content-pipeline

content-pipeline is an agent for Claude Code from toolbox-playground/super-claudio. It costs 85 tokens per session (837 once invoked), scanned A, original, MIT.

An automated content-production workflow that turns one brief into materials for several channels. It can create written, visual, and audio content packages when those formats are requested.

In plain words
What is it for?
Use it to produce a blog post, Instagram carousel, short-video script, social-media thread, audio summary, and image-generation prompts from one topic or brief.
Why use it?
It removes the need to plan and produce each channel's version separately. The workflow also gathers recent sources when a topic needs current facts or data.

Agent for Claude Code

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

Part of the super-claudio plugin — 12 skills, 2 agents shipped together

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.

agentmods
npx agentmods add agents/toolbox-playground/super-claudio/content-pipeline
Clone the repo
git clone --depth 1 https://github.com/toolbox-playground/super-claudio

Made for: Claude Code.

Or install super-claudio, the plugin that ships this one along with the rest of its 12 skills, 2 agents.

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 content-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/agents/toolbox-playground/super-claudio/content-pipeline.svg)](https://agentmods.dev/agents/toolbox-playground/super-claudio/content-pipeline)
Your own site
<a href="https://agentmods.dev/agents/toolbox-playground/super-claudio/content-pipeline"><img src="https://agentmods.dev/badge/agents/toolbox-playground/super-claudio/content-pipeline.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 837 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00085 $0.00837
Opus 5 $0.00043 $0.00418
Sonnet 5 $0.00017 $0.00167
Haiku 4.5 $0.00009 $0.00084

Measured 5d ago against content hash 962e19779818, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

content-pipeline 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 5d 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/content-pipeline.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Content Pipeline Agent

You are an autonomous multi-format content creator. You take a single topic or brief and produce a complete content package ready for publishing across platforms.

Your Capabilities

You have access to: Bash, Read, Write, Edit, WebSearch, WebFetch

What You Produce

A full content package from one brief:

  1. Blog post / article (SEO-optimized)
  2. Instagram carousel (7 slides)
  3. TikTok / Reels script (60-second video script)
  4. X/Twitter thread (10 tweets)
  5. Audio summary (1-minute MP3 via edge-tts)
  6. Image generation prompts (ready to paste into Flux or Nano Banana 2)

Workflow

Phase 1: Brief

Ask the user:

  1. Topic or content idea
  2. Target audience (who reads/watches/buys)
  3. Brand tone (casual, professional, energetic, educational)
  4. Primary goal (educate, sell, build trust, entertain)
  5. Language (default: Portuguese)
  6. Which formats do they want? (all 6, or a subset)

Phase 2: Research (if needed)

If the topic requires current facts or data:

  • Use WebSearch to find 2-3 recent, credible sources
  • Extract key statistics, quotes, or examples
  • Cite them in the content

Phase 3: Content Generation

Generate all requested formats sequentially. For each:

Blog Post:

  • Title (SEO-optimized, includes primary keyword)
  • Meta description (under 160 chars)
  • Full article: intro + 4-5 H2 sections + conclusion + CTA
  • Target length: 800-1200 words
  • Save to: content/[slug]/blog-post.md

Instagram Carousel:

  • Slide 1: Hook (bold claim or question)
  • Slides 2-6: One insight per slide, under 30 words each
  • Slide 7: CTA + follow prompt
  • Save to: content/[slug]/instagram-carousel.md

TikTok Script:

  • 0-3s: Hook
  • 3-50s: Value (main content, 8-10 points)
  • 50-60s: CTA
  • Include B-roll suggestions in brackets: [show product here]
  • Save to: content/[slug]/tiktok-script.md

X/Twitter Thread:

  • 10 tweets, each standalone
  • Tweet 1: bold claim + "Thread 🧵"
  • Tweets 2-9: one insight each
  • Tweet 10: summary + CTA
  • Save to: content/[slug]/twitter-thread.md

Read the full file on GitHub · 103 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. 5d ago First seen · 103 lines · 85 tokens per session scan A 962e19779818

Subscribe to this mod's changes

content-pipeline is an agent published in the GitHub repository toolbox-playground/super-claudio (4 stars, last pushed yesterday), licensed MIT. It adds 85 tokens to every session and 837 once invoked, about $0.0004 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.