blog-draft

A command that turns an approved blog outline into a 1,200–2,000-word article in HTML, a format websites can display.

In plain words
What is it for?
Use it to draft blog posts from saved outlines, including headings, metadata, and copy ready for a content management system.
Why use it?
It removes the need to write and structure the article manually while keeping it aligned with your approved outline and content rules.

Command

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 commands/saigonxiii/evc/blog-draft
Clone the repo
git clone --depth 1 https://github.com/SaigonXIII/evc
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,119 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 $0.00000 $0.01119
Opus 5 $0.00000 $0.00560
Sonnet 5 $0.00000 $0.00224
Haiku 4.5 $0.00000 $0.00112

Measured 3d ago against content hash 9fc06fbcdaca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

_templates/commands/blog-draft.md · 149 lines

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

Read the full file on GitHub · 149 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. 3d ago First seen · 149 lines · 0 tokens per session scan A 9fc06fbcdaca

Subscribe to this mod's changes

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.