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 redfox-data/redfox-community-dsh --skill bili-ai-feedgit clone --depth 1 https://github.com/redfox-data/redfox-community-dshWrote 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/redfox-data/redfox-community-dsh/bili-ai-feed)<a href="https://agentmods.dev/skills/redfox-data/redfox-community-dsh/bili-ai-feed"><img src="https://agentmods.dev/badge/skills/redfox-data/redfox-community-dsh/bili-ai-feed/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/redfox-data/redfox-community-dsh/bili-ai-feed"><img src="https://agentmods.dev/badge/skills/redfox-data/redfox-community-dsh/bili-ai-feed.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 | $0.00161 | $0.03493 |
| Opus 5 | $0.00081 | $0.01747 |
| Sonnet 5 | $0.00032 | $0.00699 |
| Haiku 4.5 | $0.00016 | $0.00349 |
Grade A, and why
bili-ai-feed 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 12d 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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
B站AI信息源
📝 简介
每日自动扫描B站AI创作内容，按点赞量筛选爆款视频，智能聚类后生成HTML日报。同步基于热门话题执行AI情报调查，使用多搜索引擎交叉验证，输出结构化调查报告。
重要：数据每日15:00更新前一天数据，目标日期无数据时禁止自动调用接口，必须先告知用户并等待确认。
✨ 功能特性
| 功能模块 | 能力描述 | 核心价值 |
|---|---|---|
| 爆款发现 | 从B站AI相关视频中按点赞量筛选热门内容 | 精准定位高热度AI视频 |
| 智能查询 | 默认只查“AI”，数据不足时自动扩展关键词批量查询 | 节省接口额度，高效获取数据 |
| 自定义查询 | 用户可指定任意关键词组合定向查询与分析 | 灵活覆盖任意AI细分方向 |
| 智能聚类 | 自动识别话题方向（AI教程、大模型、AI绘画等） | 每天分类由内容动态决定 |
| AI情报调查 | 基于热门话题执行多引擎搜索+交叉验证 | 深度挖掘话题背后的情报 |
| 可视化日报 | 深色主题HTML，封面图+互动数据+视频直链 | 直观展示每日AI热点 |
| 一键订阅 | --subscribe 开启每日自动产出 |
日报自动攒在本地文件夹 |
🔑 鉴权
数据查询接口通过请求头 X-API-KEY 鉴权，Key 从环境变量 REDFOX_API_KEY 获取。
API Key 获取：前往 红狐Hub 官网 注册，登录后在个人中心获取，格式为 ak_xxxxxxxx。新注册用户获赠免费积分。
配置方式：
- macOS/Linux：将
export REDFOX_API_KEY=<值>追加到~/.zshrc或~/.bashrc，然后source使其生效 - Windows：
[Environment]::SetEnvironmentVariable("REDFOX_API_KEY", "<值>", "User")（需重启终端） - 配置后验证：
echo $REDFOX_API_KEY（macOS/Linux）或echo %REDFOX_API_KEY%（Windows）
查询接口调用时通过 source 字段同步记录，无需额外请求保存接口。
🔄 工作流程
第零步：日期有效性预检（必须执行，先于任何接口调用）
⛔ 核心规则：未经用户确认，禁止调用任何数据接口，禁止自动执行
--latest绝对不能在用户未确认的情况下自动执行脚本获取数据。
数据更新规则：每日15:00更新前一天的数据
- 15:00前：最新可用日期 = T-2（前天）
- 15:00后：最新可用日期 = T-1（昨天）
执行流程（每次查询前强制执行）：
- 获取当前系统日期 T 和当前时间，按15:00规则计算最新可用日期
- 判断用户请求的目标日期是否在无数据区间（即 > 最新可用日期）
- 若目标日期有数据（≤ 最新可用日期）：直接执行第一步，无需额外确认
- 若目标日期无数据（> 最新可用日期），向用户输出以下提示：
**⚠️{查询日期}数据尚未更新**
数据更新规则：每日15:00更新前一天的数据
当前可查询的最新日期：{最新可查询到数据的日期}
是否需要查询{最新可查询到数据的日期}的数据？
- 等待用户明确确认后，才能执行第一步（带
--latest参数） - 若用户拒绝，则不执行任何接口调用
示例对话：
用户：查询今天的AI日报
Agent：⚠️2026-06-16数据尚未更新
数据更新规则：每日15:00更新前一天的数据
当前可查询的最新日期：2026-06-14
是否需要查询2026-06-14的数据？
用户：好的
Agent：（执行 python3 daily_report.py --latest）
第一步：生成爆款日报
# 生成最新一期日报（用户确认后，自动跳过无数据日期，不扣积分）
python3 "$SKILL_PATH/assets/daily_report.py" --latest
# 生成指定日期日报（历史日期已有数据，无需确认）
python3 "$SKILL_PATH/assets/daily_report.py" --date 2026-06-10
# 自定义关键词查询（用户指定方向，数据不足时按顺序逐个扩展）
python3 "$SKILL_PATH/assets/daily_report.py" --keywords "AI教程,AI绘画,ChatGPT" --latest
# 订阅 / 取消订阅
python3 "$SKILL_PATH/assets/daily_report.py" --subscribe
python3 "$SKILL_PATH/assets/daily_report.py" --unsubscribe
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 271 lines · 161 tokens per session scan A d2ed79e79adc
bili-ai-feed is a skill published in the GitHub repository redfox-data/redfox-community-dsh (6 stars, last pushed yesterday), licensed MIT. It adds 161 tokens to every session and 3,493 once invoked, about $0.0008 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 skills, from other repositories
dsh-hooks-authoring
Instructions for writing and debugging dsh-hooks-plugin scripts, which run during tool or session events such as before a tool call or after it finishes. These scripts return JSON decisions such as allowing, asking about, or denying an action.
web-artifact-designer
A design workflow for producing self-contained HTML or SVG files that open directly in a browser. It covers visual work such as posters, infographics, landing pages, charts, banners, cards, and interface mockups.
dsh-web-pet-developer
Create a pet for the dsh-pet plugin and integrate it into the dsh web GUI — author a v2 pet.json manifest plus an 8-column x 9-row atlas per the Codex/hatch-pet contract (live2d pets, voice packs and status decorations included), drop it into the pet-center user directory or contribute it as a built-in asset under…
company-research-method
A documented process for researching a company using supplied files and selected public sources. It produces a company overview with business details, sourced financial figures, and stated risks.
dsh-plugin-guide
Use when developing, reviewing, packaging, debugging, or answering questions about DeepSeek Harness (DSH) plugins — the plugin-based agent harness on vendored Cordis. Applies the official plugin-development constraints (plugin contract, cordis.yml layers, services/events/effects, tool DSL, bundles/profiles) backed by…
delivery-proof
Delivery proof and the doublecheck report. Use when the work is done and the delivery must be proven — consolidate the spec, test timeline, review verdicts, and verification checks into a doublecheckreport, and only then claim completion.