A setup command that installs the Harness-Bujang multi-agent system into the current project. It can also configure language, tool adapters, and model presets.

Initializing the harness in a project, choosing English or Korean agent instructions, adding adapters for coding tools, and checking the installed setup.

It removes the manual work of copying agents, updating project instructions, creating a learning log, and configuring tool integrations.

bujang-init — Command for Claude Code by bjcho4141

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.

Clone the repo

git clone --depth 1 https://github.com/bjcho4141/harness-bujang

Made for: Claude Code.

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/bjcho4141/harness-bujang/bujang-init/github.svg)](https://agentmods.dev/commands/bjcho4141/harness-bujang/bujang-init)

Your own site

<a href="https://agentmods.dev/commands/bjcho4141/harness-bujang/bujang-init"><img src="https://agentmods.dev/badge/commands/bjcho4141/harness-bujang/bujang-init/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/bjcho4141/harness-bujang/bujang-init"><img src="https://agentmods.dev/badge/commands/bjcho4141/harness-bujang/bujang-init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 417 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00035	$0.00417
Opus 5	$0.00017	$0.00209
Sonnet 5	$0.00007	$0.00083
Haiku 4.5	$0.00003	$0.00042

Measured 10d ago against content hash 79ef20522fc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

bujang-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 10d 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.

packages/plugin/commands/bujang-init.md · 38 lines

What it actually says

/bujang-init

You are about to install the Harness-Bujang harness into the current project.

Action — run the CLI

The published harness-bujang package on npm handles all the install logic (project detection, agent copy, CLAUDE.md merge, learning log seed, extra-tool adapters). Run it via the user's shell:

npx harness-bujang@latest init

The CLI is interactive when stdin is a TTY: it prompts for:

Agent language (en / ko)
Extra tool adapters (Cursor / Cline / Aider / Codex / Gemini — multi-select)
Per-tool model preset (balanced / keep / cost / quality / custom)

For non-interactive runs (CI / scripts), pass --yes:

npx harness-bujang@latest init --yes --lang=ko

After install

Restart Claude Code — fully quit and reopen in this folder. Agents register only at session start, so the new director + teams won't be visible until you restart.
Open the chat room — run /open-chat to launch the standalone viewer at http://localhost:7777 (server backgrounds, browser auto-opens).
Optional: run /bujang-status to verify everything landed correctly, and open CLAUDE.md to review the ## 하네스 엔지니어링 (or ## Harness Engineering) section that was appended.

Idempotence

Re-running /bujang-init is safe — the CLI skips files that already exist unless --yes is passed. Use --yes to overwrite all agent files with the latest versions (e.g., after harness-bujang is upgraded).

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.

10d ago First seen · 38 lines · 35 tokens per session scan A 79ef20522fc2

Subscribe to this mod's changes

bujang-init is a command published in the GitHub repository bjcho4141/harness-bujang (7 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 417 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.

Building agents

bujang-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

/bujang-init

Action — run the CLI

After install

Idempotence

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement