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/nahisaho/codegraphmcpserver/sdd-designgit clone --depth 1 https://github.com/nahisaho/CodeGraphMCPServerWhat 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 | $0.03746 |
| Opus 5 | $0.00000 | $0.01873 |
| Sonnet 5 | $0.00000 | $0.00749 |
| Haiku 4.5 | $0.00000 | $0.00375 |
Grade A, and why
sdd-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 2d 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 — 735 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDD Design Command
Generate technical design from requirements.
Instructions for Claude
You are executing the /sdd-design [feature-name] command to create a technical design specification.
Command Format
/sdd-design authentication
/sdd-design payment-processing
/sdd-design user-dashboard
Your Task
Generate a comprehensive technical design that implements the requirements while adhering to constitutional governance.
Process
1. Read Context (Article VI)
CRITICAL: Read these files BEFORE designing:
# Steering Context
steering/structure.md # Architecture patterns to follow
steering/tech.md # Technology stack to use
steering/product.md # Product goals and users
# Requirements
storage/specs/{{feature-name}}-requirements.md # What to implement
Extract:
- Architecture pattern (monolith, microservices, library-first)
- Approved technologies (languages, frameworks, databases)
- Requirements to implement
- Non-functional requirements (performance, security, scale)
2. Verify Requirements Exist
Check if requirements file exists:
If NOT found:
❌ **Requirements file not found**
Expected: storage/specs/{{feature-name}}-requirements.md
Please run `/sdd-requirements {{feature-name}}` first.
Design cannot proceed without requirements (Article V: Traceability).
If found: Proceed with design
3. Generate Design Document
Use template from templates/design.md:
A. Architecture Design (C4 Model)
Create 3 levels of C4 diagrams:
Level 1: Context Diagram
- Show system in context
- External users
- External systems
- Integration points
Level 2: Container Diagram
- Major deployable units
- Databases
- Message queues
- External APIs
Level 3: Component Diagram
- Internal components of main container
- Controllers, services, repositories
- Data flow between components
Example:
### C4 Model: Container Diagram
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.
- 2d ago First seen · 735 lines · 0 tokens per session scan A c30264e24b15
sdd-design is a command published in the GitHub repository nahisaho/CodeGraphMCPServer (12 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,746 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.