init

init is a command for coding agents from BitYoungjae/marketplace. It costs 49 tokens per session (1,840 once invoked), scanned A, original, MIT.

An interactive command for starting a self-learning project. It interviews you about the project and creates planning and context files, including a plan, tasks, learner persona, interview data, and project instructions.

In plain words
What is it for?
Setting up learning projects in technology, history, science, arts, or general subjects. It creates the files needed to plan and guide the project.
Why use it?
A learning project can lose direction when its audience, goals, and scope are not written down. The interview captures those decisions before the learning materials are built.

Command

Part of the dokhak plugin — 4 skills, 5 commands, 6 agents shipped together

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/bityoungjae/marketplace/init
Clone the repo
git clone --depth 1 https://github.com/BitYoungjae/marketplace

Or install dokhak, the plugin that ships this one along with the rest of its 4 skills, 5 commands, 6 agents.

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 init

README.md
[![agentmods](https://agentmods.dev/badge/commands/bityoungjae/marketplace/init.svg)](https://agentmods.dev/commands/bityoungjae/marketplace/init)
Your own site
<a href="https://agentmods.dev/commands/bityoungjae/marketplace/init"><img src="https://agentmods.dev/badge/commands/bityoungjae/marketplace/init.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,840 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 $0.00049 $0.01840
Opus 5 $0.00024 $0.00920
Sonnet 5 $0.00010 $0.00368
Haiku 4.5 $0.00005 $0.00184

Measured 4d ago against content hash 2ca531b476fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init 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 4d 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.

plugins/dokhak/commands/init.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Initialize Self-Learning Resource Project

Interactive interview-based project initialization for learning resources.


Phase 1: Project Interview

<communication_rules> CRITICAL: The interviewer agent communicates DIRECTLY with the user.

  • Do NOT add any introduction before launching the interviewer
  • Do NOT add transition messages like "Starting interview..." or "Let me start the interview"
  • Do NOT summarize or rephrase the agent's output after it completes
  • Let the conversation flow naturally as if the interviewer IS the main assistant
  • The user should feel they are talking to ONE entity, not being handed off to another

When the interview completes, silently proceed to Phase 2 without announcing completion. </communication_rules>

Launch Project Interviewer

Task(
  subagent_type="dokhak:project-interviewer",
  model="opus",
  description="Conduct project initialization interview",
  prompt="""
    <role>
    You are a learning experience designer having a direct conversation with the learner.
    You ARE the main assistant - not a separate tool or delegated agent.
    </role>

    <task>
    Conduct an interview for project initialization following the project-interview skill.
    </task>

    <instructions>
    1. Start immediately with your multilingual greeting - no preamble
    2. Have a natural conversation to understand the learner
    3. Generate persona.md and interview-data.md
    4. Return results in project_metadata XML format
    </instructions>

    <output_format>
    Use persona-template.md from project-scaffolder skill when creating persona.md.
    </output_format>
  """
)

Interview Goals

Through natural conversation, understand:

What to Learn How to Discover
Topic Open question: "What would you like to learn?"
Domain Infer from topic, confirm if ambiguous
Motivation Ask why they want to learn this
Level Ask about background and experience
Preferences Discuss desired style and volume
Environment For technology: ask about OS/tools

Read the full file on GitHub · 272 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. 4d ago First seen · 272 lines · 49 tokens per session scan A 2ca531b476fb

Subscribe to this mod's changes

init is a command published in the GitHub repository BitYoungjae/marketplace (6 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 1,840 once invoked, about $0.0002 per session on Opus 5. 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.