start

A first-time setup wizard for EVC, a system that supports several industry-specific workflows. It checks whether setup exists, collects required settings, and runs a demonstration command.

In plain words
What is it for?
Use it to choose a Web3, B2B SaaS, e-commerce, or generic setup, provide the required variables, complete configuration, and verify the result with a demo.
Why use it?
It guides a new user through configuration instead of requiring them to find starter files and environment settings themselves.

Command

Install

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.

agentmods
npx agentmods add commands/saigonxiii/evc/start
Clone the repo
git clone --depth 1 https://github.com/SaigonXIII/evc
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 966 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash b7599a2d302d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

_templates/commands/start.md · 129 lines

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:

  1. COMPANY_NAME — company name (e.g., "Acme Corp")
  2. WEBSITE_URL — website (e.g., "acme.com" — no https://)
  3. SOCIAL_HANDLE_X — X/Twitter handle (e.g., "@acmecorp")
  4. ANCHOR_STATEMENT — one sentence: what the company does (e.g., "Acme helps developers ship faster by automating deploys")
  5. 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.

Read the full file on GitHub · 129 lines

Changes

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.

  1. 2d ago First seen · 129 lines · 0 tokens per session scan A b7599a2d302d

Subscribe to this mod's changes

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.