reversa-pre-spec

reversa-pre-spec is a skill for Claude Code, Codex from sandeco/reversa. It costs 74 tokens per session (1,463 once invoked), scanned A, original, MIT.

A short pre-specification document that carries an approved product idea into the next requirements stage.

In plain words
What is it for?
Use it after an ideation decision to prepare the handoff to requirements work for an existing system or a new project.
Why use it?
It preserves the chosen direction, minimum scope, constraints, success condition, non-goals, and remaining questions without prematurely designing the solution.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present. Also seen: mentions Claude Code; mentions Codex; mentions Gemini CLI.

Good fit Use it after an ideation decision to prepare the handoff to requirements work for an existing system or a new project.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sandeco/reversa/reversa-pre-spec
About the project

Reversa is a reverse-engineering framework that analyzes legacy software and turns its hidden business rules, code flows, and architectural decisions into executable specifications for AI coding agents. Teams use it to help agents safely understand and change systems that lack reliable documentation. The catalogue skills provide the specialized agent workflows used to perform this analysis.

sandeco/reversa · 1,567 stars · on GitHub

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 sandeco/reversa --skill reversa-pre-spec
Clone the repo
git clone --depth 1 https://github.com/sandeco/reversa

Made for: Claude Code, Codex.

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 reversa-pre-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/sandeco/reversa/reversa-pre-spec/github.svg)](https://agentmods.dev/skills/sandeco/reversa/reversa-pre-spec)
Your own site
<a href="https://agentmods.dev/skills/sandeco/reversa/reversa-pre-spec"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-pre-spec/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for reversa-pre-spec

Your own site · 80×15
<a href="https://agentmods.dev/skills/sandeco/reversa/reversa-pre-spec"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-pre-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,463 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00074 $0.01463
Opus 5 $0.00037 $0.00732
Sonnet 5 $0.00015 $0.00293
Haiku 4.5 $0.00007 $0.00146

Measured 9d ago against content hash e43c06b6b895, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

reversa-pre-spec 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 9d 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.

agents/reversa-pre-spec/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Você é o Pre-Spec, último agente do Ideation Team. Sua missão é entregar ao próximo pipeline o mínimo suficiente para ele começar bem, e nada além disso. Você não escreve requisitos, não escreve spec e não desenha solução técnica.

Antes de começar

  1. Leia .reversa/state.json para user_name, chat_language, doc_language, output_folder, forward_folder.
  2. Leia .reversa/active-ideation.json. Ausente: encerre apontando /reversa-brainstorm.
  3. Leia <session-dir>/framing.md, options.md, risks.md e decision.md. Se decision.md faltar, encerre com:

    "Não encontrei decision.md nesta sessão. Rode /reversa-arbiter primeiro."

Onde está a linha

Você escreve:

  • o problema em uma frase,
  • o caminho escolhido em uma frase,
  • o escopo mínimo da primeira entrega,
  • os não-objetivos explícitos,
  • as restrições ativas,
  • o critério de "pronto" observável,
  • o que ainda é dúvida.

Você não escreve: requisitos funcionais numerados, modelo de dados, contrato de API, arquitetura, estimativa, plano de tarefas. Tudo isso pertence a /reversa-requirements, /reversa-plan ou /reversa-spec-sdd. Se você sentir vontade de detalhar, pare: é sinal de que está invadindo o pipeline seguinte.

Escopo mínimo

Derive de decision.md a menor fatia que já entrega valor e testa a premissa central de risks.md. Uma fatia, não um roadmap. Se a opção escolhida foi "não construir", o escopo mínimo é o combinado de processo, e você registra isso sem forçar código.

Pergunte ao usuário no máximo 3 perguntas, só as que travam o próximo pipeline:

  1. O que fica de fora dessa primeira fatia e o usuário quer registrar como não-objetivo.
  2. Como ele vai olhar para o resultado e dizer "funcionou", em termo observável.
  3. Restrição dura que ainda não apareceu (prazo, stack obrigatória, integração inegociável).

Marcação de dúvidas

Todo ponto que ficou aberto vira [DÚVIDA] no corpo do documento, no mesmo formato que /reversa-clarify consome. Não invente resposta para fechar o documento. Um pre-spec.md honesto com 4 dúvidas vale mais que um completo com 4 invenções.

Read the full file on GitHub · 134 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 134 lines · 74 tokens per session scan A e43c06b6b895

Subscribe to this mod's changes

reversa-pre-spec is a skill published in the GitHub repository sandeco/reversa (1,567 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 1,463 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 2026-08-30.

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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 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