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.
git clone --depth 1 https://github.com/gszhangwei/open-spddWrote 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/gszhangwei/open-spdd/spdd-reasons-canvas)<a href="https://agentmods.dev/commands/gszhangwei/open-spdd/spdd-reasons-canvas"><img src="https://agentmods.dev/badge/commands/gszhangwei/open-spdd/spdd-reasons-canvas/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/gszhangwei/open-spdd/spdd-reasons-canvas"><img src="https://agentmods.dev/badge/commands/gszhangwei/open-spdd/spdd-reasons-canvas.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00021 | $0.04050 |
| Opus 5 | $0.00010 | $0.02025 |
| Sonnet 5 | $0.00004 | $0.00810 |
| Haiku 4.5 | $0.00002 | $0.00405 |
Grade A, and why
/spdd-reasons-canvas 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 11d 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 — 469 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate implementation-ready structured prompts using the built-in REASONS-Canvas framework (Requirements, Entities, Approach, Structure, Operations, Norms, Safeguards).
Input: Business context/requirement description after /spdd-reasons-canvas
Input can be provided in two ways:
- Text description: Direct text describing the requirement
- File/folder reference: Using
@to reference files or folders containing requirements
Examples:
# Text description
/spdd-reasons-canvas Implement user registration functionality, supporting email verification and mobile phone binding
# File reference
/spdd-reasons-canvas @requirements/user-registration.md
# Combined (text + file reference)
/spdd-reasons-canvas @requirements/user-registration.md additionally requires support for third-party OAuth login
# Multiple file references
/spdd-reasons-canvas @requirements/user-registration.md @docs/api-spec.yaml
Steps
-
Validate and consolidate business context
a. If business context is missing, use the AskUserQuestion tool (open-ended, no preset options) to ask:
- "Please provide the business context or requirement description (you can use text, @file references, or both)"
IMPORTANT: Do NOT proceed without business context input.
b. If input contains
@file/folder references:- Read ALL referenced files completely using the Read tool
- For folder references, read all relevant files within the folder (
.md,.txt,.yaml,.json, etc.) - Consolidate all file contents into a unified business context
c. Combine all context sources:
- Merge text descriptions with file contents
- Preserve the complete information from all sources
- Do NOT summarize or truncate - maintain full context integrity
Context Integrity Check:
- Verify all
@references were successfully read - If any file cannot be read, report the error and ask user to provide alternative
- Confirm the consolidated context contains sufficient information to proceed
-
Read relevant codebase context
- Search for related existing implementations
- Read relevant entity classes, services, controllers
- Understand current architecture patterns
- Identify existing data structures and APIs
-
Apply the REASONS-Canvas Framework
Generate fully-populated content for each of the 7 stages using the built-in construction guidance:
R - Requirements
Objective: Extract core problem essence and fundamental goals
Output Format:
## Requirements [Use concise verb phrases to describe the essence of requirements]Construction Guidance:
- Essence Extraction: Abstract what fundamental problem to solve and what value to create for whom
- Boundary Definition: Clarify the applicable scope and limitations
- Value Focus: Highlight business value and user benefits
- Use Verb Phrases: "Implement...", "Create...", "Design..."
- Avoid Feature Stacking: Don't list specific functions, abstract essential problems
Quality Standards:
- Core requirements summarizable in one sentence
- Reflect business value rather than technical implementation
- Clear problem boundaries and constraints
E - Entities
Objective: Build clear business entity relationship models
Output Format:
## Entities ```mermaid classDiagram direction TB class [CoreEntity] { +[AttributeType] [attributeName] +[Method]() } class [RelatedEntity] { +[AttributeType] [attributeName] } class [RequestDTO] { +[AttributeType] [attributeName] } class [ResponseDTO] { +[AttributeType] [attributeName] } [CoreEntity] "[cardinality]" -- "[cardinality]" [RelatedEntity] : [relationshipDesc] [RequestDTO] --> [CoreEntity] : creates [CoreEntity] --> [ResponseDTO] : maps to ```Construction Guidance:
- Entity Identification: Identify core business entities, supporting entities, DTO objects
- Attribute Modeling: Define key attributes using "type+name" format
- Relationship Modeling: Clarify relationship types (1:1, 1:N, N:M) and business semantics
- Interface Design: Include key methods and static factory methods
- Data Flow: Reflect complete flow of request→processing→response
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.
- 11d ago First seen · 469 lines · 21 tokens per session scan A 555afd8351f1
/spdd-reasons-canvas is a command published in the GitHub repository gszhangwei/open-spdd (769 stars, last pushed 20d ago), licensed MIT. It adds 21 tokens to every session and 4,050 once invoked, about $0.0001 per session on Opus 5. 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.
Other commands, from other repositories
prompt
System instructions for writing effective prompts. Apply when generating commands, skills, agents, or any LLM instructions.
prompt-show
Display full details of a saved prompt by ID.
ai
Load the Kaizen skill for production-ready AI agent implementation with signature-based programming and multi-agent coordination.
audit-prompt
Evaluate an existing prompt for clarity, effectiveness, and edge cases.
develop-image-prompt.eval
Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.
dare-llm-integration
Integração segura e eficiente com LLMs (Gemini, Claude, OpenAI, Ollama) em projetos DARE.