Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/SaigonXIII/evcnpx agentmods add commands/saigonxiii/evc/blog-publishWrote 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/saigonxiii/evc/blog-publish)<a href="https://agentmods.dev/commands/saigonxiii/evc/blog-publish"><img src="https://agentmods.dev/badge/commands/saigonxiii/evc/blog-publish.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 | $0.00000 | $0.01290 |
| Opus 5 | $0.00000 | $0.00645 |
| Sonnet 5 | $0.00000 | $0.00258 |
| Haiku 4.5 | $0.00000 | $0.00129 |
Grade A, and why
blog-publish 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 8d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blog Publish
Push a completed blog article to the CMS -- upload images, create CMS item, sync components. Final step in the blog production pipeline.
Trigger
User invokes /blog-publish [slug] or says "publish the blog", "push to CMS", "upload the article"
Examples:
/blog-publish how-we-built-our-first-feature/blog-publish product-launch-announcement
Prerequisites
- Copy:
{{CONTENT_OUTPUT_DIR}}/blog/[slug]/copy.html - Metadata:
{{CONTENT_OUTPUT_DIR}}/blog/[slug]/metadata.json - Exports:
{{CONTENT_OUTPUT_DIR}}/blog/[slug]/exports/*.png - QA report should show READY status
If any are missing, report which and stop.
CMS Configuration
- Collection ID:
{{CMS_COLLECTION_ID}} - Field IDs (map to your CMS schema):
- Title:
{{CMS_FIELD_TITLE}} - Content:
{{CMS_FIELD_CONTENT}} - Cover:
{{CMS_FIELD_COVER}} - Date:
{{CMS_FIELD_DATE}} - Author:
{{CMS_FIELD_AUTHOR}} - Excerpt:
{{CMS_FIELD_EXCERPT}} - Category:
{{CMS_FIELD_CATEGORY}}
- Title:
Steps
0. Staging Preview Gate
Before any publish work, confirm the staging HTML exists at staging/blog/[slug]-blog.html.
If the file does not exist, prompt and exit without publishing:
Staging HTML not found at staging/blog/[slug]-blog.html. Run /blog-assets [slug] first to build the staging page, then review it in your browser before publishing.
If the file exists, ask:
Have you reviewed the staging page at staging/blog/[slug]-blog.html? (yes/no)
Only proceed to Step 1 if the user answers yes. Otherwise, stop.
0b. Clean Export (strip internal drawer)
Before uploading the staging HTML content to the CMS, produce a clean export with the internal version drawer stripped:
mkdir -p staging/exports
bash scripts/export-staging.sh \
staging/blog/[slug]-blog.html \
staging/exports/[slug]-blog.html
Use staging/exports/[slug]-blog.html as the source for CMS upload — NEVER upload the staging file directly (it contains the internal review drawer). The clean export has all data-internal elements removed.
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.
- 8d ago First seen · 163 lines · 0 tokens per session scan A cc19c1038530
blog-publish 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 1,290 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.