A setup command that adds Harness Kit's configuration, project rules, planning files, and pre-commit check to a repository.

Use it when starting Harness Kit in a Godot, web, or custom project.

It provides the files and settings needed to use the plugin while avoiding replacement of an existing configuration unless asked.

init — Command by whieet

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/whieet/harness-kit/init

Clone the repo

git clone --depth 1 https://github.com/whieet/harness-kit

Per session 96 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,327 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	$0.00096	$0.01327
Opus 5	$0.00048	$0.00664
Sonnet 5	$0.00019	$0.00265
Haiku 4.5	$0.00010	$0.00133

Measured yesterday against content hash 5da4f3239fb7, 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 yesterday.

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.

commands/init.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/harness-kit:init

Set up the harness in this repository. Be careful and idempotent — never clobber a user's existing .harness/config.json unless they explicitly ask to reset.

Steps

Ask for the project language first.
- If the user's message explicitly includes --lang en, --lang zh, English/en, or Chinese/中文/zh, use that explicit choice.
- Otherwise always ask language before any repo probing or project-type question with the AskUserQuestion tool: 中文 (zh) | English (en). Do not infer from the current conversation and do not proceed without a language choice.
- Once chosen, use that language for every subsequent explanation, question, and generated document in this init flow.
- This preference is persisted in .harness/config.json as language and can be changed later. It controls AI-facing guidance and generated document content; file/directory names, command names, and config keys stay untranslated.
Decide the project type using the selected language.
- If the user's message names a type (godot, web, or custom), use it.
- Otherwise probe the repo:
  - test -f project.godot → godot
  - test -f package.json and it depends on react/vue/vite/next/svelte (grep package.json) → web
- If exactly one matches, state the detected type in the selected language and proceed.
- If both or neither match, ask the user with the AskUserQuestion tool in the selected language: custom | godot | web. Do not silently guess.
Run the scaffolder (it does all file writes deterministically and idempotently):
```
harness-init <type> --lang <en|zh>
```
- Add --force only if the user explicitly asked to reset/overwrite an existing config.
- Add --no-claude-md if the user doesn't want a CLAUDE.md constitution.
- harness-init is on PATH (bundled in the plugin's bin/). If the shell can't find it, the plugin may not be enabled — tell the user to run /plugin install harness-kit.

Read the full file on GitHub · 56 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.

yesterday First seen · 56 lines · 96 tokens per session scan A 5da4f3239fb7

Subscribe to this mod's changes

init is a command published in the GitHub repository whieet/harness-kit (5 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 1,327 once invoked, about $0.0005 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.

Game development Git and workflow Writing and docs

init

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/harness-kit:init

Steps

What this file has done since we first saw it

Other commands, from other repositories

plan

speckit.taskstoissues

cert-check

combat-design

ui-flow-review

tech-debt