create-steering-documents-standalone

create-steering-documents-standalone is a command for Claude Code from jasonkneen/kiro. It costs 0 tokens per session (3,258 once invoked), scanned A, original, MIT.

A command that creates written guidance for how a software project should be built and maintained.

In plain words
What is it for?
Use it to prepare guidance for projects such as React or Vue websites, Python or Node.js APIs, and component libraries.
Why use it?
It gives a project consistent rules for coding, testing, Git—the system used to track code changes—and its development setup.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the kiro plugin — 8 skills, 2 commands shipped together

Good fit Use it to prepare guidance for projects such as React or Vue websites, Python or Node.js APIs, and component libraries.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jasonkneen/kiro/create-steering-documents-standalone
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/jasonkneen/kiro

Made for: Claude Code.

Or install kiro, the plugin that ships this one along with the rest of its 8 skills, 2 commands.

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 create-steering-documents-standalone

README.md
[![agentmods](https://agentmods.dev/badge/commands/jasonkneen/kiro/create-steering-documents-standalone.svg)](https://agentmods.dev/commands/jasonkneen/kiro/create-steering-documents-standalone)
Your own site
<a href="https://agentmods.dev/commands/jasonkneen/kiro/create-steering-documents-standalone"><img src="https://agentmods.dev/badge/commands/jasonkneen/kiro/create-steering-documents-standalone.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 3,258 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 $0.03258
Opus 5 $0.00000 $0.01629
Sonnet 5 $0.00000 $0.00652
Haiku 4.5 $0.00000 $0.00326

Measured 8d ago against content hash 5ac313ea5fb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

create-steering-documents-standalone 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 8d 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.

commands/create-steering-documents-standalone.md · 479 lines

How it starts

The opening of the file, as written. The whole thing — 479 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Steering Documents - Standalone

Create comprehensive steering documents for a development project based on the project type and requirements.

Usage

Create steering documents for [project description]

Examples

  • Create steering documents for a React TypeScript e-commerce application
  • Create steering documents for a Python Django REST API with PostgreSQL
  • Create steering documents for a Node.js microservices architecture
  • Create steering documents for a Vue.js component library

Process

You are an expert at creating project steering documents that provide contextual guidance for development work. Follow this systematic approach:

1. Project Analysis

First, analyze the project requirements and determine which steering documents are needed:

For Frontend Projects (React, Vue, Angular):

  • Include: project-standards.md, git-workflow.md, frontend-standards.md, development-environment.md
  • Consider: component-library.md, testing-strategy.md

For Backend/API Projects (Node.js, Python, Java):

  • Include: project-standards.md, git-workflow.md, api-design.md, development-environment.md
  • Consider: database-standards.md, security-guidelines.md

For Full-Stack Projects:

  • Include: All core documents plus technology-specific ones
  • Consider: deployment-standards.md, monitoring-guidelines.md

For Library/Package Projects:

  • Include: project-standards.md, git-workflow.md, documentation-standards.md
  • Consider: versioning-strategy.md, publishing-guidelines.md

2. Document Creation Strategy

Create steering documents using these templates and guidelines:

Core Documents (Always Create)

project-standards.md Template:

# Project Standards and Guidelines

## Code Quality Standards
- Follow language-specific style guides (ESLint for JS/TS, Black for Python, etc.)
- Maintain consistent naming conventions across the codebase
- Write self-documenting code with clear variable and function names
- Include meaningful comments for complex business logic
- Keep functions small and focused on single responsibilities

## Testing Requirements
- Write unit tests for all business logic functions
- Maintain minimum 80% code coverage
- Include integration tests for API endpoints
- Write end-to-end tests for critical user flows
- Use descriptive test names that explain the scenario being tested

## Documentation Standards
- Update README.md for any significant changes
- Document API endpoints with clear examples
- Include setup and deployment instructions
- Maintain changelog for version releases
- Document architectural decisions in ADR format

## Security Practices
- Never commit secrets, API keys, or passwords
- Use environment variables for configuration
- Validate all user inputs
- Implement proper authentication and authorization
- Follow OWASP security guidelines

## Performance Guidelines
- Optimize database queries and avoid N+1 problems
- Implement caching where appropriate
- Use lazy loading for large datasets
- Monitor and profile performance regularly
- Consider scalability in architectural decisions

Read the full file on GitHub · 479 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.

  1. 8d ago First seen · 479 lines · 0 tokens per session scan A 5ac313ea5fb2

Subscribe to this mod's changes

create-steering-documents-standalone is a command published in the GitHub repository jasonkneen/kiro (746 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,258 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 2026-08-30.