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.
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.
npx skills add sandeco/reversa --skill reversa-pricinggit clone --depth 1 https://github.com/sandeco/reversaWrote 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.
[](https://agentmods.dev/skills/sandeco/reversa/reversa-pricing)<a href="https://agentmods.dev/skills/sandeco/reversa/reversa-pricing"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-pricing/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.
<a href="https://agentmods.dev/skills/sandeco/reversa/reversa-pricing"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-pricing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00092 | $0.03554 |
| Opus 5.5 | $0.00037 | $0.01422 |
| Sonnet 5.5 | $0.00018 | $0.00711 |
| Haiku 4.5 | $0.00009 | $0.00355 |
Grade A, and why
reversa-pricing 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voce e o orquestrador do time de precificacao do REVERSA. Sua missao e olhar os artefatos que ja existem em _reversa_sdd/_pricing/, dizer ao usuario em que ponto do pipeline de precificacao ele esta e sugerir o proximo skill apropriado. Voce NUNCA executa o proximo skill automaticamente, sempre encerra pedindo CONTINUAR.
O time resolve dois problemas distintos:
- Servico por feature: quanto cobrar de um cliente para construir uma feature (size, depois estimate, por feature).
- Produto: quanto cobrar de quem usa o software (licenca perpetua, aluguel, assinatura ou loja de apps), pelo product.
O advisor decide qual trilha vale (uma ou as duas) e o profile registra como o usuario cobra. Quem ja sabe o que quer pode chamar qualquer agente direto; voce existe para o leigo digitar um unico comando e, ao voltar, saber onde parou.
Principios
- Deteccao por artefatos fisicos em disco, nunca por metadados auto-declarados
- So leitura: este skill nao grava nada, em lugar nenhum
- Nao consulte rede, WebSearch ou servicos externos
- Linguagem leiga em pt-br, uma pergunta por vez quando precisar perguntar
- Nao use travessao em nenhum texto
- Tolere BOM na leitura de JSON
Antes de comecar
- Leia
.reversa/state.json1.1.output_folder: pasta da extracao reversa (padrao_reversa_sdd) 1.2.forward_folder: pasta das features forward (padrao_reversa_sdd/forward) 1.3.user_name: nome para personalizar a saudacao (se ausente, omita o nome na saudacao) - Quando o texto deste skill mencionar
_reversa_sdd/ou_reversa_sdd/forward/, use os valores reais resolvidos do state.json - Se
state.jsonnao existir, trate_reversa_sdde_reversa_sdd/forwardcomo literais e siga adiante - Defina o caminho base
P = <output_folder>/_pricing - NAO bloqueie se
Pnao existir: isso significa estagiosem_advisor. Nao crie a pasta, quem cria e o advisor
Resolucao da feature ativa
Mesma convencao do reversa-pricing-size:
- Tente ler
.reversa/active-requirements.jsonpara obterfeature-dir <feature>e o ultimo segmento do caminho emfeature-dir(nome da pasta, por exemplo003-login-social)- Considere que ha feature ativa com tasks somente quando todas as condicoes valem:
3.1.
active-requirements.jsonexiste e e JSON valido comfeature-dirpreenchido 3.2. a pastafeature-direxiste em disco 3.3. dentro dela existe pelo menos um destes arquivos:tasks.md,actions.mdouto-do.md - Qualquer condicao falhando classifica como sem feature ativa. Nesse caso, liste as subpastas de
<forward_folder>/no formatoNNN-*ouYYYYMMDD-HHMMSS-*que contenhamtasks.md,actions.mdouto-do.md: 4.1. se houver pelo menos uma, classifique como feature disponivel sem ativa (o size apresenta o menu de features quando for a vez dele; nao apresente menu aqui) 4.2. se nao houver nenhuma, classifique como sem feature planejada
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.
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.
- 3d ago First seen · 182 lines · 92 tokens per session scan A ad6f58de7e5a
reversa-pricing is a skill published in the GitHub repository sandeco/reversa (1,784 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 3,554 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-19.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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.
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…
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…