sdd-validate

A command that checks whether a feature follows the project’s constitutional rules and whether its requirements are fully covered by the design, tasks, code, and tests.

In plain words
What is it for?
Use it after feature work to review the requirements, design, task list, source files, tests, security standards, code quality, and test coverage.
Why use it?
It provides a final traceability check, meaning you can connect each requirement to the work that implements and tests it.

Command for Claude Code

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.

agentmods
npx agentmods add commands/nahisaho/codegraphmcpserver/sdd-validate
Clone the repo
git clone --depth 1 https://github.com/nahisaho/CodeGraphMCPServer

Made for: Claude Code.

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 4,313 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.04313
Opus 5 $0.00000 $0.02157
Sonnet 5 $0.00000 $0.00863
Haiku 4.5 $0.00000 $0.00431

Measured 2d ago against content hash 55a98968724c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdd-validate 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.

.claude/commands/sdd-validate.md · 783 lines

How it starts

The opening of the file, as written. The whole thing — 783 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SDD Validate Command

Validate constitutional compliance and requirements coverage.


Instructions for Claude

You are executing the /sdd-validate [feature-name] command to validate constitutional compliance and requirements coverage for a feature.

Command Format

/sdd-validate authentication
/sdd-validate payment-processing
/sdd-validate user-dashboard

Your Task

Perform comprehensive validation of the feature implementation against:

  1. Constitutional Articles (9 articles)
  2. Requirements coverage (100% traceability)
  3. Code quality standards
  4. Security standards
  5. Test coverage

Process

1. Read All Documentation

IMPORTANT: Always read ENGLISH versions (.md) as they are the reference/source.

# Requirements and Design (English versions)
storage/specs/{{feature-name}}-requirements.md
storage/specs/{{feature-name}}-design.md
storage/specs/{{feature-name}}-tasks.md

# Steering Context (English versions)
steering/structure.md
steering/tech.md
steering/product.md
steering/rules/constitution.md

# Source Code
lib/{{feature}}/src/**/*.ts
lib/{{feature}}/tests/**/*.test.ts
app/api/{{resource}}/**/*.ts

Note: Japanese versions (.ja.md) are translations only. Use English versions for validation.


2. Constitutional Validation

Validate each of the 9 Constitutional Articles:

Article I: Library-First Principle

Requirement: All new features SHALL begin as independent libraries.

Validation Steps:

  1. Check lib/{{feature}}/ directory exists
  2. Verify library structure:
    • lib/{{feature}}/src/ exists
    • lib/{{feature}}/tests/ exists
    • lib/{{feature}}/package.json exists
    • Public API exported via src/index.ts
  3. Verify NO dependencies on application code:
    • Grep for imports from app/, pages/, etc.
    • Library should only import from own src/ or external packages

Example Output:

### Article I: Library-First Principle

**Status**: ✅ PASS

**Evidence**:

- Library location: `lib/auth/`
- Public API: `lib/auth/src/index.ts`
- Independent tests: `lib/auth/tests/`
- No application dependencies found

**Files Checked**:

- lib/auth/src/service.ts
- lib/auth/src/repository.ts
- lib/auth/src/index.ts

Read the full file on GitHub · 783 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. 2d ago First seen · 783 lines · 0 tokens per session scan A 55a98968724c

Subscribe to this mod's changes

sdd-validate 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 4,313 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.