feed-curation

feed-curation is a skill for Claude Code from ManiaSacha/web-mcp. It costs 60 tokens per session (656 once invoked), scanned A, original, MIT.

A guide for managing RSS and Atom feeds in a web-mcp server. It covers adding sources, checking whether they work, and removing or replacing feeds that are empty or too noisy.

In plain words
What is it for?
Use it to add news sources, check feed health, reduce unwanted articles, or replace unreliable feeds.
Why use it?
It removes the guesswork from building a useful set of feeds and finding broken sources. It also explains how to handle feed URLs that fail validation or parsing.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the web-mcp plugin — 2 skills, 3 agents, 1 MCP server shipped together

Good fit Use it to add news sources, check feed health, reduce unwanted articles, or replace unreliable feeds.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/maniasacha/web-mcp/feed-curation
Install

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.

Any agent
npx skills add ManiaSacha/web-mcp --skill feed-curation
Clone the repo
git clone --depth 1 https://github.com/ManiaSacha/web-mcp

Made for: Claude Code.

Or install web-mcp, the plugin that ships this one along with the rest of its 2 skills, 3 agents, 1 MCP server.

Wrote 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.

agentmods badge for feed-curation

README.md
[![agentmods](https://agentmods.dev/badge/skills/maniasacha/web-mcp/feed-curation/github.svg)](https://agentmods.dev/skills/maniasacha/web-mcp/feed-curation)
Your own site
<a href="https://agentmods.dev/skills/maniasacha/web-mcp/feed-curation"><img src="https://agentmods.dev/badge/skills/maniasacha/web-mcp/feed-curation/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.

agentmods 80×15 button for feed-curation

Your own site · 80×15
<a href="https://agentmods.dev/skills/maniasacha/web-mcp/feed-curation"><img src="https://agentmods.dev/badge/skills/maniasacha/web-mcp/feed-curation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 656 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00060 $0.00656
Opus 5 $0.00030 $0.00328
Sonnet 5 $0.00012 $0.00131
Haiku 4.5 $0.00006 $0.00066

Measured 8d ago against content hash 5a2afaa02c2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

feed-curation 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 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.

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.

skills/feed-curation/SKILL.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feed curation

Helps a user build and maintain a healthy set of feeds in a running web-mcp server.

Adding feeds

  1. Ask what topic(s) or sources the user wants covered, if not already clear.
  2. Prefer well-known, stable RSS/Atom endpoints (a project's own /feed/ or /rss path, not a third-party aggregator scraping it) — these are less likely to disappear or change shape.
  3. Call the add_feed tool for each candidate URL and read its response — it reports how many articles were indexed, or a fetch/parse error. Zero articles indexed is worth flagging to the user even if the call "succeeded": it usually means the URL isn't actually a feed, or is empty.
  4. If add_feed fails, read the error message before retrying — it will say if the URL was rejected for scheme/host reasons (assert_fetchable) or failed to parse as XML. Don't just retry blindly; confirm the URL actually points at a feed (open it in a browser check, or ask the user) before trying alternates.

Auditing existing feeds

  1. Call source_health() and read it feed-by-feed. Statuses:
    • OK — fine, no action needed.
    • WARN — no successful refresh in >24h. Worth a mention, not necessarily removal.
    • SILENT — no successful refresh in >7 days. Likely dead or moved; recommend removal or check for a replacement URL.
    • ERROR — currently failing; read the attached error text and explain what it means in plain terms (fetch timeout, non-200, XML parse failure, SSRF rejection because the URL is misconfigured, etc).
  2. Call list_feeds() for article counts. A feed with a suspiciously low count relative to others might be under-indexed rather than genuinely low-volume — a refresh() call can confirm.

Pruning noisy feeds

If the user says a feed is too noisy (dominating recent()/digest() output), use trending() and digest() to show what it's contributing, confirm with the user which feed is the source, then remove_feed(url). Removal is immediate and drops that feed's already-indexed articles too — mention that before doing it, since it's not trivially reversible without re-adding and re-fetching.

Read the full file on GitHub · 34 lines

Changes

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.

  1. 8d ago First seen · 34 lines · 60 tokens per session scan A 5a2afaa02c2a

Subscribe to this mod's changes

feed-curation is a skill published in the GitHub repository ManiaSacha/web-mcp (0 stars, last pushed 20d ago), licensed MIT. It adds 60 tokens to every session and 656 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

rss-digest

Subscribe to RSS/Atom feeds with keyword filters and run digests delivered to Telegram. Use when subscribing to feeds, checking which feeds run, running a digest manually, or adjusting feed keywords.

JansenAnalytics/claudex · 42 tokens

feishu-memory-recall

Cross-group memory, search, and event sharing for OpenClaw Feishu agents.

CraftOS-dev/CraftBot · 22 tokens

building-threat-intelligence-feed-integration

Builds automated threat intelligence feed integration pipelines connecting STIX/TAXII feeds, open-source threat intel, and commercial TI platforms into SIEM and security tools for real-time IOC matching and alerting. Use when SOC teams need to operationalize threat intelligence by automating feed ingestion…

26zl/cybersec-toolkit · 74 tokens

support-digest

A local tool that reads exported customer-support tickets in JSON or CSV and produces a daily summary after hiding personal information. It does not fetch data from support systems or call outside APIs.

ChanningLua/prax-agent · 31 tokens

knowledge-compile

A knowledge-organizing tool that turns a folder of scattered Markdown notes, articles, and captured posts into an Obsidian-style wiki. It creates an index, topic pages with links back to the originals, and a short daily digest.

ChanningLua/prax-agent · 40 tokens

stream-flutter

Build and integrate Stream Chat, Video, and Feeds in Flutter apps. Use for Flutter/Dart project work with Stream package setup, auth wiring, and widget blueprints. Supports streamchatflutter (pre-built Chat UI), streamchatfluttercore (custom Chat UI), streamvideoflutter (Video calling and livestreaming), and…

GetStream/agent-skills · 112 tokens