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.
git 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/commands/feednest-app/mcp/briefing)<a href="https://agentmods.dev/commands/feednest-app/mcp/briefing"><img src="https://agentmods.dev/badge/commands/feednest-app/mcp/briefing/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/commands/feednest-app/mcp/briefing"><img src="https://agentmods.dev/badge/commands/feednest-app/mcp/briefing.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 | $0.00014 | $0.00415 |
| Opus 5.5 | $0.00006 | $0.00166 |
| Sonnet 5.5 | $0.00003 | $0.00083 |
| Haiku 4.5 | $0.00001 | $0.00042 |
Grade A, and why
briefing 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.
What it actually says
Give me a briefing of what's new in my FeedNest feeds. $ARGUMENTS
Use only the FeedNest tools and the articles they return, never the open web.
- Call
get_articlesonce withview: "newsfeed",unread_only: trueandlimit: 100.- If I named a folder, find its ID with
get_foldersand useview: "by-folder"withfolder_id. - If I named a topic, pass it as
query. - Use
date_fromanddate_toonly if I asked for a time span. They need the Pro plan: if the tool says my plan does not include them, carry on without them.
- If I named a folder, find its ID with
- Build the briefing from each article's title, source and
summary_preview. Do not open the articles one by one: on the Free plan FeedNest allows 20 tool calls an hour, so a briefing should take one or two calls. - Group the stories into at most seven topics, the most important first. Under each topic, give one line per story: the title, the source in brackets, and what is new in a few words. Say when several of my sources cover the same story.
- If you got 100 articles, there may be more: say so, and offer to continue with the next page (
before_published_atandbefore_idof the last article). - End by offering to read any story in full, or to mark the articles you covered as read. Ask before marking anything as read.
If nothing is unread, say so and offer the latest articles instead. If FeedNest says I follow no sources yet, point me to feednest.com to add some.
Write the briefing in the language I have been using in this conversation, or in English if there is none.
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 First seen · 22 lines · 14 tokens per session scan A 4345631620a1
briefing is a command published in the GitHub repository feednest-app/mcp (1 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 415 once invoked, about $0.0001 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 2026-10-27.
Other commands, from other repositories
adhoc-flow
Workflow for the rest of tasks: lightweight documentation, build, track, synchronize, etc.
init-workspace-flow-shells
Phase 2 Shells of init-workspace-flow.
setup
Configure MeiGen MCP credentials privately, or set up an OpenAI-compatible provider for ordinary image generation. Use for /meigen:setup, "configure meigen", "add API key", or connection setup requests.
models
List available AI models and switch the default model for this session. Use when user runs /meigen:models to see or change models.
firm
Convene your standing AI staff — memos on every beat, a board session without you, minutes with dissent preserved.
ship-an-mcp-server
Workflow recipe — make your product agent-usable by chaining 4 skills, spec to pricing.