sdd-init

sdd-init is a skill for Claude Code, Codex from rubenzarroca/sdd-plugin. It costs 75 tokens per session (3,435 once invoked), scanned A, original, MIT.

A setup workflow for Specification-Driven Development, a way to define project rules and feature specifications before writing code. It creates the files needed to track those rules and the project’s progress.

In plain words
What is it for?
Use it when starting this workflow in a new or existing codebase, such as when you say “start SDD,” “init project,” or “initialize specs.”
Why use it?
It reduces unclear decisions about tools, naming, structure, and feature requirements when building a project with an AI coding agent.

Skill for Claude CodeCodex

Part of the sdd plugin — 12 skills shipped together

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

Made for: Claude Code, Codex.

Or install sdd, the plugin that ships this one along with the rest of its 12 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-init

README.md
[![agentmods](https://agentmods.dev/badge/skills/rubenzarroca/sdd-plugin/sdd-init.svg)](https://agentmods.dev/skills/rubenzarroca/sdd-plugin/sdd-init)
Your own site
<a href="https://agentmods.dev/skills/rubenzarroca/sdd-plugin/sdd-init"><img src="https://agentmods.dev/badge/skills/rubenzarroca/sdd-plugin/sdd-init.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,435 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 $0.00075 $0.03435
Opus 5 $0.00037 $0.01717
Sonnet 5 $0.00015 $0.00687
Haiku 4.5 $0.00007 $0.00344

Measured 4d ago against content hash 74714829caf7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdd-init 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 4d 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-init/SKILL.md · 294 lines

How it starts

The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sdd:init — Initialize SDD workflow for this project

You are setting up Specification-Driven Development for a project. Follow these steps exactly, in order. Do NOT skip steps. Do NOT read source code — only directory listing and package manifest.

Step 0: Orient the user

Before any detection or file creation, briefly explain what is about to happen — in plain language, not technical jargon:

"Before we write any code, we're going to set up two things: a project constitution (your non-negotiable rules — like which tools to use and how code should be organized) and a specifications workflow (a structured way to define features before building them). Without clear rules, an AI makes hundreds of small decisions on your behalf — naming conventions, folder structure, which libraries to use — and many will conflict with what you actually want. These two tools stop that. I'll ask you a few questions — there are no wrong answers, and we can always refine later."

Then ask: "Can you describe in one or two sentences what this project does?" Use the answer to ground all subsequent questions — refer back to the user's own words, use their terminology, and frame every technical concept through their business context throughout the entire init process.

Coaching Layer

Init is the user's first encounter with SDD. The coaching here focuses on the constitution interview (Step 5), where the user must articulate project principles they may never have formalized.

Scaffolding triggers during the constitution interview:

What Claude detects What Claude does
User says "I don't know" to a category question Propose based on detected stack: "Based on your package.json, you're using Next.js with App Router. That typically means file-based routing with colocated components. Does that sound right?"
User gives an overly broad answer ("we test everything" / "standard security") Narrow with specifics: "What do you test today? Unit tests on business logic? E2E on key flows? If nothing is set up yet, that's fine — we'll define it when you build your first feature."
User provides a non-verifiable principle ("keep code clean", "follow best practices") Reframe concretely: "'Clean code' means different things to different teams. For your project, could we say 'All functions under 50 lines' or 'No file exceeds 300 lines'? What does clean mean to you?"
User defers all decisions ("whatever you think is best") Anchor to their project: "I can suggest defaults based on your stack, but these rules are yours — they'll constrain everything I build later. Let me propose something and you tell me if it fits."

Read the full file on GitHub · 294 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. 4d ago First seen · 294 lines · 75 tokens per session scan A 74714829caf7

Subscribe to this mod's changes

sdd-init is a skill published in the GitHub repository rubenzarroca/sdd-plugin (6 stars, last pushed 6mo ago), licensed MIT. It adds 75 tokens to every session and 3,435 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

fix

Use to drive a bug fix from first report through close, with a "why didn't we catch it?" loop at the end. Triggers — "/engineer.fix", "a bug came in", "this is broken", "a user reported X", "there's a defect", "we have a regression", "this needs a fix", "another report", "more issues", "still failing", "validation…

swingerman/engineer · 100 tokens

next

Use at the start of a work session, or any time the question is "what should I pick up now" across the whole project. Triggers — "/engineer.next", "what's next", "what should I work on", "what should I do next", "where do I pick up".

swingerman/engineer · 64 tokens

crap-analyzer

Use to produce a risk-based refactor + test plan for recently-changed code on a diff/branch/PR by computing CRAP (complexity × untested) on changed methods. Multi-language — TypeScript, JavaScript, Python, Java, Kotlin, Go, Ruby, C#, Rust, PHP — auto-discovers how the repo generates coverage. Triggers …

swingerman/engineer · 109 tokens

post-merge

Use immediately after a PR is merged to clean up the local feature branch and resync main. Triggers — "/engineer.post-merge", "did we merge", "did we push", "PR merged", "post-merge cleanup", or right after a gh pr merge succeeds in the same session.

swingerman/engineer · 68 tokens

session-summary

Use at the end of a work session on a DAE feature, so the next session picks up cleanly. Triggers — "/engineer.session-summary", "wrap up the session", "write the session log", "I'm stopping for the day".

swingerman/engineer · 54 tokens

onboard

Use to bring a project into the DAE methodology, or to check an onboarded project for gaps. Triggers — "/engineer.onboard", "onboard this project", "set up DAE here", "adopt the methodology", or when a DAE skill fails because no manifest exists.

swingerman/engineer · 64 tokens