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 skills add SupSub-AI/supsub-cli --skill supsub-searchgit 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/skills/supsub-ai/supsub-cli/supsub-search)<a href="https://agentmods.dev/skills/supsub-ai/supsub-cli/supsub-search"><img src="https://agentmods.dev/badge/skills/supsub-ai/supsub-cli/supsub-search/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.
<a href="https://agentmods.dev/skills/supsub-ai/supsub-cli/supsub-search"><img src="https://agentmods.dev/badge/skills/supsub-ai/supsub-cli/supsub-search.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00280 | $0.01945 |
| Opus 5 | $0.00140 | $0.00972 |
| Sonnet 5 | $0.00056 | $0.00389 |
| Haiku 4.5 | $0.00028 | $0.00194 |
Grade C, and why
supsub-search 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` 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.
supsub-search Skill
全量搜索:在订阅源(公众号、网站)和文章正文里同时搜,可按类型缩小范围。
先判范围:全站搜索 vs 用户自己的订阅
拿到一个词 X,看动词,不看 X 像不像专名:
| 用户说法 | 意图 | 走哪 |
|---|---|---|
| 「搜一下 X」「查 X 相关文章」「全文搜 X」 | 检索 | 本 skill(全站) |
| 「看一下最近 X 的内容」「X 最近有什么」「X 更新了吗」「读读 X」 | 浏览某主体的内容流 | 先比对订阅范围(见下) |
| 「我的订阅 / 我的公众号 / 我的网站」 | 已限定本人范围 | supsub-sub |
| 「我的关注点」 | 已限定本人范围 | supsub-focus |
浏览意图的处理步骤:
supsub sub list -o json+supsub focus list -o json;- 把 X 与
name/title做包含匹配(忽略大小写); - 命中订阅源 →
supsub sub contents --source-id <sid> --type <t>;命中关注点 →supsub focus contents --id <fid>;两边都命中就都列出来让用户选(同一个词很可能既是源名又是关注点主题); - 命中后补一句「也可以全站搜 X 相关文章」,别把全局搜索这条路藏起来;
- 一个都没命中 → 直接执行
supsub search <X>全站搜索,不要反问「要不要我帮你搜一下」。用户的浏览意图没有变,只是这个词不在他的订阅里;正确做法是搜完再说明「你没有订阅叫 X 的源,以下是全站结果」。
实测教训:「看一下最近 Anthropic 的内容」曾被直接送进全站 search,返回一堆第三方评论文章,而用户自己订阅的 Anthropic 官方博客源、以及「Anthropic 公司动态与 AI 前沿进展」关注点被完全绕过。用户提某个主体名时,他自己订阅的那份优先。
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
Search
supsub search <keyword> [--type <ALL|MP|WEBSITE|CONTENT>]
| Flag | Default | Description |
|---|---|---|
--type |
ALL |
搜索范围:ALL(源 + 文章)/ MP(公众号源)/ WEBSITE(网站源)/ CONTENT(文章正文) |
<keyword> 是位置参数,可以是中文或英文,建议用引号包起来避免 shell 拆分。
# 全量搜索(默认 ALL:同时搜源 + 文章)
supsub search "RAG"
# 只搜公众号
supsub search "阮一峰" --type MP
# 只搜网站
supsub search "hacker news" --type WEBSITE
# 只搜文章正文
supsub search "向量数据库" --type CONTENT
# JSON
supsub search "MCP 协议" -o json
JSON shape: {"success":true,"data":{"results":[...],"recommendations":[...],"prompts":[...]}}
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.
- 9d ago First seen · 96 lines · 280 tokens per session scan C 0a8a84382e3c
supsub-search is a skill published in the GitHub repository SupSub-AI/supsub-cli (5 stars, last pushed 1mo ago), licensed MIT. It adds 280 tokens to every session and 1,945 once invoked, about $0.0014 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.
Other skills, from other repositories
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.
flow-cytometry-analysis
Complete flow cytometry analysis pipeline. FCS file handling, compensation, manual/automated gating, immunophenotyping, CFSE proliferation analysis, cell cycle analysis (Dean-Jett-Fox), and apoptosis assays. Extends flowio with analytical workflows. For raw FCS parsing only use flowio.
molecular-cloning
Molecular cloning simulation and design. PCR amplicon prediction, restriction enzyme digestion, Golden Gate and Gibson assembly simulation, primer design, CRISPR sgRNA design, and plasmid annotation. For protein-level sequence analysis use biopython or esm; for database lookups use gene-database or ensembl-database.
datamol
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters…
shap
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing…
glycobiology
Glycosylation site prediction and glycobiology analysis. N-glycosylation motif finding, O-glycosylation hotspot prediction, glycan structure resources. Lightweight, pure Python. For protein function queries use uniprot-database; for structure analysis use alphafold-database.