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/spec-designgit 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/spec-design)<a href="https://agentmods.dev/commands/kaze-jp/kusa/spec-design"><img src="https://agentmods.dev/badge/commands/kaze-jp/kusa/spec-design.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 | $0.00624 |
| Opus 5 | $0.00000 | $0.00312 |
| Sonnet 5 | $0.00000 | $0.00125 |
| Haiku 4.5 | $0.00000 | $0.00062 |
Grade A, and why
spec-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Technical Design
Generate a technical design document from approved requirements.
Usage
/kiro:spec-design <feature-name>
Instructions
-
Read the requirements from
.kiro/specs/$FEATURE_NAME/requirements.md. If it does not exist, instruct the user to run/kiro:spec-requirementsfirst. -
Read steering documents for technical constraints:
.ao/steering/tech.mdfor technology stack, patterns, and conventions.ao/steering/structure.mdfor project structure and file organization.ao/steering/product.mdfor product context
-
Generate
design.mdwith the following sections:
# Technical Design: <feature-name>
## Document Info
- Feature: <name>
- Status: Draft
- Created: <date>
- Requirements: ./requirements.md
## Architecture Overview
<High-level architecture description and diagram (ASCII or Mermaid)>
## Component Design
### Component: <name>
- **Purpose**: <what it does>
- **Location**: <file path>
- **Dependencies**: <other components>
- **Interface**: <public API>
### Component: <name>
...
## API Contracts
### <Endpoint/Function>
- **Signature**: <full signature>
- **Input**: <parameters with types and validation>
- **Output**: <return type and structure>
- **Errors**: <error cases and codes>
- **Example**: <usage example>
## Data Models
### <Model Name>
- **Fields**: <field definitions with types>
- **Validation**: <validation rules>
- **Relationships**: <references to other models>
## State Management
<How state flows through the system>
## Error Handling Strategy
<Error categories, recovery strategies, user-facing messages>
## Testing Strategy
- Unit test targets
- Integration test boundaries
- Edge cases to cover
## Security Considerations
<Authentication, authorization, data protection>
## Requirements Traceability
<Map each requirement ID to the design component(s) that fulfill it>
- Design principles to follow:
- Every architecture decision must include rationale
- Component boundaries must be explicit with clear interfaces
- API contracts must specify all error cases
- Data models must include validation rules
- Design for testability; avoid tight coupling
- No premature optimization
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 · 100 lines · 0 tokens per session scan A 982242be7997
spec-design 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 624 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.