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/blog-plangit clone --depth 1 https://github.com/SaigonXIII/evcWrote 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-plan)<a href="https://agentmods.dev/commands/saigonxiii/evc/blog-plan"><img src="https://agentmods.dev/badge/commands/saigonxiii/evc/blog-plan.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 | $0.00000 | $0.01056 |
| Opus 5 | $0.00000 | $0.00528 |
| Sonnet 5 | $0.00000 | $0.00211 |
| Haiku 4.5 | $0.00000 | $0.00106 |
Grade A, and why
blog-plan 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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blog Plan
Research canon sources for a blog topic, build a structured outline with visual placeholders, and draft CMS metadata. This is the first step in the blog production pipeline.
Trigger
User invokes /blog-plan [topic] or says "plan the blog post about X", "outline the X article", "start the X blog"
Examples:
/blog-plan five-ways-to-write-a-better-headline/blog-plan "why your pricing page converts worse than your homepage"/blog-plan product-launch-playbook
Arguments
- Required: topic name or slug (matches an Academy article or freeform topic)
- Optional:
--sources [paths]to override default canon research
Steps
1. Load Academy Context
Read the Academy plan to understand where this article sits in the narrative arc:
cat {{PLANS_DIR}}/academy-plan.md
Identify:
- Which act (Why / What / How) this article belongs to
- What articles come before and after (what the reader already knows)
- What this article's specific job is in the overall story
2. Research Canon Sources
Read 3-5 canon sources relevant to this topic. Priority order:
| Source Type | Path Pattern |
|---|---|
| Product specs | {{CANON_DIR}}/docs/ |
| Business canon | {{CANON_DIR}}/BUSINESS_CANON.md |
| GitBook data | Check memory: reference_gitbook_product_data.md |
| SDK docs | {{CANON_DIR}}/codebase/sdk/README.md |
| Existing drafts | {{BRAND_DIR}}/Templates/content/*.html |
| USP pillars | {{CONFIG_DIR}}/canon-rules.json -> usps[] |
For each source:
- Extract relevant quotes with exact file paths
- Note any claims that need verification
- Flag single-source claims as "unverified"
3. Build Outline
Produce a structured markdown outline:
# [Article Title]
**Slug:** [kebab-case]
**Act:** [I: Why / II: What / III: How]
**Position:** Article [N] of 8
**Word target:** [1,200-2,000]
**Audience:** [primary] + [secondary]
## Narrative Setup
[1-2 sentences: what the reader knows from previous articles, what this one adds]
## Section Outline
### S1: [Section Title] (~[word count] words)
[Brief description of what this section covers]
Canon source: [file path + quote]
### S2: [Section Title] (~[word count] words)
[Brief description]
Canon source: [file path + quote]
[VISUAL: description of what the image should show]
### S3-S6: [repeat pattern]
## Visual Map
| Asset | Type | Theme | Description |
|-------|------|-------|-------------|
| cover | Cover image | Dark | [description] |
| [name] | [table/flow/comparison/timeline/tiers] | Light | [description] |
| cta | CTA card | Dark green | [standard CTA] |
## CMS Metadata Draft
- **Title:** [under 70 chars]
- **Excerpt:** [under 160 chars]
- **Date:** [target publish date]
- **Author:** {{COMPANY_NAME}}
- **Category:** Academy
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.
- 5d ago First seen · 139 lines · 0 tokens per session scan A 64fc88fb400f
blog-plan 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 1,056 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.