法反悔 SupSub 没有「标回未读」这个功能,所以助手会在动手前跟你确认一次。确认前你可以先让它列出来看看。
另外只能整个号、或者整个关注点一起标,没法只标某一篇。 :::
一句话包含好几步
助手可以自己把一件事拆成好几步做完,不用你一步步指挥:
帮我找找「少数派」这个号,订上,然后归到「效率」组里
看看我今天所有未读,按主题分类,每类挑一条讲讲
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 · 184 lines · 0 tokens per session scan A 30bb5430dd1a
scenarios is an agent published in the GitHub repository SupSub-AI/supsub-cli (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,844 tokens. 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 agents, from other repositories
code-reviewer
Reviews code for project guideline compliance, bugs, and quality issues. Use after writing code, before commits, or before PRs. Specify files to review or defaults to unstaged git changes. High-confidence issues only (80+) to minimize noise.
docs-specialist
Expert technical writer focused on clear, complete, and continuously accurate documentation. Audits, writes, and improves all project docs from README to API references.
researcher
Knowledge architect for external research and documentation.
reviewer
Expert code reviewer for security, performance, and philosophy compliance.
triage-labels
The skills speak in terms of five canonical triage roles. This repo uses the default strings unchanged, recorded as the Status: line in each .scratch//issues/.md file.
triage-scan
You are a triage analyst. ./input.json names one repo and the exact source tree to read it against.