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 feednest-app/mcp --skill feednestgit clone --depth 1 https://github.com/feednest-app/mcpWrote 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/feednest-app/mcp/feednest)<a href="https://agentmods.dev/skills/feednest-app/mcp/feednest"><img src="https://agentmods.dev/badge/skills/feednest-app/mcp/feednest/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/feednest-app/mcp/feednest"><img src="https://agentmods.dev/badge/skills/feednest-app/mcp/feednest.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 | $0.00055 | $0.01757 |
| Opus 5.5 | $0.00022 | $0.00703 |
| Sonnet 5.5 | $0.00011 | $0.00351 |
| Haiku 4.5 | $0.00006 | $0.00176 |
Grade A, and why
feednest 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 today.
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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FeedNest: Your Sources, Not the Whole Web
A web search looks at the whole internet. FeedNest is different: you work only with the sources the user chose, the blogs they trust, the publications they follow, the experts they believe in. No algorithmic noise, no black-box results: answers grounded in their world.
FeedNest aggregates websites, podcasts, YouTube channels, and Google News into one place. You can read articles, manage highlights and notes, tag content, save links, and check reading stats. Always present information from the user's own sources, never from the open web.
Requirements
This skill uses the FeedNest MCP server at https://mcp.feednest.com. The user signs in with their FeedNest account when the plugin connects, so no API key is needed.
What each FeedNest plan allows:
- Free: read feeds, folders, articles, saved articles, tags, and highlights, up to 20 tool calls an hour. Nothing can be changed.
- Plus and Pro: also notes, reading stats, full article text with
extract_article, and every write (save, tag, highlight, mark as read). - Date filters (
date_from,date_to,since) need Pro. Without them, articles still come newest first.
When a tool answers that something is not included in the user's plan, say so plainly and carry on with what the plan allows.
When to Use Each Tool
Reading Articles
| Intent | Tool | Key Params |
|---|---|---|
| "What's new?" | get_articles |
view: "newsfeed", unread_only: true |
| "How many articles today?" | get_articles |
view: "newsfeed", count_only: true, date_from, date_to (Pro) |
| "Today's recap" | get_articles |
count_only: true first, then paginate with limit: 100 and use the summary previews |
| "News from folder Tech" | get_articles |
view: "by-folder", folder_id |
| "Articles from Vercel blog" | get_articles |
view: "by-feed", feed_id |
| "Search for React" | get_articles |
view: "newsfeed", query: "React" |
| "Articles tagged AI" | get_articles |
view: "by-tag", tag_id |
| "Articles with highlights" | get_articles |
view: "highlighted" |
| "Articles with notes" | get_articles |
view: "noted" |
| "What did I read yesterday?" | get_recently_read |
since: "<yesterday ISO>" (Pro) |
| "Full article content" | get_article |
article_id: if it reads in under a minute, the feed probably sent an excerpt |
| "Load full content from URL" | extract_article |
article_id, only when the content is truncated |
What ships with it
1 file 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.
- today Changed · +34 tokens per session 8bd2840af8bc
- 10d ago Changed · +6 lines dd8830229078
- 1mo ago Changed · -6 lines ad275968ec80
- 1mo ago First seen · 144 lines · 21 tokens per session scan A b613d959feaf
feednest is a skill published in the GitHub repository feednest-app/mcp (1 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 1,757 once invoked, about $0.0002 per session on Opus 5.5. 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
9router-stt
Speech-to-text via 9Router /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models. Use when the user wants to transcribe audio, convert speech to text, or get subtitles from audio files.
9router-web-fetch
Fetch URL → markdown / text / HTML via 9Router /v1/web/fetch using Ollama Cloud / Firecrawl / Jina Reader / Tavily Extract / Exa Contents. Use when the user wants to scrape a webpage, extract URL content, read article, or convert a URL to markdown.
9router-web-search
Web and X search via 9Router /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Linkup / SearchAPI / You.com / Perplexity / Xquik. Use when the user wants to search the web, find articles, or search public X posts.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
Product Photoshoot Workflow
A workflow for turning one product photo into a set of four e-commerce images from different visual directions.
requirements-authoring
To author, update, and validate functional/non-functional requirements as atomic units with user approval.