sdd:init

sdd:init is a skill for Claude Code, Codex from alfredoperez/sdd. It costs 32 tokens per session (1,761 once invoked), scanned A, original, MIT.

A setup command for Spec-Driven Development, an approach where a codebase is guided by maintained written specifications. It creates the .sdd project structure and can add specifications for existing areas one at a time.

In plain words
What is it for?
Use it to initialize specification files, record principles and decisions, and gradually document parts of an existing repository.
Why use it?
It creates shared project context without forcing a full rewrite or replacing specifications you have already reviewed.

Skill for Claude CodeCodex

Part of the sdd plugin — 11 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/alfredoperez/sdd/init
Any agent
npx skills add alfredoperez/sdd --skill init
Clone the repo
git clone --depth 1 https://github.com/alfredoperez/sdd

Made for: Claude Code, Codex.

Or install sdd, the plugin that ships this one along with the rest of its 11 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/alfredoperez/sdd/init.svg)](https://agentmods.dev/skills/alfredoperez/sdd/init)
Your own site
<a href="https://agentmods.dev/skills/alfredoperez/sdd/init"><img src="https://agentmods.dev/badge/skills/alfredoperez/sdd/init.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,761 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 $0.00032 $0.01761
Opus 5 $0.00016 $0.00881
Sonnet 5 $0.00006 $0.00352
Haiku 4.5 $0.00003 $0.00176

Measured 4d ago against content hash f67d0f96a366, 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/init/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sdd:init does two things, both optional and idempotent:

  1. Scaffold — create the .sdd/ folder for project-wide context (principles, ADR storage, config).
  2. Adopt — incrementally bootstrap Layer 1 living specs from an existing codebase, one area at a time.

You can stop after the scaffold. Adoption is never forced, never whole-repo, and safe to re-run — it only adds new areas and never overwrites a spec you've reviewed.

Shared Instructions

  • Layered Context — living-spec paths, the resolver script (lib/scripts/resolve-spec-paths.py), tier files, and the domains registry.

Steps

1. Detect state

Check the project root for: .sdd.json, .sdd/principles.md, .sdd/decisions/, and whether .sdd.json already has a domains map.

  • If the scaffold artifacts are missing → first run: do Phase 1, then offer Phase 2.
  • If they all already exist → already initialized: skip Phase 1 and go straight to Phase 2 (adopt another area).

Phase 1 — Scaffold (Layer 0)

Build a list of only the artifacts that don't exist (never overwrite). If the list is empty, say ✓ .sdd/ already initialized and go to Phase 2.

  1. Present via AskUserQuestion: Create all / Customize / Cancel. (Customize → ask per-artifact yes/no.)
  2. Create the chosen artifacts:
    • .sdd.json (only if absent): minimal default
      { "specsDir": "specs", "commitFormat": "conventional", "noAttribution": true }
      
    • .sdd/decisions/.gitkeep (empty file so git tracks the folder).
    • .sdd/principles.md — ask via AskUserQuestion how to seed it:
      • Blank template — copy lib/templates/principles.md verbatim.
      • Infer from codebase — spawn one subagent: read lint/format/test/build config (e.g. eslint, prettier, tsconfig, package.json scripts, CI files), CLAUDE.md, and the folder layout, then draft 5–10 candidate project MUSTs in the principles.md bullet shape. Ground every rule in something it actually saw; mark anything uncertain for the user. Show the draft; the user confirms/edits before you write the file.
  3. Output the created files.

Read the full file on GitHub · 125 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 · 125 lines · 32 tokens per session scan A f67d0f96a366

Subscribe to this mod's changes

sdd:init is a skill published in the GitHub repository alfredoperez/sdd (2 stars, last pushed 12d ago), licensed MIT. It adds 32 tokens to every session and 1,761 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens