NewsBlur: Command for Claude Code

.claude/commands/blog-post.md

blog-post is a command for Claude Code from samuelclay/NewsBlur. It costs 14 tokens per session (828 once invoked), scanned A, original, MIT.

A command that drafts a NewsBlur feature announcement from the changes on the current Git branch and recent blog posts. It can use requested length, tone, and focus.

In plain words
What is it for?
Use it to prepare short, standard, or in-depth Markdown blog posts with matching structure, screenshots, examples, and closing information.
Why use it?
It removes the need to manually inspect code changes and imitate the existing blog style when announcing a new feature.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is samuelclay/NewsBlur's own configuration. It tells Claude Code how to work on NewsBlur 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 NewsBlur configures →

About the project

NewsBlur is a personal RSS news reader and social network that displays stories, the original sites they come from, and tools for filtering and discussing them. Readers use it to follow subscriptions, train story preferences, search and tag articles, share reading, and optionally self-host the service. The catalogue entries provide commands, skills, instructions, hooks, and settings for working with the NewsBlur project.

samuelclay/NewsBlur · 7,612 stars · on GitHub · newsblur.com

Reuse

Borrowing it

Nothing to install: this file belongs to samuelclay/NewsBlur. 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/samuelclay/NewsBlur/main/.claude/commands/blog-post.md
Clone the repo
git clone --depth 1 https://github.com/samuelclay/NewsBlur

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 blog-post

README.md
[![agentmods](https://agentmods.dev/badge/commands/samuelclay/newsblur/blog-post/github.svg)](https://agentmods.dev/commands/samuelclay/newsblur/blog-post)
Your own site
<a href="https://agentmods.dev/commands/samuelclay/newsblur/blog-post"><img src="https://agentmods.dev/badge/commands/samuelclay/newsblur/blog-post/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 blog-post

Your own site · 80×15
<a href="https://agentmods.dev/commands/samuelclay/newsblur/blog-post"><img src="https://agentmods.dev/badge/commands/samuelclay/newsblur/blog-post.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 828 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 $0.00014 $0.00828
Opus 5 $0.00007 $0.00414
Sonnet 5 $0.00003 $0.00166
Haiku 4.5 $0.00001 $0.00083

Measured 9d ago against content hash 62fb825fdb4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

blog-post 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 9d 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.

.claude/commands/blog-post.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.

Your task

Write a blog post announcing a new NewsBlur feature based on the changes in the current branch. The blog post should match NewsBlur's voice and style.

Arguments provided: {{ arguments }}

Use the arguments to determine:

  • Length: short (2-3 paragraphs), medium (standard feature announcement), or long (in-depth with history/context)
  • Tone: Any specific tone guidance (excited, technical, casual, etc.)
  • Focus: Any specific aspects to emphasize

Steps to execute

  1. Analyze the branch changes to understand the feature:

    git log main..HEAD --oneline
    git diff main..HEAD --stat
    

    Then read the full diff to understand what was built:

    git diff main..HEAD
    
  2. Read the last 10 blog posts to match the voice and style:

    ls -t blog/_posts/*.md | head -10
    

    Read each of these files to understand:

    • The conversational first-person voice
    • How features are introduced and explained
    • Screenshot placement and formatting
    • Section structure (headers, examples, etc.)
    • How posts end (forum link, availability info)
  3. Write the blog post following these guidelines:

    Front matter:

    ---
    layout: post
    title: <compelling title that describes the feature>
    tags: ["web"]  # or ["ios"], ["android"], or multiple
    ---
    

    Voice and style:

    • First-person conversational tone ("I wanted...", "You can now...")
    • Start with the problem or motivation, then introduce the solution
    • Be direct and practical, not marketing-speak
    • Include real examples of how to use the feature
    • No em dashes or hyphens as punctuation. Restructure sentences instead.
    • Avoid AI slop: no overly polished language, no filler phrases like "excited to announce"

    Screenshots:

    • Use placeholder comments where screenshots should go:
      <!-- SCREENSHOT: description of what to capture -->
      <img src="/assets/FILENAME.png" style="width: 80%;border: 1px solid rgba(0,0,0,0.1);margin: 24px auto;display: block;">
      
    • Adjust width (50%, 60%, 80%, 90%, 100%) based on content
    • Screenshots should show the feature in action

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. 9d ago First seen · 99 lines · 14 tokens per session scan A 62fb825fdb4f

Subscribe to this mod's changes

blog-post is a command published in the GitHub repository samuelclay/NewsBlur (7,612 stars, last pushed 5d ago), licensed MIT. It adds 14 tokens to every session and 828 once invoked, about $0.0001 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.