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.
npx agentmods add commands/kaze-jp/kusa/steering-customgit clone --depth 1 https://github.com/kaze-jp/kusaWrote 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.
[](https://agentmods.dev/commands/kaze-jp/kusa/steering-custom)<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>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 | $0.00000 | $0.00461 |
| Opus 5 | $0.00000 | $0.00230 |
| Sonnet 5 | $0.00000 | $0.00092 |
| Haiku 4.5 | $0.00000 | $0.00046 |
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.
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
-
Validate the document name: Must be kebab-case (e.g.,
performance-budgets,accessibility,api-versioning). -
Check for conflicts: Ensure no existing document at
.ao/steering/<document-name>.md. -
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)
-
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>
-
Save the document to
.ao/steering/<document-name>.md. -
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:steeringto view all documents including custom ones.
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.
- 4d ago First seen · 75 lines · 0 tokens per session scan A 58bbcce048fe
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.