rss-feeds: Skill for Claude Code

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

cmd-rss-feed-review is a skill for Claude Code, Codex from Olshansk/rss-feeds. It costs 65 tokens per session (863 once invoked), scanned A, original, MIT.

A code-and-output review process for RSS feed generators. RSS is a format that lets readers and apps receive updates from a website, while the generator creates the feed's XML file.

In plain words
What is it for?
Use it to audit one or all feed generators, inspect their XML output, check network and browser-handling code, and report findings with file and line references.
Why use it?
It helps find broken page selectors, weak error handling, stale caching, invalid or empty feeds, duplicate entries, and incorrect feed links before they affect readers.

Skill for Claude CodeCodex

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

This is Olshansk/rss-feeds's own configuration. It tells Claude Code and Codex 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 →

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-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Olshansk/rss-feeds

Made for: Claude Code, Codex.

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 cmd-rss-feed-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/olshansk/rss-feeds/rss-feed-review/github.svg)](https://agentmods.dev/skills/olshansk/rss-feeds/rss-feed-review)
Your own site
<a href="https://agentmods.dev/skills/olshansk/rss-feeds/rss-feed-review"><img src="https://agentmods.dev/badge/skills/olshansk/rss-feeds/rss-feed-review/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 cmd-rss-feed-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/olshansk/rss-feeds/rss-feed-review"><img src="https://agentmods.dev/badge/skills/olshansk/rss-feeds/rss-feed-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 863 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. 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 $0.00065 $0.00863
Opus 5 $0.00032 $0.00432
Sonnet 5 $0.00013 $0.00173
Haiku 4.5 $0.00006 $0.00086

Measured 10d ago against content hash ec2027022103, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

cmd-rss-feed-review 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 10d 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.

.agents/skills/rss-feed-review/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RSS Feed Review

Review RSS feed generators and their output XML for correctness, robustness, and adherence to project conventions.

Instructions

  1. Determine scope — review all feed generators by default, or a specific one if the user specifies.
  2. Read the target generator(s) and their corresponding feeds/feed_*.xml output files.
  3. Read feed_generators/utils.py to understand shared helpers.
  4. Evaluate against the checklists below. For every finding, cite file_path:line_number.
  5. If everything looks good, say so briefly.

Generator Code Review

Selectors & Parsing

  • Are CSS selectors specific enough to survive minor site redesigns?
  • Are selectors targeting semantic elements (article, h2) over generated class names?
  • Is there fallback logic if a selector returns no results?

Error Handling

  • Does fetch_* use timeout= on requests?
  • Are HTTP errors handled (response.raise_for_status() or status check)?
  • Are Selenium waits using explicit waits (WebDriverWait) rather than time.sleep()?
  • Is the Selenium driver properly closed in a finally block?

Feed Link Setup

Critical convention (from AGENTS.md):

from utils import setup_feed_links
setup_feed_links(fg, blog_url="https://...", feed_name="...")
  • The main <link> must point to the original blog URL, NOT the feed URL
  • rel="self" must be set first, rel="alternate" must be set last
  • Generators should use the setup_feed_links() helper from utils.py
  • Flag any generator that sets links manually instead of using the helper

Cache Logic (Pagination & Selenium patterns only)

  • Is cache loaded before fetching new articles?
  • Are articles deduped by URL before saving?
  • Is the cache sorted by date descending?
  • Does the --full flag correctly bypass incremental logic?

Pattern Compliance

  • Simple Static: No cache needed, fetches all posts each run
  • Pagination + Caching: URL-based pagination with JSON cache in cache/
  • Selenium + Click: Uses undetected-chromedriver, clicks load-more buttons, caches results
  • Is the generator using the right pattern for how the target site loads content?

Read the full file on GitHub · 99 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. 10d ago First seen · 99 lines · 65 tokens per session scan A ec2027022103

Subscribe to this mod's changes

cmd-rss-feed-review is a skill published in the GitHub repository Olshansk/rss-feeds (679 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 863 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 2026-08-30.