spec-driven

spec-driven is a skill for Claude Code from lucasandradeb/my-claude-code-config. It costs 38 tokens per session (1,067 once invoked), scanned B, original, MIT.

A setup guide for specification-driven development, a way of writing clear requirements and acceptance checks before implementation. It creates a project structure for specifications and guides the first specification.

In plain words
What is it for?
Use it when starting a new project or a substantial feature with the explicit /spec-driven command.
Why use it?
It turns vague feature ideas into requirements that an agent can use to build and verify the result.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Good fit Use it when starting a new project or a substantial feature with the explicit /spec-driven command.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lucasandradeb/my-claude-code-config/spec-driven
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 lucasandradeb/my-claude-code-config --skill spec-driven
Clone the repo
git clone --depth 1 https://github.com/lucasandradeb/my-claude-code-config

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 spec-driven

README.md
[![agentmods](https://agentmods.dev/badge/skills/lucasandradeb/my-claude-code-config/spec-driven.svg)](https://agentmods.dev/skills/lucasandradeb/my-claude-code-config/spec-driven)
Your own site
<a href="https://agentmods.dev/skills/lucasandradeb/my-claude-code-config/spec-driven"><img src="https://agentmods.dev/badge/skills/lucasandradeb/my-claude-code-config/spec-driven.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,067 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00038 $0.01067
Opus 5 $0.00019 $0.00534
Sonnet 5 $0.00008 $0.00213
Haiku 4.5 $0.00004 $0.00107

Measured 7d ago against content hash 5e6fbc548ef2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

spec-driven scanned grade B with 2 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -X POST http://localhost:3000/endpoint -d '{"key":"value"}'

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST http://localhost:3000/endpoint -d '{"key":"value"}'
skills/spec-driven/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec-Driven Development Setup

Overview

Spec-driven development transforma requisitos vagos em artefatos estruturados que o Claude pode usar para verificar o proprio trabalho. O ciclo e: escrever spec → implementar → validar contra criterios de aceite.

Principio central: Uma boa spec nao descreve apenas "o que construir", mas tambem "como saber que esta correto".

Quando Usar

  • Novo projeto iniciando do zero
  • Nova feature com escopo nao trivial
  • Qualquer entrega onde "feito" precisa de definicao objetiva

Passo 1 — Setup da Estrutura

Se o projeto nao tem a estrutura abaixo, criá-la agora:

projeto/
├─ CLAUDE.md                     # convencoes permanentes (stack, build, lint, test)
├─ docs/
│  └─ specs/
│     └─ .gitkeep
└─ .claude/
   └─ settings.json
mkdir -p docs/specs .claude
touch docs/specs/.gitkeep

Se CLAUDE.md nao existir, perguntar ao usuario:

  • Stack principal e versoes
  • Comando de build/test/lint
  • Padroes de PR e commit
  • Restricoes de arquitetura

Passo 2 — Criar a Spec

Criar docs/specs/<nome-da-feature>.md com o template abaixo.

Preencher cada secao com o usuario antes de qualquer codigo.

# [Nome da Feature]

## Problema
<!-- O que esta quebrado ou faltando? Por que isso importa? -->

## Objetivo
<!-- Uma frase: o que deve ser verdade apos a implementacao? -->

## Escopo

### Incluido
- 

### Excluido (fora de escopo)
- 

## Requisitos Funcionais
<!-- O que o sistema DEVE fazer -->
1. 

## Requisitos Nao Funcionais
<!-- Performance, seguranca, compatibilidade -->
- 

## Criterios de Aceite
<!-- Condicoes objetivas e verificaveis. Cada item deve ser true/false. -->
- [ ] 
- [ ] 

## Validacao
<!-- Comandos exatos para verificar cada criterio de aceite -->
```bash
# exemplo:
npm test -- --testPathPattern=feature-x
curl -X POST http://localhost:3000/endpoint -d '{"key":"value"}'

Arquivos Impactados

Dependencias e Riscos

Read the full file on GitHub · 149 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 · 149 lines · 38 tokens per session scan B 5e6fbc548ef2

Subscribe to this mod's changes

spec-driven is a skill published in the GitHub repository lucasandradeb/my-claude-code-config (2 stars, last pushed 20d ago), licensed MIT. It adds 38 tokens to every session and 1,067 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). 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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens