rss-feeds: Skill for Claude Code

.agents/skills/rss-feed-fix/SKILL.md

rss-feed-fix is a skill for Claude Code from Olshansk/rss-feeds. It costs 74 tokens per session (1,697 once invoked), scanned A, original, MIT.

A repair workflow for RSS feed scrapers whose CSS selectors no longer match a blog's current HTML. CSS selectors are rules used to locate parts of a web page, such as an article title or date.

In plain words
What is it for?
It helps identify the broken generator, download the live page, compare its structure with the scraper, update selectors, verify the feed, and add a safety check.
Why use it?
It helps restore feeds that have become empty or stopped updating after a website changes its page structure.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: agent in frontmatter; installed under .agents/ (shared by several agents).

This is Olshansk/rss-feeds's own configuration. It tells Claude Code how to work on rss-feeds itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything rss-feeds configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run feed_generators/validate_feeds.py.

Reuse

Borrowing it

Nothing to install: this file belongs to Olshansk/rss-feeds. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Olshansk/rss-feeds/main/.agents/skills/rss-feed-fix/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Olshansk/rss-feeds

Made for: Claude Code.

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 rss-feed-fix

README.md
[![agentmods](https://agentmods.dev/badge/skills/olshansk/rss-feeds/rss-feed-fix.svg)](https://agentmods.dev/skills/olshansk/rss-feeds/rss-feed-fix)
Your own site
<a href="https://agentmods.dev/skills/olshansk/rss-feeds/rss-feed-fix"><img src="https://agentmods.dev/badge/skills/olshansk/rss-feeds/rss-feed-fix.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,697 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00074 $0.01697
Opus 5 $0.00037 $0.00848
Sonnet 5 $0.00015 $0.00339
Haiku 4.5 $0.00007 $0.00170

Measured 8d ago against content hash dc0e4af58b58, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

rss-feed-fix scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Use `curl` to download the raw HTML (not the WebFetch tool — it converts to markdown and loses class names):
.agents/skills/rss-feed-fix/SKILL.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RSS Feed Fix

You are the RSS Feed Fix Agent. A feed generator is broken — its CSS selectors no longer match the live site. Your job is to download the current HTML, identify what changed, update the selectors, verify the fix, and add a safety guard if one is missing.

Inputs

The user should provide:

  • The feed name (e.g. weaviate, cursor) OR the generator filename (e.g. weaviate_blog.py)

If neither is provided, check feed_generators/validate_feeds.py output or feeds/feed_*.xml to identify which feed is EMPTY.

Workflow

Step 1: Identify the generator and blog URL

  1. Map the feed name to its generator:
    • Feed name → feed_generators/{name}_blog.py
    • If ambiguous, check feeds.yaml for the script: field
  2. Read the generator file in full.
  3. Note: BLOG_URL, FEED_NAME, and every CSS selector used in parse_* functions.

Step 2: Fetch the live HTML

Use curl to download the raw HTML (not the WebFetch tool — it converts to markdown and loses class names):

curl -s "{BLOG_URL}" -o /tmp/feed_fix_live.html

If the site blocks curl (empty body or 403), try with a browser-like User-Agent:

curl -s -A "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36" "{BLOG_URL}" -o /tmp/feed_fix_live.html

If the site is JavaScript-rendered (SPA), note that and advise the user to provide a saved HTML file. Do not attempt to spin up Selenium during a fix — that requires a separate debugging session.

Step 3: Diagnose the broken selectors

For each selector used in the generator's parse_* functions, check whether it still matches:

python3 -c "
import sys
sys.path.insert(0, 'feed_generators')
from bs4 import BeautifulSoup

with open('/tmp/feed_fix_live.html') as f:
    soup = BeautifulSoup(f.read(), 'html.parser')

# Test each selector from the generator
selectors = [
    'article.margin-bottom--xl',   # replace with actual selectors
    'a[itemprop=\"url\"]',
    'meta[itemprop=\"description\"]',
    'time[datetime]',
]
for sel in selectors:
    results = soup.select(sel)
    print(f'{len(results):4d} matches  {sel}')
"

Read the full file on GitHub · 196 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 · 196 lines · 74 tokens per session scan A dc0e4af58b58

Subscribe to this mod's changes

rss-feed-fix is a skill published in the GitHub repository Olshansk/rss-feeds (678 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 1,697 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

interactive-login

How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.

yc-software/qm · 46 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

azure-messaging-webpubsub-java

Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.

microsoft/skills · 43 tokens

google-safe-browsing

Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…

davidondrej/skills · 105 tokens