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/stagegit 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 | $0.00938 |
| Opus 5 | $0.00000 | $0.00469 |
| Sonnet 5 | $0.00000 | $0.00188 |
| Haiku 4.5 | $0.00000 | $0.00094 |
Grade A, and why
stage 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 2d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/stage — Universal Staging Builder
The /stage command builds staging HTML previews for EVC content. It supports three modes: blog articles, weekly social content, and individual visual assets.
Usage
/stage blog [slug]— build staging HTML for a blog article/stage week [week-number]— build staging dashboard for a week's social content/stage asset [name]— build staging preview for a single visual asset
Steps
1. Parse argument
Read the first argument to determine mode: blog, week, or asset. The second argument is the target identifier (slug, week number, or asset name).
If no arguments provided, print usage help and exit.
2. Load staging base CSS
Read _templates/staging/staging-base.css. This is the shared stylesheet used across every staging page. Either link it relatively from the output HTML or inline it into a <style> block — whichever keeps the staging page self-contained and offline-capable.
3. Build the staging HTML per mode
Blog mode — builds staging/blog/[slug]-blog.html
- Read copy from
content-engine/output/blog/[slug]/copy.html - Read metadata from
content-engine/output/blog/[slug]/metadata.json - Find all exported assets in
content-engine/output/blog/[slug]/exports/*.png - Build a full-article staging page with:
- Staging nav bar at the top (link back to
staging/index.html) - Article header: title, excerpt, meta row (date, author, category, slug)
- Article body wrapped in
<div class="article-preview">— use the.article-previewclass fromstaging-base.css - Rewrite every
<img src="exports/...">inside the copy so the relative path points at the actual export directory (e.g.../../content-engine/output/blog/[slug]/exports/foo.png) - Staging footer noting: "Review before publish. Run
/blog-publishwhen approved."
- Staging nav bar at the top (link back to
- Embed
staging-base.cssvia<link rel="stylesheet" href="../staging-base.css">(copy the CSS intostaging/staging-base.cssif not already there) or inline it directly
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.
- 2d ago First seen · 82 lines · 0 tokens per session scan A 446051600bd3
stage 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 938 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.
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.
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.