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/animalzinc/claude-plugins/update-style-guidegit 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/commands/animalzinc/claude-plugins/update-style-guide)<a href="https://agentmods.dev/commands/animalzinc/claude-plugins/update-style-guide"><img src="https://agentmods.dev/badge/commands/animalzinc/claude-plugins/update-style-guide.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 5.1 | $0.00009 | $0.01174 |
| Opus 5 | $0.00005 | $0.00587 |
| Sonnet 5 | $0.00002 | $0.00235 |
| Haiku 4.5 | $0.00001 | $0.00117 |
Grade A, and why
update-style-guide 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 6d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Style Guide
Incrementally update the $1 style guide with patterns from new articles at $2.
Step 1: Validate Existing Style Guide
Before proceeding:
- Verify style guide exists at
brands/$1/style-guide.md- If missing: Error and suggest running
/generate-style-guide $1 [source]
- If missing: Error and suggest running
- Read and parse existing style guide
- Extract current rules, preferences, and exceptions from all 8 sections
- Note current version number (e.g., "1.0", "1.1")
Step 2: Collect New Articles
- Read all markdown files from $2
- Verify at least 3 new articles provided
- If fewer than 3: Warn that updates may be less reliable
- Check articles aren't already in
brands/$1/source-articles/(avoid duplicates) - If duplicates found: Warn user and exclude duplicates from analysis
Step 3: Analyze New Patterns
Launch style guide generator agent (Opus model) with:
- Existing style guide content
- New article contents
- Special instruction: "Compare new articles against existing rules. Identify:
- NEW patterns not covered by existing rules
- Patterns that CONTRADICT existing rules
- Patterns that CONFIRM existing rules (strengthen confidence)"
The agent should categorize findings:
- New Rules: Patterns appearing in 95%+ of new articles that aren't in current guide
- Rule Modifications: Existing rules that new articles consistently contradict
- Confirmed Rules: Existing rules that new articles follow (no action needed)
- Edge Cases: Unusual patterns that may warrant adding exceptions
Step 4: Generate Update Report
Create report showing proposed changes:
# Style Guide Update Report: $1
**Current Version:** [X.X]
**Proposed Version:** [X.Y]
**New Articles Analyzed:** [number]
**Date:** [current date]
---
## Proposed Changes
### New Rules to Add
**Section [X] - [Section Name]:**
- **New Rule:** [description]
- **Evidence:** Found in [X]/[Y] new articles
- **Example:** [example from articles]
### Rules to Modify
**Section [X] - [Section Name]:**
- **Current Rule:** [existing text]
- **Proposed Change:** [new text]
- **Reason:** New articles show [pattern] in [X]/[Y] cases
### Rules Confirmed (No Changes)
- Section 1: [X] rules confirmed
- Section 2: [X] rules confirmed
- ...
### Potential Exceptions to Add
- **Rule:** [existing rule]
- **Exception:** [new exception based on articles]
- **Example:** [example showing valid exception]
---
## Summary
- New rules to add: [X]
- Rules to modify: [X]
- Rules confirmed: [X]
- Exceptions to add: [X]
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.
- 6d ago First seen · 162 lines · 0 tokens per session scan A af12542fa339
update-style-guide is a command published in the GitHub repository animalzinc/claude-plugins (15 stars, last pushed 16d ago), licensed MIT. It adds 9 tokens to every session and 1,174 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
output-folder
Print the absolute path to the user-visible ContentForge output folder and open it in the OS file manager.
audit-content
Audit your content library for freshness decay, coverage gaps, and optimization opportunities.
content-brief
Generate a research-backed content brief with keyword data, competitor analysis, search intent, and SEO strategy.
publish
Publish finished content to Webflow or WordPress with preview, verification, and HTML export fallback.
social-adapt
Repurpose articles into platform-specific social media posts for LinkedIn, Twitter/X, Instagram, Facebook, Threads, TikTok, Bluesky, and YouTube Shorts.
translate
Translate content into 15 languages while preserving brand voice, citations, and SEO optimization.