rss-monitor
Skill1 starsChanged 4 months agoMITView on GitHub
Use when the user wants to be notified when a blog, news feed, or other RSS/Atom source publishes new content, or wants to track updates from multiple feeds in one place — triggers include "monitor this RSS feed", "notify me when this blog updates", or "watch for new entries".
- Installs packages
1 other project uses a version of this.
Adopted by
Most recently taken up by
- claude-world/claude-agenttheir own version, first seen Mar 22, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- claude-world/claude-agent★ 5same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository58 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- api-test-suiteSkill
- ascii-artSkill
- caddy-reverse-proxySkill
- changelog-generatorSkill
- color-palette-generatorSkill
- cron-taskSkill
- csv-toolkitSkill
- discord-bot-buildSkill
- docker-umbrellaSkill
- dotfiles-manageSkill
- email-sendSkill
- env-config-managerSkill
- excalidraw-diagramSkill
- file-organizerSkill
- forgejo-self-hostSkill
- frontend-design-toolkitSkill
- generate-dockerfileSkill
- gif-searchSkill
- git-backupSkill
- github-actions-ciSkill
- hallmark-readmeSkill
- http-api-testerSkill
- invoice-generatorSkill
- json-formatterSkill
- log-analyzerSkill
- markdown-linterSkill
- markdown-to-pdfSkill
- markdown-to-slidesSkill
- mcp-server-buildSkill
- media-id-mappingSkill
- movie-catalogue-siteSkill
- movie-night-calendarSkill
- ntfy-notifierSkill
- ocr-documentsSkill
- ollama-localSkill
- openapi-generatorSkill
- password-generatorSkill
- pdf-extractSkill
- portfolio-upkeepSkill
- qr-code-generatorSkill
- regex-testerSkill
- resume-builderSkill
- searxng-self-hostSkill
- skill-publishSkill
- skill-registry-catalogSkill
- skills-portfolio-scaffoldSkill
- snippet-managerSkill
- sqlite-dashboardSkill
- streaming-provider-embedsSkill
- tailscale-deploySkill
- telegram-bot-buildSkill
- tmdb-metadataSkill
- uptime-kuma-self-hostSkill
- watchlist-syncSkill
- webhook-receiverSkill
- youtube-transcriptSkill
The file
Files
rss-monitor
Overview
Monitor RSS and Atom feeds for new entries. The agent sets up a feed monitoring loop that checks feeds on a schedule, detects new entries, and delivers notifications via your preferred channel (Telegram, Discord, email, ntfy).
When to Use
- The user wants to know when a blog publishes a new post.
- The user wants to monitor news feeds for specific topics.
- The user wants to track updates from multiple sources in one place.
- The user says "monitor this RSS feed", "notify me when this blog updates", or "watch for new entries".
Prerequisites
- Python 3.8+ with
feedparserinstalled:pip install feedparser - A notification channel (ntfy, Telegram, Discord, or email)
Feed Discovery
Find the RSS/Atom feed for a site
# Check for <link rel="alternate"> in the HTML
curl -s https://example.com | grep -oP '(?<=href=")[^"]*(rss|atom|feed)[^"]*'
# Common feed paths to try
curl -s -o /dev/null -w "%{http_code}" https://example.com/feed/
curl -s -o /dev/null -w "%{http_code}" https://example.com/rss/
curl -s -o /dev/null -w "%{http_code}" https://example.com/atom.xml
curl -s -o /dev/null -w "%{http_code}" https://example.com/feed.xmlVerify a feed is valid
import feedparser
feed = feedparser.parse("https://example.com/feed/")
print(f"Feed: {feed.feed.get('title', 'Unknown')}")
print(f"Entries: {len(feed.entries)}")
for entry in feed.entries[:3]:
print(f" - {entry.title}")Monitoring Loop
Simple monitor script
#!/usr/bin/env python3
"""Monitor RSS feeds for new entries. Notifies via ntfy on new content."""
