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/contentgit 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 | $0.01261 |
| Opus 5 | $0.00000 | $0.00630 |
| Sonnet 5 | $0.00000 | $0.00252 |
| Haiku 4.5 | $0.00000 | $0.00126 |
Grade A, and why
content 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Produce
Produce content for a specific day from the weekly plan. Runs the full pipeline: canon research -> copy -> visual -> brand compliance -> review.
Trigger
User invokes /content [day] or /content [day] [pillar] or asks to "create today's post", "produce Monday's content", "build the Tuesday post"
Examples:
/content monday/content wednesday product/content friday community
Arguments
- Required: day of week
- Optional: pillar override (defaults to the scheduled pillar from config)
Steps
1. Load Context
Read the weekly brief: find the most recent *-brief.md in content-engine/calendar/
- Extract this day's plan: audience segment, headline concept, visual direction, canon source, narrative thread
- If no brief exists, read config for the default pillar and audience mapping
Read supporting context:
content-engine/config.md— rules, banned phrases, posting schedulecontent-engine/memory/audience-segments.md— tone and style for target audiencecontent-engine/memory/learning-log.md— what's worked beforecontent-engine/memory/visual-log.md— visual best practices
2. Canon Research
Read the canon source specified in the brief:
- GTM deck, products copy, one-pager, community plan (paths in config.md)
- Extract relevant quotes and messaging for this day's topic
- Ensure every claim traces to a canon document
3. Draft Copy
X Post:
- Draft copy within 280 characters
- Follow the audience segment's tone and style
- Include the narrative thread (how this connects to yesterday's and tomorrow's posts)
- No emojis unless requested
- Link in reply, not main post
LinkedIn Post (if specified in brief):
- 800-1300 characters
- Professional tone, first 2 lines are the hook
- Tag relevant people/companies if appropriate
For both, include:
- Audience justification
- Key message
- Tone of voice
4. Create Visual Asset
Based on the visual direction from the brief:
If static banner:
- Select template from
brand/templates/social/templates/ - Create or modify the HTML template with this post's content
- Export using:
node brand/templates/social/export.js --template [name] --platform x
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 · 144 lines · 0 tokens per session scan A f197b99b06f4
content 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 1,261 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.