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/setup-canongit 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 | $0.01205 |
| Opus 5 | $0.00000 | $0.00602 |
| Sonnet 5 | $0.00000 | $0.00241 |
| Haiku 4.5 | $0.00000 | $0.00120 |
Grade A, and why
setup-canon 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 3d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup Canon
Interactive brand rules builder. Asks questions to construct brand/canon-rules.json — the guardrail file that all content commands reference.
Trigger
User invokes /setup-canon or says "set up brand rules", "configure canon", "build brand guardrails"
Steps
1. Check for existing rules
if [ -f "{{BRAND_DIR}}/canon-rules.json" ]; then
echo "RULES_EXIST"
else
echo "NO_RULES"
fi
If rules exist: Read and present them. Ask "Want to update these or start fresh?" If no rules: Start from scratch.
2. Interactive interview
Run this as an adaptive interview, not a script: the 8 sections below define WHAT to collect — group related questions, follow up where an answer is thin, and skip what the user's earlier answers already covered. "skip" is always a valid answer.
Let's build your brand guardrails. These rules will be checked
automatically whenever content is produced or reviewed.
There are 8 areas to cover. Answer as thoroughly as you like.
Type "skip" to leave a section empty for now.
Question 1: Banned phrases
What phrases should NEVER appear in your content?
(e.g., industry jargon to avoid, competitor names, outdated terms, legal risks)
Examples: "guaranteed returns", "risk-free", "the best in the market"
>
Question 2: Required language
How do you ALWAYS describe your product? What phrases are mandatory?
(e.g., "AI-native platform" not "AI tool", "infrastructure" not "app")
Provide your preferred phrasings:
>
Question 3: Value propositions
What are your 3-5 key value propositions (USPs)?
These will be the only approved USPs for content — no inventing new ones.
List them:
>
Question 4: Current partners/customers
Who are your current customers or partners that can be mentioned publicly?
(Only list those approved for external mention.)
>
Question 5: Competitors and defunct brands
Any competitors or defunct brands to AVOID mentioning?
(We will never reference these in content.)
>
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.
- 3d ago First seen · 214 lines · 0 tokens per session scan A fb7eb4f7a15e
setup-canon 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 1,205 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.