import feedparser
import requests
import json
import os
import time
from datetime import datetime, timezone
FEEDS = [
"https://blog.example.com/feed/",
"https://news.ycombinator.com/rss",
]
STATE_FILE = os.path.expanduser("~/.rss-monitor-state.json")
NTFY_TOPIC = "rss-alerts-abc123"
def load_state():
if os.path.exists(STATE_FILE):
with open(STATE_FILE) as f:
return json.load(f)
return {}
def save_state(state):
with open(STATE_FILE, 'w') as f:
json.dump(state, f, indent=2)
def notify(title, body):
requests.post(
f"https://ntfy.sh/{NTFY_TOPIC}",
data=body.encode('utf-8'),
headers={"Title": title, "Tags": "rss,new"}
)
def check_feeds():
state = load_state()
new_entries = []
for feed_url in FEEDS:
feed = feedparser.parse(feed_url)
seen_ids = state.get(feed_url, [])
for entry in feed.entries:
entry_id = entry.get('id', entry.get('link', ''))
if entry_id not in seen_ids:
new_entries.append({
'feed': feed.feed.get('title', feed_url),
'title': entry.title,
'link': entry.get('link', ''),
'published': entry.get('published', '')
})
# Update seen IDs (keep last 100)
all_ids = [e.get('id', e.get('link', '')) for e in feed.entries]
state[feed_url] = list(set(seen_ids + all_ids))[-100:]
save_state(state)
for entry in new_entries:
title = f"New: {entry['title'][:60]}"
body = f"{entry['feed']}\n{entry['link']}"
notify(title, body)
print(f"New entry: {entry['feed']} — {entry['title']}")
if not new_entries:
print(f"No new entries ({datetime.now().isoformat()})")
if __name__ == "__main__":
check_feeds()Schedule with cron
# Check every hour
crontab -e
# Add:
0 * * * * /usr/bin/python3 /path/to/rss-monitor.py
# Or with Hermes cron
hermes cron create "1h" --prompt "Run the RSS monitor script at scripts/rss-monitor.py and report any new entries"Change Detection
The monitor tracks seen entry IDs to detect what's new. Two approaches:
| Approach | How | Tradeoff |
| Entry ID tracking | Store entry IDs in a JSON state file | Reliable, but misses entries if IDs change |
| Timestamp threshold | Notify on entries newer than last check | Simpler, but misses backdated entries |
The script above uses entry ID tracking — more reliable for most feeds.
Filtering
Keyword filter
KEYWORDS = ["python", "ai", "agents", "llm"]
def matches_keywords(entry):
text = (entry.title + " " + entry.get('summary', '')).lower()
return any(kw in text for kw in KEYWORDS)
# In check_feeds, before notifying:
if matches_keywords(entry):
notify(title, body)Regex filter
import re
PATTERNS = [
re.compile(r'\b(funding|series [a-c])\b', re.IGNORECASE),
re.compile(r'\b(security|vulnerability|cve)\b', re.IGNORECASE),
]
def matches_patterns(entry):
text = entry.title + " " + entry.get('summary', '')
return any(p.search(text) for p in PATTERNS)Notification Delivery
| Channel | How |
| ntfy | requests.post(f"https://ntfy.sh/{topic}", data=body, headers={"Title": title}) |
| Discord | Webhook URL: requests.post(discord_webhook_url, json={"content": f"**{title}**\n{body}"}) |
| Telegram | Bot API: requests.post(f"https://api.telegram.org/bot{token}/sendMessage", json={"chat_id": chat_id, "text": f"{title}\n{body}"}) |
See the email-send skill |
Common Pitfalls
- Feed URL changes silently. Sites sometimes change their feed URL without redirecting — a 404 from a previously-working feed means the site needs a new feed URL found.
- Polling too frequently. Most publishers don't update more than a few times per day — checking every 15-30 minutes is sufficient; checking every minute risks the monitor's IP getting blocked.
- Entry ID instability causing duplicates. Some feeds don't provide stable entry IDs — if
idchanges between checks, fall back to using the entry link as the dedup key. - Partial feed content. Some feeds only include a summary, not the full article — follow the entry link and scrape the page if full text is needed.
- Inconsistent date fields. Feeds vary between
published,updated, andcreated— usefeedparser's parsed fields (entry.published_parsed, atime.struct_time) rather than string-parsing. - State file corruption causing re-notification. A corrupted state JSON makes the monitor treat every entry as new — handle JSON decode errors gracefully and fall back to a fresh state rather than crashing.
- Authenticated feeds. Private Substacks and paid newsletters require auth headers — fetch with
requestsusing auth, then pass the response text tofeedparser.parse()instead of the URL.
Verification Checklist
- Feed URL verified valid with
feedparser.parse()returning a non-emptyentrieslist - State file (
~/.rss-monitor-state.jsonor equivalent) created and persists entry IDs across runs - A test run against a feed with a known new entry actually triggers a notification
- Polling interval is 15+ minutes (not aggressive enough to risk IP blocking)
- Notification channel (ntfy/Discord/Telegram/email) confirmed to deliver by checking for the message
- Keyword/regex filters (if used) tested against both matching and non-matching sample entries
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

