blog-qa

blog-qa is a command for coding agents from SaigonXIII/evc. It costs 0 tokens per session (1,256 once invoked), scanned A, original, MIT.

A command that runs several quality checks on a blog draft and reports whether it is READY or NOT READY.

In plain words
What is it for?
Use it to check an article's copy, compliance with brand rules, writing quality, and readiness for the publishing step.
Why use it?
It catches rule violations, weak or unwanted writing patterns, unsupported claims, and blog-specific issues before publication.

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-qa
Clone the repo
git clone --depth 1 https://github.com/SaigonXIII/evc

Wrote 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.

agentmods badge for blog-qa

README.md
[![agentmods](https://agentmods.dev/badge/commands/saigonxiii/evc/blog-qa.svg)](https://agentmods.dev/commands/saigonxiii/evc/blog-qa)
Your own site
<a href="https://agentmods.dev/commands/saigonxiii/evc/blog-qa"><img src="https://agentmods.dev/badge/commands/saigonxiii/evc/blog-qa.svg" alt="Measured on agentmods" height="20"></a>
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 1,256 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 $0.01256
Opus 5 $0.00000 $0.00628
Sonnet 5 $0.00000 $0.00251
Haiku 4.5 $0.00000 $0.00126

Measured 5d ago against content hash ae067c9b2904, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

blog-qa 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 5d 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-qa.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Blog QA

Run the full quality pipeline on a blog draft. Chains /content-qa + /stop-slop + blog-specific checks. Returns READY or NOT READY. Third step in the blog production pipeline.

Trigger

User invokes /blog-qa [slug] or says "QA the blog", "check the article", "is the blog ready"

Examples:

  • /blog-qa five-ways-to-write-a-better-headline
  • /blog-qa product-launch-playbook

Prerequisites

  • Draft must exist at {{CONTENT_OUTPUT_DIR}}/blog/[slug]/copy.html
  • If no draft exists, prompt: "No draft found. Run /blog-draft [slug] first."

Pipeline

Run all 8 checks in order. Each returns PASS, WARN, or FAIL.

Check 1: Canon Compliance

Load {{CONFIG_DIR}}/canon-rules.json. Scan the full copy against:

  • banned_phrases[] -- each match is FAIL
  • framing_red_flags[] -- each match is WARN
  • usps[] -- claims not traceable to a USP are WARN
  • required_language -- verify correct usage
  • live_partners[] vs defunct_partners[] -- wrong partner reference is FAIL

Check 2: Stop Slop

Apply the stop-slop criteria — the canonical pattern list lives in /stop-slop (.claude/commands/stop-slop.md); do not maintain a separate list here.

Severity mapping for blog QA: filler phrases -> FAIL; all other stop-slop patterns -> WARN.

Check 3: Word Count + Structure

Metric Target Check
Total words 1,200-2,000 FAIL if outside range
H2 sections 5-7 WARN if outside range
Avg paragraph length 2-4 sentences WARN if avg > 4
Longest paragraph Max 5 sentences WARN if exceeded
H1 tags 0 FAIL if any present
Inline CSS 0 FAIL if any present

Check 4: Canon Traceability

For every factual claim (numbers, percentages, partner names, fee amounts, product descriptions):

  • Can it be traced to a specific canon document?
  • If single-source only -> WARN ("unverified -- single source")
  • If no source -> FAIL ("unsourced claim")

Check 5: Image Placeholders

  • At least 2 <img class="blog-asset"> tags present (cover + CTA minimum) -> FAIL if fewer
  • Every <img> has descriptive alt text (not "image" or empty) -> WARN if missing
  • Image src paths follow exports/[slug]-[name].png pattern -> WARN if malformed

Read the full file on GitHub · 136 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. 5d ago First seen · 136 lines · 0 tokens per session scan A ae067c9b2904

Subscribe to this mod's changes

blog-qa 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 1,256 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.