reversa-audit

reversa-audit is a skill for Claude Code, Codex from sandeco/reversa. It costs 56 tokens per session (1,160 once invoked), scanned A, original, MIT.

A read-only audit that compares requirements, a roadmap, and planned actions for contradictions and missing details. It reports each issue as critical, high, medium, or low severity.

In plain words
What is it for?
Use it as an optional review step in the Reversa development workflow to check requirements.md, roadmap.md, and actions.md. It writes only a cross-check report for a person to resolve.
Why use it?
It helps reveal when planned work does not cover the stated requirements or when the planning documents disagree. The audited planning files remain unchanged.

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 as an optional review step in the Reversa development workflow to check requirements.md, roadmap.md, and actions.md. It writes only a cross-check report for a person to resolve.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sandeco/reversa/reversa-audit
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-audit
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-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/sandeco/reversa/reversa-audit.svg)](https://agentmods.dev/skills/sandeco/reversa/reversa-audit)
Your own site
<a href="https://agentmods.dev/skills/sandeco/reversa/reversa-audit"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,160 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 $0.00056 $0.01160
Opus 5 $0.00028 $0.00580
Sonnet 5 $0.00011 $0.00232
Haiku 4.5 $0.00006 $0.00116

Measured 9d ago against content hash a36d8da34741, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

reversa-audit 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-audit/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Você é o auditor. Esse skill é estritamente leitor. Sua missão é encontrar contradições e lacunas entre requirements.md, roadmap.md e actions.md, e produzir um relatório para o humano resolver.

Regra inegociável

Esse skill NUNCA altera requirements.md, roadmap.md, actions.md, data-delta.md, interfaces/, investigation.md ou onboarding.md. Em hipótese alguma, mesmo que o usuário peça. Se o usuário pedir correção, oriente-o a usar /reversa-clarify ou edição manual.

A única escrita permitida é feature-dir/audit/cross-check.md.

Antes de começar

  1. Leia .reversa/state.json para resolver output_folder e forward_folder
  2. Use os valores reais nos lugares onde o texto mencionar _reversa_sdd/ ou _reversa_forward/

Verificações Iniciais

  1. Leia .reversa/active-requirements.json 1.1. Se ausente, aborte
  2. Verifique existência dos três artefatos: requirements.md, roadmap.md, actions.md 2.1. Se algum estiver ausente, aborte com mensagem listando o que falta e qual skill gera
  3. Aplique before-audit da forma padrão

Eixos de comparação

Verifique cada par de artefatos quanto a:

  1. Cobertura 1.1. Todo requisito funcional virou pelo menos uma decisão no roadmap 1.2. Toda decisão no roadmap virou pelo menos uma ação no actions 1.3. Todo cenário Gherkin do requirements está coberto por alguma ação ou decisão
  2. Consistência 2.1. Termos usam o mesmo nome ao longo dos três documentos (não apareça "fatura" em um e "boleto" em outro) 2.2. Identificadores citados existem (RF-12 referenciado no roadmap precisa existir no requirements) 2.3. Contratos descritos em interfaces/ aparecem no roadmap
  3. Coerência com o legado 3.1. Decisões do roadmap não contradizem regras 🟢 do _reversa_sdd/domain.md 3.2. Componentes do _reversa_sdd/architecture.md citados existem mesmo
  4. Sanidade do actions 4.1. Dependências apontam para IDs existentes 4.2. Tarefas marcadas [//] não compartilham arquivo alvo 4.3. Não há ciclo de dependência

Read the full file on GitHub · 99 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 · 99 lines · 56 tokens per session scan A a36d8da34741

Subscribe to this mod's changes

reversa-audit is a skill published in the GitHub repository sandeco/reversa (1,567 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 1,160 once invoked, about $0.0003 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

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