sdd: Instructions file for Claude Code

CLAUDE.md

sdd CLAUDE.md is an instructions file for Claude Code from alfredoperez/sdd. It costs 2,023 tokens per session, scanned A, original, MIT.

Instructions for spec-driven development (SDD), a workflow that moves a feature through specifying, planning, task breakdown, and implementation.

In plain words
What is it for?
Use it to organize development work under numbered spec folders containing requirements, plans, tasks, and state information.
Why use it?
It gives feature work a consistent structure and keeps its specifications and progress state in agreed files.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents.

This is alfredoperez/sdd's own configuration. It tells Claude Code how to work on sdd itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sdd configures →

Reuse

Borrowing it

Nothing to install: this file belongs to alfredoperez/sdd. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/alfredoperez/sdd/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/alfredoperez/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 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/alfredoperez/sdd/claude-md.svg)](https://agentmods.dev/instructions/alfredoperez/sdd/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/alfredoperez/sdd/claude-md"><img src="https://agentmods.dev/badge/instructions/alfredoperez/sdd/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,023 This file is loaded in full into every session.
When invoked 2,023 The same file — it is already loaded in full.
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 $0.02023 $0.02023
Opus 5 $0.01012 $0.01012
Sonnet 5 $0.00405 $0.00405
Haiku 4.5 $0.00202 $0.00202

Measured 7d ago against content hash 0c6f41292248, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

sdd CLAUDE.md 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 7d 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.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SDD — Spec-Driven Development

Overview

SDD is a structured workflow for AI-assisted development. Every feature goes through: specify → plan → tasks → implement. Small changes auto-detect and fast-track through the pipeline.

Core Concepts

Slug Rules

  • 2–4 words, action-noun format, lowercase, hyphens
  • Examples: clickable-file-refs, fix-payment-timeout
  • Preserve technical terms (OAuth2, JWT, API)

Spec Directory

  • All specs live in specs/{NNN}-{slug}/
  • NNN is zero-padded to 3 digits (001, 002, ...)
  • Each spec directory contains: spec.md, plan.md, tasks.md, .spec-context.json

.spec-context.json Format

The runtime state file is specs/{NNN}-{slug}/.spec-context.json. Every spec has one. SDD skills and (optionally) the SpecKit Companion VS Code extension both read and write it; both authors must follow read-then-merge and append-only transitions[]. /sdd:implement updates it via a per-spec event journal (a write-ahead log drained into the file at batched boundaries) rather than writing on every task.

Canonical reference: docs/STATE.md — narrative + field tables. Machine-readable schema: lib/schemas/spec-context.schema.json (JSON Schema draft 2020-12).

When changing the schema (adding/renaming/removing a field, changing an enum, deprecating something), update both files in the same PR. See the Docs Sync Rule below.

Commit Conventions

  • No AI attribution lines (no Co-Authored-By, no "Generated with...")

Complexity Detection

Signal Mode
Touches ≤3 existing files, change is <10 lines minimal
Pure style or config tweak minimal
Touches 4+ files, or adds a new component/service normal
Introduces new public behavior or API normal

If unclear, default to normal.

Fast Path (Minimal Mode)

When /sdd:specify detects a minimal change, it auto-generates plan.md + tasks.md in one shot. Jump straight to /sdd:implement.

Read the full file on GitHub · 110 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. 7d ago First seen · 110 lines · 2,023 tokens per session scan A 0c6f41292248

Subscribe to this mod's changes

sdd CLAUDE.md is an instructions file published in the GitHub repository alfredoperez/sdd (2 stars, last pushed 15d ago), licensed MIT. It adds 2,023 tokens to every session, about $0.0101 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 instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens