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/startgit 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 | $0.00966 |
| Opus 5 | $0.00000 | $0.00483 |
| Sonnet 5 | $0.00000 | $0.00193 |
| Haiku 4.5 | $0.00000 | $0.00097 |
Grade A, and why
start 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start — First-Time Onboarding Wizard
Walks a first-time user through EVC setup. Checks if the system is configured, offers industry starter, collects required vars, runs setup, and runs a demo command.
Trigger
User invokes /start or says "get started", "first time", "setup", "onboard me"
Steps
1. Check setup state
Check if config.env exists in the project root.
If it exists, skip to step 5 (already configured).
If it does not exist, this is a first-time run. Continue to step 2.
2. Ask industry
Present the four industry options and ask the user to pick one:
Which industry fits your company best?
1) Web3 / Crypto / DeFi (with compliance rules)
2) B2B SaaS (LinkedIn-heavy, case-study focus)
3) E-commerce / D2C (product launches, seasonal)
4) Generic (any other industry)
Wait for the user's response. Map the choice to a starter file:
- 1 →
starters/web3.env - 2 →
starters/saas.env - 3 →
starters/ecommerce.env - 4 →
starters/generic.env
Copy the selected starter to config.env:
cp starters/<chosen>.env config.env
3. Collect required variables
Ask the user for the 5 required variables in one exchange — present all five together and let them answer in a single reply. Follow up only on missing or invalid values.
Required:
- COMPANY_NAME — company name (e.g., "Acme Corp")
- WEBSITE_URL — website (e.g., "acme.com" — no https://)
- SOCIAL_HANDLE_X — X/Twitter handle (e.g., "@acmecorp")
- ANCHOR_STATEMENT — one sentence: what the company does (e.g., "Acme helps developers ship faster by automating deploys")
- BRAND_PRIMARY_COLOR — primary brand color (hex code, e.g., #2563eb)
After collecting the values, update config.env using the Edit tool to replace the placeholder lines.
4. Run setup.sh
Tell the user you're about to run the setup. Then execute:
./setup.sh
This will render all commands, wire hooks, install context modes, create brand/canon-rules.json with your company variables, and set file permissions.
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 · 129 lines · 0 tokens per session scan A b7599a2d302d
start 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 966 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.
gtm-jobs
Uncovers the customer's Jobs to Be Done (progress + circumstance, functional/social/emotional dimensions), the Forces of Progress, and the Big/Little Hire risk — the demand-side foundation that precedes positioning and offer.
gtm
Adaptive end-to-end GTM pipeline (classifies archetype/stage, positioning, offer, leads, content, channels, email, KPIs), with GTM Readiness Score and adversarial review. Produces gtm-plan.md. If you don't know where to start, use /gtm-buddy first.
gtm-copy
Writes ready-to-use copy (email, landing, or post) by applying the SUCKS framework to your input and industry.
gtm-email
Design an email automation workflow (goal+KPI, segment, trigger, delay, if/then, sequence) starting from the input.
gtm-instagram
Set up Meta/Instagram conversion campaigns with structure, audience, creative, and budget for your industry.