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.
npx agentmods add commands/kanaerulabs/growth-kit/mediumgit clone --depth 1 https://github.com/kanaerulabs/growth-kitWrote 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.
[](https://agentmods.dev/commands/kanaerulabs/growth-kit/medium)<a href="https://agentmods.dev/commands/kanaerulabs/growth-kit/medium"><img src="https://agentmods.dev/badge/commands/kanaerulabs/growth-kit/medium.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00008 | $0.03640 |
| Opus 5 | $0.00004 | $0.01820 |
| Sonnet 5 | $0.00002 | $0.00728 |
| Haiku 4.5 | $0.00001 | $0.00364 |
Grade A, and why
medium 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 467 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Convert any content source to Medium-ready format. This command is adaptive - it works with any input format and blog structure.
Usage: $ARGUMENTS
Phase 1: Universal Input Detection
Parse Input:
- Extract content input from
$ARGUMENTS - Examples:
2025-10-06-my-post(slug)path/to/article.md(file path)https://myblog.com/post(URL)
Detect and Load Content:
If input looks like a file path (contains / or file extension):
- Use Read tool to load the file
- Detect format by extension:
.md/.mdx→ Parse markdown with frontmatter.pdf→ Inform user PDF parsing is limited, suggest markdown.html→ Extract main content, strip HTML tags.txt→ Read as plain text.json→ Parse and extract relevant fields
If input looks like a URL (starts with http:// or https://):
- Use WebFetch tool to retrieve the page
- Extract main article content, title, and description
- Parse and clean the text
If input is a slug (no / and no protocol):
- Search codebase using Glob:
**/*${input}*.md - Common blog locations:
src/content/blog/posts/**/*${input}*.mdcontent/blog/*${input}*.mdposts/*${input}*.mdblog/*${input}*.md
- Use Read tool to parse found markdown file
Discover Blog Structure (if slug or file path): Explore the codebase to understand:
- 📁 Where are markdown files stored?
- 📋 What frontmatter format is used?
- 🖼️ Where are images/diagrams stored?
- 🎨 How are images referenced? (relative paths, absolute URLs, picture elements?)
- 🔗 What's the blog post URL structure?
For URLs: Extract and use the content as-is, skip blog structure discovery.
Phase 2: Create Conversion Script
Write a custom TypeScript conversion script that handles their specific structure.
Required Outputs (Universal Medium Best Practices):
1. Image Handling - Upload Markers (CRITICAL)
// Medium strips base64 and external URLs fail
// Solution: Add clear upload marker for FIRST image only
// IMPORTANT: Only include the FIRST image from the blog post
return `\n\n---\n\n**📊 [UPLOAD IMAGE HERE: ${altText}]**\n\n*File: \`${relPath}\`*\n\n---\n\n`;
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.
- 4d ago First seen · 467 lines · 8 tokens per session scan A 7dd162500024
medium is a command published in the GitHub repository kanaerulabs/growth-kit (15 stars, last pushed 7mo ago), licensed MIT. It adds 8 tokens to every session and 3,640 once invoked, about $0.0000 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.
Other commands, from other repositories
learn
Force claude-smart to extract learnings from this session now.
init
Install the formatters this repository needs, with every command visible before it runs.
brand-generate
Generate an on-brand document from a saved Brand Profile.
genshijin-compress
Markdown・テキストファイルを原始人形式へ安全圧縮.
save
Save this conversation as a new or existing reusable context.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.