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 JeanDiable/obsidian-claude --skill ai-newslettergit clone --depth 1 https://github.com/JeanDiable/obsidian-claudeWrote 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/jeandiable/obsidian-claude/ai-newsletter)<a href="https://agentmods.dev/skills/jeandiable/obsidian-claude/ai-newsletter"><img src="https://agentmods.dev/badge/skills/jeandiable/obsidian-claude/ai-newsletter/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/jeandiable/obsidian-claude/ai-newsletter"><img src="https://agentmods.dev/badge/skills/jeandiable/obsidian-claude/ai-newsletter.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 | $0.00026 | $0.01045 |
| Opus 5 | $0.00013 | $0.00522 |
| Sonnet 5 | $0.00005 | $0.00209 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
ai-newsletter 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Newsletter Curation
Fetch, deduplicate, and rank AI newsletter content into a daily digest.
Vault Path
/Library/Mobile Documents/iCloudmd~obsidian/Documents/My_note
RSS Sources
- TLDR AI:
https://bullrich.dev/tldr-rss/ai.rss - The Rundown AI:
https://rss.beehiiv.com/feeds/2R3C6Bt5wj.xml
Workflow
-
Check cache: Look for
50_Clippings/AI/Newsletters/YYYY-MM/YYYY-MM-DD-摘要.md. If exists with today's date, return cached content. -
Fetch feeds: Use WebFetch on both RSS URLs. Extract title, link, pubDate, description for each item. If RSS fails, fall back to DuckDuckGo MCP search for "AI newsletter this week", "LLM updates this week", targeting TLDR AI, The Rundown AI, Ben's Bites, Import AI, The Batch.
-
Deduplicate: Merge items with similar titles (80%+ word overlap). Keep longer description, track both sources.
-
Rank items by:
- AI relevance (LLM, GPT, Claude, agents, ML, transformer, diffusion keywords)
- Productivity relevance (workflow, automation, tools, PKM)
- Recency (newer = higher)
- Novelty (check recent archives, penalize repeats)
- Practical impact (tools, products > pure research > opinion)
-
Generate digest: Use the template below. Include:
- 精选推荐 (3-5 highest scoring) with content creation angles
- AI动态 section
- 生产力工具 section
- Stats footer
-
Save files using Obsidian CLI (
obsidian create):50_Clippings/AI/Newsletters/YYYY-MM/YYYY-MM-DD-摘要.md(curated digest)50_Clippings/AI/Newsletters/YYYY-MM/原始数据/YYYY-MM-DD_TLDR-AI-Raw.md(raw feed)50_Clippings/AI/Newsletters/YYYY-MM/原始数据/YYYY-MM-DD_Rundown-AI-Raw.md(raw feed)
Digest Template
---
title: "AI Newsletter 摘要 YYYY-MM-DD"
created: YYYY-MM-DD
modified: YYYY-MM-DD
tags: [ai, newsletter, digest]
description: "AI newsletter curated digest"
source: "TLDR AI, The Rundown AI"
type: newsletter-digest
item_count: N
duplicates_merged: N
top_topics: [话题1, 话题2, 话题3]
raw_sources:
- "[[YYYY-MM-DD_TLDR-AI-Raw]]"
- "[[YYYY-MM-DD_Rundown-AI-Raw]]"
---
## Related
- [[AI]]
# AI Newsletter 摘要: YYYY-MM-DD
> 来源: TLDR AI, The Rundown AI
> 原始 Newsletter: [[YYYY-MM-DD_TLDR-AI-Raw]] | [[YYYY-MM-DD_Rundown-AI-Raw]]
## 精选推荐 (内容创作机会)
- [ ] **[标题]** ([来源])
链接: [URL]
亮点: [相关性说明]
角度: [教程 | 工具评测 | 趋势分析 | 对比]
## AI动态
- **[标题]** ([来源])
[简要总结]
链接: [URL]
## 生产力工具
- **[标题]** ([来源])
[简要总结]
链接: [URL]
## 其他值得关注
- **[标题]** ([来源]) - 链接: [URL]
---
**统计:**
- 获取条目总数: X
- 合并重复数: Y
- 最终精选数: Z
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 · 123 lines · 26 tokens per session scan A 4c0f88cb3570
ai-newsletter is a skill published in the GitHub repository JeanDiable/obsidian-claude (2 stars, last pushed 6mo ago), licensed MIT. It adds 26 tokens to every session and 1,045 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…