A setup command for starting a John workspace, a structured project area for extracting knowledge from source materials. It creates working files such as a plan and project instructions, and can copy supplied input files.

Use it at the beginning of a new John project to initialize the workspace, optionally add input materials, and prepare the plan for defining the project's goals and workflow.

It establishes the folders and starter documents that the rest of the John workflow expects. This prevents later commands from starting without the required project state.

init — Command for coding agents by kitchen-engineer42: A setup command for starting a John workspace, a…

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/kitchen-engineer42/joharnessburg/init

Clone the repo

git clone --depth 1 https://github.com/kitchen-engineer42/joharnessburg

Or install john, the plugin that ships this one along with the rest of its 28 skills, 5 commands, 5 agents, 3 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/kitchen-engineer42/joharnessburg/init.svg)](https://agentmods.dev/commands/kitchen-engineer42/joharnessburg/init)

Your own site

<a href="https://agentmods.dev/commands/kitchen-engineer42/joharnessburg/init"><img src="https://agentmods.dev/badge/commands/kitchen-engineer42/joharnessburg/init.svg" alt="Measured on agentmods" height="20"></a>

Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 445 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.

Model	Per session	Once invoked
Fable 5	$0.00067	$0.00445
Opus 5	$0.00034	$0.00222
Sonnet 5	$0.00013	$0.00089
Haiku 4.5	$0.00007	$0.00044

Measured 3d ago against content hash 845b33d6c0c8, 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 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.

plugins/joharnessburg/commands/init.md · 25 lines

What it actually says

When this command fires, the user is starting a new John project (or re-bootstrapping one). Your job:

Parse the user's argument. The first positional argument (if any) is a path to a file or directory of input materials to copy into .john/input/. The --force flag (if present) recreates .john/ even if it exists.
Invoke the init script via Bash:
```
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/init_workspace.py" <user-args>
```
Pass the user's positional + --force (if present). If the user gave no input path, just run the script with no positional argument.
Parse the JSON status on stdout. On success: true, summarize for the user: project_root, .john/ created, PLAN.md written (or kept), CLAUDE.md written (or kept), files copied. On success: false, surface the human-readable error from stderr.
After a successful init, read the freshly-written PLAN.md and invite the user to start the start-of-project conversation per the plan-md-authoring skill — confirm project intent, decide the app-type definition (knowledge format, knowledge schema, app mechanism, build pipeline), sketch the first 2-3 phases.

Do NOT skip step 4. The init script only writes a skeleton; the actual project intent + app-type definition decisions are a conversation you owe the user.

If the user already has a PLAN.md or CLAUDE.md in the project, init preserves them by default (only --force recreates PLAN.md; CLAUDE.md is never overwritten). Tell the user when this happens so they know the existing files were kept.

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.

3d ago First seen · 25 lines · 67 tokens per session scan A 845b33d6c0c8

Subscribe to this mod's changes

init is a command published in the GitHub repository kitchen-engineer42/joharnessburg (9 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 445 once invoked, about $0.0003 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.

ai-agents anthropic claude claude-code claude-code-plugin knowledge-engineering

init

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

learn

init

brand-generate

genshijin-compress

save

standup