start

start is a command for Codex from KaelSensei/MagicAIBuilder. It costs 0 tokens per session (495 once invoked), scanned A, original, MIT.

A project-start command for MagicTheOfflining, an offline Android app for viewing Magic: The Gathering card decks. It reads the project’s documentation and rules, then identifies the current milestone and next task.

In plain words
What is it for?
Use it at the beginning of a coding session to load the project plan, architecture, progress notes, deployment instructions, and Cursor rules.
Why use it?
It removes the need to manually gather project context before beginning work and helps the agent start from the documented priorities.

Command for Codex

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/kaelsensei/magicaibuilder/start
Clone the repo
git clone --depth 1 https://github.com/KaelSensei/MagicAIBuilder

Made for: Codex.

Wrote 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.

agentmods badge for start

README.md
[![agentmods](https://agentmods.dev/badge/commands/kaelsensei/magicaibuilder/start.svg)](https://agentmods.dev/commands/kaelsensei/magicaibuilder/start)
Your own site
<a href="https://agentmods.dev/commands/kaelsensei/magicaibuilder/start"><img src="https://agentmods.dev/badge/commands/kaelsensei/magicaibuilder/start.svg" alt="Measured on agentmods" height="20"></a>
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 495 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 5.1 $0.00000 $0.00495
Opus 5 $0.00000 $0.00247
Sonnet 5 $0.00000 $0.00099
Haiku 4.5 $0.00000 $0.00049

Measured 5d ago against content hash 1ea01c05c91a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 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.

.agents/commands/start.md · 54 lines

What it actually says

Start Command - MagicTheOfflining Bootstrap

When /start is invoked, immediately execute these steps:

Step 1: Project Context

  1. Assume a single app: the root MagicTheOfflining/ directory
  2. Ignore any concept of "services" or ascend/apps/*
  3. Use the project-level rules in .cursor/rules/*.mdc

Step 2: Load Core Documentation

  1. Read and internalize these files (if they exist), in this order:
    • README.md
    • offline_commander_decks_mobile_app.md
    • docs/architecture/magic_the_offlining_architecture.md
    • docs/development/magic_the_offlining_step_by_step_dev_plan.md
    • PROGRESS.md
    • docs/deployment/PLAY_STORE_DEPLOYMENT.md
  2. Then load Cursor rules from .cursor/rules/*.mdc
  3. Set the working context to the project root

Step 3: Bootstrap Project Context

  1. From the docs above, infer:
    • The current milestone
    • The next concrete feature or fix
  2. Prefer:
    • Steps listed as next in docs/development/magic_the_offlining_step_by_step_dev_plan.md
    • Explicit TODO / next items in PROGRESS.md

Step 4: Summarize and Start Working

Without asking for confirmation:

  1. Summarize:
    • Overall goal: offline Commander deck viewer using Moxfield scraping, SQLite, and local image caching
    • Current milestone and any relevant constraints (Android‑first, offline‑first)
  2. List all documents that were loaded
  3. Choose the next concrete task based on the docs (feature, bugfix, refactor, or deployment work)
  4. Immediately start implementing that task, following:
    • The tech‑stack rules (React Native + TypeScript + SQLite)
    • The security rules (no backends, no unsafe network behavior, no dynamic code)
    • The version‑management rules (commit + push after each meaningful chunk of work)

Usage

Type /start when opening MagicTheOfflining in a new session. The AI will:

  1. Load the project docs and rules
  2. Understand what’s done and what’s next
  3. Pick the next task
  4. Begin implementing it right away
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. 5d ago First seen · 54 lines · 0 tokens per session scan A 1ea01c05c91a

Subscribe to this mod's changes

start is a command published in the GitHub repository KaelSensei/MagicAIBuilder (2 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 495 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 2026-08-31.

Related

Other commands, from other repositories