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/saigonxiii/evc/blog-draftgit clone --depth 1 https://github.com/SaigonXIII/evcWhat 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 | $0.00000 | $0.01119 |
| Opus 5 | $0.00000 | $0.00560 |
| Sonnet 5 | $0.00000 | $0.00224 |
| Haiku 4.5 | $0.00000 | $0.00112 |
Grade A, and why
blog-draft 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 3d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blog Draft
Write a 1,200-2,000 word blog article as plain semantic HTML from an approved outline. Second step in the blog production pipeline.
Trigger
User invokes /blog-draft [slug] or says "draft the X article", "write the X blog", "turn the outline into copy"
Examples:
/blog-draft five-ways-to-write-a-better-headline/blog-draft product-launch-playbook
Prerequisites
- An approved outline must exist at
{{CONTENT_OUTPUT_DIR}}/blog/[slug]/outline.md - If no outline exists, prompt: "No outline found. Run
/blog-plan [topic]first."
Steps
1. Load Outline + Context
Read the approved outline:
{{CONTENT_OUTPUT_DIR}}/blog/[slug]/outline.md
Also load:
- Canon sources referenced in the outline
{{CONFIG_DIR}}/canon-rules.json-- banned phrases, USPs, required language- Previous articles in the series (for narrative continuity)
2. Write Semantic HTML
Produce clean HTML copy following the CMS blog template pattern:
<!-- CMS Metadata
Title: [title]
Excerpt: [excerpt]
Date: [YYYY-MM-DD]
Author: {{COMPANY_NAME}}
Category: Academy
Slug: [slug]
-->
<h2><span class="sec-num">01</span> [Section Title]</h2>
<p>[Body paragraph. Keep paragraphs to 2-4 sentences max.]</p>
<p>[Next paragraph.]</p>
<h2><span class="sec-num">02</span> [Section Title]</h2>
<p>[Body text.]</p>
<p><strong>[Key term or callout phrase]</strong> -- [explanation].</p>
<img class="blog-asset" src="exports/[slug]-[asset-name].png" alt="[descriptive alt text]" />
<blockquote>[Pull quote or key insight]</blockquote>
<h2><span class="sec-num">03</span> [Section Title]</h2>
<!-- repeat pattern -->
3. Writing Rules
Structure:
- 5-7 H2 sections with
<span class="sec-num">numbering - No H1 (CMS provides the title)
- No H3 unless absolutely necessary for nested content
- No inline CSS -- CMS handles all styling
Copy quality:
- Write to pass
/stop-slop(.claude/commands/stop-slop.md) — the canonical anti-AI-pattern criteria - Vary paragraph length (1-4 sentences)
- Lead with the point, not the context
- Every claim traces to a canon source from the outline
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.
- 3d ago First seen · 149 lines · 0 tokens per session scan A 9fc06fbcdaca
blog-draft is a command published in the GitHub repository SaigonXIII/evc (56 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,119 tokens. 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
review-tool
Research a tool or product for skill-gap, architecture, and verb-fit per the Anatomy framework.
setup
First-run setup — replace the fictional company and authors with yours.
review-content
Review content for brand alignment, lead placement, bio consistency, and proof points.
voice-check
Check a draft against the author's voice profile and flag deviations.
content-status
Scan all content directories and report status of drafts, ideas, and published content.
draft-blog
Scaffold a blog post with proper structure, voice, and frontmatter.