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.
git clone --depth 1 https://github.com/animalzinc/claude-pluginsWrote 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/plugins/animalzinc/claude-plugins/blog-style-guide-creator)<a href="https://agentmods.dev/plugins/animalzinc/claude-plugins/blog-style-guide-creator"><img src="https://agentmods.dev/badge/plugins/animalzinc/claude-plugins/blog-style-guide-creator/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.
<a href="https://agentmods.dev/plugins/animalzinc/claude-plugins/blog-style-guide-creator"><img src="https://agentmods.dev/badge/plugins/animalzinc/claude-plugins/blog-style-guide-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
blog-style-guide-creator 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 yesterday.
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.
What it actually says
{
"name": "blog-style-guide-creator",
"displayName": "Blog Style Guide Creator",
"version": "2.0.1",
"description": "Builds a brand's editorial style guide from its published articles, an existing brand kit or style document, or its editors' edits, then checks drafts against it with parallel reviewers whose every finding is verified. Includes proofreading and an optional fact-check.",
"author": {
"name": "Tim Metz @ Animalz",
"email": "[email protected]",
"url": "https://animalz.co"
},
"homepage": "https://github.com/animalzinc/claude-plugins/tree/main/plugins/blog-style-guide-creator",
"repository": "https://github.com/animalzinc/claude-plugins",
"license": "MIT",
"keywords": ["style-guide", "editorial", "content-marketing", "proofreading", "fact-check", "brand-voice", "blog"],
"userConfig": {
"guides_dir": {
"type": "directory",
"title": "Brand guides folder",
"description": "Folder that holds one subfolder per brand (brand/style-guide.md). Leave empty to use a brands folder in the current project."
},
"deep_model": {
"type": "string",
"title": "Model for building guides",
"description": "Model alias for building and auditing guides: opus or fable.",
"default": "opus"
}
}
}
What it installs
The manifest is a name and a version. 4 skills, 2 commands, 11 agents travel with it, and installing the plugin installs all of them — 953 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill style-check A 131 tokens
- Skill build-style-guide A 92 tokens
- Skill validate-style-guide A 74 tokens
- Skill batch-review A 65 tokens
- Command generate-style-guide A 18 tokens
- Command update-style-guide A 18 tokens
- Agent guide-builder A 46 tokens
- Agent fact-checker A 56 tokens
- Agent proofreader A 59 tokens
- Agent source-reader A 41 tokens
- Agent structure-checker A 60 tokens
- Agent usage-checker A 48 tokens
- Agent voice-checker A 47 tokens
- Agent edit-miner A 41 tokens
- Agent guide-auditor A 53 tokens
- Agent finding-verifier A 46 tokens
- Agent mechanical-confirmer A 58 tokens
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.
- yesterday Changed 5f86643433ca
- 2d ago Changed · +18 lines 348293833135
- 2mo ago First seen · 11 lines scan A d921a0b9f192
blog-style-guide-creator is a plugin published in the GitHub repository animalzinc/claude-plugins (15 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
blog-style-guide-creator compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| blog-style-guide-creatoranimalzinc/claude-plugins | Plugin | 15 | 2d ago | MIT | A | — | Claude Code |
| contentforgeteachskillofskills-ai/ContentForge-techshu | Plugin | 1 | 2mo ago | MIT | A | — | Claude Code |
| bevy-pluginlaurigates/claude-plugins | Plugin | 60 | yesterday | MIT | A | — | Claude Code |
| desktop-notificationmelodic-software/claude-code-plugins | Plugin | 30 | today | MIT | A | — | Claude Code |
| disk-hygienemelodic-software/claude-code-plugins | Plugin | 30 | today | MIT | A | — | Claude Code |
| explainer-videomelodic-software/claude-code-plugins | Plugin | 30 | today | MIT | A | — | Claude Code |
| firecrawlmelodic-software/claude-code-plugins | Plugin | 30 | today | MIT | A | — | Claude Code |