kusa: Command for Claude Code

.claude/commands/kiro/steering.md

steering is a command for Claude Code from kaze-jp/kusa. It costs 0 tokens per session (450 once invoked), scanned A, original, MIT.

A project-document manager for files that record the product vision, technology choices, and code structure. It can show these documents and edit a selected one.

In plain words
What is it for?
Use it to review project rules, summarize steering files, edit one of them, or create missing core documents from the codebase.
Why use it?
It gives the coding agent a shared description of how the project should be built and organized, while revealing missing guidance documents.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is kaze-jp/kusa's own configuration. It tells Claude Code how to work on kusa itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kusa configures →

View source ↗ kaze-jp/kusa
Reuse

Borrowing it

Nothing to install: this file belongs to kaze-jp/kusa. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kaze-jp/kusa/main/.claude/commands/kiro/steering.md
Clone the repo
git clone --depth 1 https://github.com/kaze-jp/kusa

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.

agentmods badge for steering

README.md
[![agentmods](https://agentmods.dev/badge/commands/kaze-jp/kusa/steering.svg)](https://agentmods.dev/commands/kaze-jp/kusa/steering)
Your own site
<a href="https://agentmods.dev/commands/kaze-jp/kusa/steering"><img src="https://agentmods.dev/badge/commands/kaze-jp/kusa/steering.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 450 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00450
Opus 5 $0.00000 $0.00225
Sonnet 5 $0.00000 $0.00090
Haiku 4.5 $0.00000 $0.00045

Measured 6d ago against content hash 503b70ce5630, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

steering 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 6d 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.

.claude/commands/kiro/steering.md · 69 lines

What it actually says

Manage Steering Documents

View and edit the project's steering documents that guide spec generation and implementation.

Usage

/kiro:steering [show|edit <document>]

Instructions

Show Mode (default)

  1. Read all steering documents from .ao/steering/:

    • product.md - Product vision, goals, target users
    • tech.md - Technology stack, patterns, conventions
    • structure.md - Project structure and file organization
  2. Display a summary of each document:

# Steering Documents

## Product (.ao/steering/product.md)
<First 5-10 lines or key points summary>
Status: Found | Missing

## Tech (.ao/steering/tech.md)
<First 5-10 lines or key points summary>
Status: Found | Missing

## Structure (.ao/steering/structure.md)
<First 5-10 lines or key points summary>
Status: Found | Missing

## Custom Documents
<List any additional .md files in .ao/steering/>
  1. If any core document is missing, offer to create it with sensible defaults derived from the codebase.

Edit Mode

  1. When the user specifies edit <document>, read the full content of that steering document.

  2. Present the current content and ask the user what they want to change.

  3. Apply the edits as requested by the user.

  4. Validate the edited document:

    • Ensure it still has required sections
    • Check for internal consistency
    • Warn if changes conflict with other steering documents
  5. Save the updated document and confirm the changes.

Output

  • Display of steering document status and content
  • Modified steering documents when editing

Notes

  • Steering documents are the source of truth for all spec commands.
  • Changes to steering documents do not retroactively update existing specs.
  • If .ao/steering/ does not exist, create it when the user wants to add a document.
  • Custom steering documents (added via /kiro:steering-custom) are also listed here.
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. 6d ago First seen · 69 lines · 0 tokens per session scan A 503b70ce5630

Subscribe to this mod's changes

steering is a command published in the GitHub repository kaze-jp/kusa (2 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 450 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.