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-implementgit 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 | $0.04365 |
| Opus 5 | $0.00000 | $0.02183 |
| Sonnet 5 | $0.00000 | $0.00873 |
| Haiku 4.5 | $0.00000 | $0.00436 |
Grade A, and why
sdd-implement 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 — 810 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDD Implement Command
Execute implementation tasks for a feature.
Instructions for Claude
You are executing the /sdd-implement [feature-name] command to implement a feature following SDD workflow.
Command Format
/sdd-implement authentication
/sdd-implement payment-processing
/sdd-implement user-dashboard
Your Task
Implement the feature by executing tasks from the task breakdown document, following Test-First principles (Article III) and constitutional governance.
Process
1. Read All Context
CRITICAL: Read these files first:
IMPORTANT: Always read ENGLISH versions (.md) as they are the reference/source.
# Task Breakdown (English version)
storage/specs/{{feature-name}}-tasks.md
# Design (English version)
storage/specs/{{feature-name}}-design.md
# Requirements (English version)
storage/specs/{{feature-name}}-requirements.md
# Steering Context (English version)
steering/structure.md
steering/tech.md
steering/product.md
Note: Japanese versions (.ja.md) are translations only. Always use English versions for implementation.
2. Verify Prerequisites
Check task breakdown exists:
❌ **Error**: Task breakdown not found
Expected: storage/specs/{{feature-name}}-tasks.md
Please run `/sdd-tasks {{feature-name}}` first.
Implementation requires task breakdown.
Check design exists:
❌ **Error**: Design document not found
Expected: storage/specs/{{feature-name}}-design.md
Implementation requires design document.
3. Use TodoWrite Tool
IMPORTANT: Use TodoWrite tool to track implementation progress.
Create todos for P0 tasks:
1. TASK-001: Set Up Project Structure
2. TASK-002: Write Tests for REQ-XXX-001 (RED)
3. TASK-003: Implement [Component] (GREEN)
4. TASK-004: Refactor [Component] (BLUE)
5. TASK-005: Implement Database Repository
6. TASK-006: Implement CLI Interface
7. TASK-007: Implement API Endpoints
Mark tasks as:
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 · 810 lines · 0 tokens per session scan A c8eee70ce30c
sdd-implement 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 4,365 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.