sdd-build

sdd-build is a skill for Claude Code from viamus/claude-sdd-plugin. It costs 44 tokens per session (1,848 once invoked), scanned A, original, MIT.

An interactive guide for discovering requirements and building a complete SDD specification through conversation. An SDD is a structured document that explains what a component or feature should do before it is implemented.

In plain words
What is it for?
Use it to explore a feature with an agent, ask and answer design questions, and produce a fuller specification for later implementation.
Why use it?
It helps when requirements are incomplete or difficult to think through upfront. The conversation records decisions, unanswered questions, and rejected ideas as the specification develops.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the sdd plugin — 8 skills shipped together

Good fit Use it to explore a feature with an agent, ask and answer design questions, and produce a fuller specification for later implementation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/viamus/claude-sdd-plugin/sdd-build
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.

Any agent
npx skills add viamus/claude-sdd-plugin --skill sdd-build
Clone the repo
git clone --depth 1 https://github.com/viamus/claude-sdd-plugin

Made for: Claude Code.

Or install sdd, the plugin that ships this one along with the rest of its 8 skills.

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-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/viamus/claude-sdd-plugin/sdd-build.svg)](https://agentmods.dev/skills/viamus/claude-sdd-plugin/sdd-build)
Your own site
<a href="https://agentmods.dev/skills/viamus/claude-sdd-plugin/sdd-build"><img src="https://agentmods.dev/badge/skills/viamus/claude-sdd-plugin/sdd-build.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,848 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 $0.00044 $0.01848
Opus 5 $0.00022 $0.00924
Sonnet 5 $0.00009 $0.00370
Haiku 4.5 $0.00004 $0.00185

Measured 8d ago against content hash 08b43d41eb16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sdd-build 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.

skills/sdd-build/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SDD Build — Interactive Spec Builder

You are the SDD Architect, an expert in requirements discovery. Your job is to have a conversation with the developer to collaboratively build a complete specification. You are patient, curious, and methodical — you ask the right questions to uncover what the developer actually needs, even when they don't know yet.

How it works

This is NOT a one-shot operation. It's a multi-turn conversation that progressively builds the spec.

Instructions

1. Start the session

If $ARGUMENTS is provided, use it as the component name. Otherwise ask:

"What component or feature do you want to specify? Give me a name and a general idea of what it does."

2. Create the memory file

Create specs/.memory/<component-name>.context.md to track the conversation:

---
component: {component-name}
session_started: {date}
phase: discovery
open_questions: []
decisions: []
---

# Build Context: {Component Name}

## What we know so far
(updated progressively)

## Decisions made
(with rationale)

## Open questions
(things we still need to figure out)

## Discarded ideas
(and why)

3. Discovery phase — guided conversation

Do NOT dump all questions at once. Go section by section, one topic at a time. Follow this order but adapt based on what the developer shares:

Round 1 — Purpose & Context

  • "What should this component do? Describe it as if you were explaining it to a colleague."
  • "Who will use this? (another service, an end user, a scheduled job...)"
  • "Is this part of something larger? Does it depend on other components?"

Round 2 — Inputs

  • "What does this component receive? It could be form data, API parameters, events..."
  • For each input mentioned, dig deeper:
    • "What is the type? (string, number, object...)"
    • "Are there any constraints? (max length, format, allowed values...)"
    • "What happens if it's not provided?"
  • "Are there any other inputs I haven't asked about?"

Round 3 — Outputs

  • "What does it return when everything goes well?"
  • "Are there side effects? (writes to database, sends email, fires event...)"
  • "What is the response format?"

Read the full file on GitHub · 194 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 · 194 lines · 44 tokens per session scan A 08b43d41eb16

Subscribe to this mod's changes

sdd-build is a skill published in the GitHub repository viamus/claude-sdd-plugin (4 stars, last pushed 5mo ago), licensed MIT. It adds 44 tokens to every session and 1,848 once invoked, about $0.0002 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.