steering-custom

steering-custom is a command for Claude Code from kaze-jp/kusa. It costs 0 tokens per session (461 once invoked), scanned A, original, MIT.

A command for creating a custom steering document: a project file that records rules for a specific concern such as accessibility, performance, or API versioning. It asks for the concern, its rules, and the development phases it should guide.

In plain words
What is it for?
Use it to add a named document under the project's steering directory with its purpose, scope, rules, examples, and references.
Why use it?
It captures project-specific decisions that general instructions do not cover, so later work can follow the same expectations.

Command for Claude Code

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/kaze-jp/kusa/steering-custom
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-custom

README.md
[![agentmods](https://agentmods.dev/badge/commands/kaze-jp/kusa/steering-custom.svg)](https://agentmods.dev/commands/kaze-jp/kusa/steering-custom)
Your own site
<a href="https://agentmods.dev/commands/kaze-jp/kusa/steering-custom"><img src="https://agentmods.dev/badge/commands/kaze-jp/kusa/steering-custom.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 461 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 $0.00000 $0.00461
Opus 5 $0.00000 $0.00230
Sonnet 5 $0.00000 $0.00092
Haiku 4.5 $0.00000 $0.00046

Measured 4d ago against content hash 58bbcce048fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

steering-custom 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.

.claude/commands/kiro/steering-custom.md · 75 lines

What it actually says

Add Custom Steering Document

Create a custom steering document for specific project concerns that the core documents do not cover.

Usage

/kiro:steering-custom <document-name>

Instructions

  1. Validate the document name: Must be kebab-case (e.g., performance-budgets, accessibility, api-versioning).

  2. Check for conflicts: Ensure no existing document at .ao/steering/<document-name>.md.

  3. Ask the user for the document's purpose and content:

    • What concern does this document address?
    • What rules or constraints should it define?
    • Which spec phases should reference it? (requirements, design, tasks, implementation)
  4. Generate the steering document with this structure:

# <Document Title>

## Purpose
<Why this steering document exists>

## Scope
<Which phases and commands should reference this document>

## Rules

### <Rule Category>
- <Rule 1>
- <Rule 2>

### <Rule Category>
- <Rule 1>

## Examples

### Correct
<Example of following these rules>

### Incorrect
<Example of violating these rules>

## References
<Links to standards, specs, or documentation>
  1. Save the document to .ao/steering/<document-name>.md.

  2. Confirm the document was created and explain how it will be picked up by spec commands.

Common Custom Documents

  • performance-budgets: Page load times, bundle sizes, API response times
  • accessibility: WCAG level, screen reader support, keyboard navigation
  • api-versioning: Versioning strategy, deprecation policy
  • data-privacy: PII handling, retention policies, GDPR compliance
  • internationalization: Supported locales, translation workflow
  • error-codes: Standardized error code format and registry

Output

  • .ao/steering/<document-name>.md

Notes

  • Custom steering documents are automatically discovered by spec commands that read from .ao/steering/.
  • Use /kiro:steering to view all documents including custom ones.
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 · 75 lines · 0 tokens per session scan A 58bbcce048fe

Subscribe to this mod's changes

steering-custom 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 461 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.