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-subgit 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-sub)<a href="https://agentmods.dev/skills/supsub-ai/supsub-cli/supsub-sub"><img src="https://agentmods.dev/badge/skills/supsub-ai/supsub-cli/supsub-sub/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-sub"><img src="https://agentmods.dev/badge/skills/supsub-ai/supsub-cli/supsub-sub.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 | $0.00460 | $0.04699 |
| Opus 5 | $0.00230 | $0.02350 |
| Sonnet 5 | $0.00092 | $0.00940 |
| Haiku 4.5 | $0.00046 | $0.00470 |
Grade C, and why
supsub-sub 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 8d 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
supsub-sub Skill
List, add, remove subscription sources, and browse the articles inside each source. Sources are typed MP(微信公众号)、WEBSITE(网站)或 X(推特 / Twitter 平台账号)。
⚠️ 关于字母「X」的歧义(务必先读)
本文档里 X 有两种完全不同的含义,不要混淆:
--type X—— 这是一个真实的 sourceType 枚举值,专指 推特 / Twitter / X 平台账号。- 占位符 X —— 用户口语里说「订阅 X」「取消订阅 X」「X 公众号最近的文章」时,这里的 X 通常只是一个占位代号,代指某个具体账号(可能是公众号、网站,也可能就是名字里带 X),与推特无关。
判定规则:
- 只有当用户**明确提到「推特 / Twitter / X 平台」**时,才使用
--type X。 - 用户说「订阅 X」「X 公众号」「看 X 的文章」而没有提到推特平台时,不要据此推断
--type X;这里的 X 是占位符,应按其真实类型(多为MP或WEBSITE)处理。
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 subscriptions
supsub sub list [--type <MP|WEBSITE|X>]
| Flag | Default | Description |
|---|---|---|
--type |
— (all) | 过滤来源类型:MP(公众号)/ WEBSITE(网站)/ X(推特) |
Each row includes: sourceId, sourceType, name, img, description, unreadCount。表格模式下 类型 列会把 sourceType 显示为中文:MP→公众号、WEBSITE→网站、X→推特。
# 列出全部订阅
supsub sub list
# 仅看公众号
supsub sub list --type MP
# 仅看网站
supsub sub list --type WEBSITE
# 仅看推特(X 平台账号)
supsub sub list --type X
# 导出 JSON
supsub sub list -o json
JSON shape: {"success":true,"data":[{"sourceType":"MP","sourceId":12345,"name":"...","img":"...","description":"...","unreadCount":3}, ...]}
Add a subscription
sub add 有两条互斥入口,对应两种"拿到的 ID 形态":
# A) 全局搜索 / 已收录源 → 用内部正整数 sourceId
supsub sub add --source-id <id> --type <MP|WEBSITE|X> [--group <gid>]...
# B) mp search 发现的微信原生公众号 → 用 base64 字符串 mpId
supsub sub add --mp-id <mpId> [--type MP] [--group <gid>]...
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.
- 8d ago First seen · 254 lines · 460 tokens per session scan C 10599f3c58e2
supsub-sub is a skill published in the GitHub repository SupSub-AI/supsub-cli (5 stars, last pushed 1mo ago), licensed MIT. It adds 460 tokens to every session and 4,699 once invoked, about $0.0023 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.
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.
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.
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.
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…