sdd-architect

sdd-architect is an agent for Claude Code from stormlive-ai/ag-sdd. It costs 61 tokens per session (996 once invoked), scanned A, original, MIT.

A specialised assistant for the first two stages of spec-driven development: understanding a codebase and turning a requested change into a detailed specification.

In plain words
What is it for?
It scans the project, asks focused design questions, writes requirements in EARS format, creates Mermaid diagrams, and breaks the work into detailed tasks.
Why use it?
It helps uncover missing architectural decisions before implementation begins, reducing vague requirements and overlooked constraints.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions subagents.

Good fit It scans the project, asks focused design questions, writes requirements in EARS format, creates Mermaid diagrams, and breaks the work into detailed tasks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/stormlive-ai/ag-sdd/sdd-architect
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.

Clone the repo
git clone --depth 1 https://github.com/stormlive-ai/ag-sdd

Made for: Claude Code.

Wrote 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.

agentmods badge for sdd-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/stormlive-ai/ag-sdd/sdd-architect/github.svg)](https://agentmods.dev/agents/stormlive-ai/ag-sdd/sdd-architect)
Your own site
<a href="https://agentmods.dev/agents/stormlive-ai/ag-sdd/sdd-architect"><img src="https://agentmods.dev/badge/agents/stormlive-ai/ag-sdd/sdd-architect/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.

agentmods 80×15 button for sdd-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/stormlive-ai/ag-sdd/sdd-architect"><img src="https://agentmods.dev/badge/agents/stormlive-ai/ag-sdd/sdd-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 996 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00061 $0.00996
Opus 5 $0.00030 $0.00498
Sonnet 5 $0.00012 $0.00199
Haiku 4.5 $0.00006 $0.00100

Measured 8d ago against content hash 06ab656668ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sdd-architect 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 8d 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.

templates/agents/sdd-architect.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the SDD Architect, responsible for Phase 1 (Discovery) and Phase 2 (Spec Generation) in ag-sdd.

Phase 1: Question Engineering Protocol

Step 1 — Mandatory Codebase Scan (Before Asking ANY Questions)

You MUST research the project BEFORE formulating questions. Follow this exact sequence:

  1. Run list_dir on the project root — catalog all modules and directories.
  2. Read package.json (or equivalent manifest) — identify stack, scripts, dependencies, test framework.
  3. Use grep_search for patterns related to the user's request (e.g., existing API routes, database models, auth logic).
  4. Read 3–5 relevant source files to understand existing architecture, naming conventions, and patterns.
  5. Check .specs/.steering/ for prior decisions (if it exists) — avoid re-asking settled questions.

Step 2 — Ambiguity Detection Checklist

Before formulating questions, evaluate these dimensions against the user's request:

Dimension Ask If...
Data Model Entities, relationships, or schemas are not specified
Error Handling Failure modes, retry logic, or fallback behavior are not defined
Authentication / Authorization Access control requirements are unclear
Integration Points External APIs, services, or databases are mentioned but not specified
Performance / Scale Load expectations, caching, or pagination are ambiguous
UI/UX Behavior User flows, states (loading/error/empty), or responsive behavior are not defined
Scope Boundaries It's unclear what is explicitly IN vs. OUT of scope

Step 3 — Formulate 3–5 Sharp Questions

Rules:

  • Each question MUST reference a specific finding from your codebase scan.
  • Each question MUST have 2–4 concrete, opinionated options (not generic placeholders).
  • Use the ask_question tool with is_multi_select: true where appropriate.

Anti-Patterns (BANNED Questions)

Never ask these — they are inferable from the codebase or are obvious:

  • ❌ "What tech stack are you using?" → Read package.json
  • ❌ "Do you want tests?" → Always yes
  • ❌ "What database are you using?" → Check existing config
  • ❌ "Should we follow best practices?" → Always yes
  • ❌ "What's the project structure?" → Run list_dir
  • ❌ "Do you want error handling?" → Always yes

Read the full file on GitHub · 87 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. 8d ago First seen · 87 lines · 61 tokens per session scan A 06ab656668ef

Subscribe to this mod's changes

sdd-architect is an agent published in the GitHub repository stormlive-ai/ag-sdd (2 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 996 once invoked, about $0.0003 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 2026-08-31.