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-forwardgit 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-forward)<a href="https://agentmods.dev/skills/sandeco/reversa/reversa-forward"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-forward/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-forward"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-forward.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00107 | $0.04213 |
| Opus 5.5 | $0.00043 | $0.01685 |
| Sonnet 5.5 | $0.00021 | $0.00843 |
| Haiku 4.5 | $0.00011 | $0.00421 |
Grade A, and why
reversa-forward 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 26d 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é o orquestrador do ciclo forward do Reversa. Sua missão é olhar o estado atual do projeto e da feature ativa, dizer ao usuário em que ponto do pipeline ele está e sugerir o próximo skill apropriado. Você NUNCA executa o próximo skill automaticamente, sempre encerra pedindo CONTINUAR.
Fila ou execução sem parar: se o pedido envolve várias features (lista ou intervalo, ex. "features 10 a 20") ou pede para executar sem parar (ex. via /goal), este skill não é o certo. Leia o SKILL.md do reversa-forward-autonomous (pasta irmã) e siga-o no lugar deste, repassando o pedido do usuário como argumento.
Antes de começar
- Leia
.reversa/state.json1.1.output_folder→ pasta da extração reversa (padrão_reversa_sdd) 1.2.forward_folder→ pasta das features forward (padrão_reversa_forward) 1.3.user_name→ nome para personalizar a saudação - Quando o texto deste skill mencionar
_reversa_sdd/ou_reversa_forward/, use os valores reais resolvidos do state.json - Se
state.jsonnão existir, trate como_reversa_sdd/e_reversa_forward/literais e siga adiante
Contexto de extração reversa
O pipeline forward funciona em dois cenários:
- Evolução de legado: existe
_reversa_sdd/com artefatos da extração reversa. Os skills do pipeline (especialmente/reversa-requirementse/reversa-plan) vão ancorar decisões nesses artefatos. - Projeto novo (greenfield): não existe
_reversa_sdd/ainda. O pipeline forward continua valendo, só perde a ancoragem no legado.
NÃO bloqueie em nenhum caso. Verifique e prepare a estrutura seguindo as MESMAS regras de criação de pastas que o /reversa original aplica:
- Resolva os paths reais a partir de
.reversa/state.json: 1.1.output_folder(padrão_reversa_sdd) 1.2.forward_folder(padrão_reversa_forward) - Se a pasta
output_folderexiste e contém pelo menos um arquivo.md, registre internamente o cenário como legado e diga ao usuário: "Extração reversa detectada, o pipeline vai ancorar decisões em<output_folder>/." - Se a pasta
output_folderNÃO existe ou está vazia, registre internamente como greenfield e: 3.1. Crie a pasta<output_folder>/(criação recursiva, equivalente amkdir -p) 3.2. Crie também a pasta<forward_folder>/se ainda não existir (pelo mesmo método) 3.3. NÃO crie nenhum arquivo dentro dessas pastas. Sem.gitkeep, sem placeholders. A pastaoutput_folderjá está no.gitignore(gerenciado pelo installer), criar arquivos só introduziria ruído 3.4. NÃO altere.reversa/state.json#created_filesnem.gitignore, isso é responsabilidade do installer e do/reversaoriginal, não deste skill 3.5. Comunique ao usuário: "Sem extração reversa neste projeto, vou operar em modo greenfield. Criei<output_folder>/e<forward_folder>/para que os skills do pipeline possam escrever artefatos quando precisarem. Se quiser ancorar em legado depois, rode/reversaa qualquer momento."
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.
- 26d ago Changed · +2 lines · +23 tokens per session aba33844cf81
- 1mo ago First seen · 234 lines · 84 tokens per session scan A e1165d3b5e2b
reversa-forward is a skill published in the GitHub repository sandeco/reversa (1,784 stars, last pushed yesterday), licensed MIT. It adds 107 tokens to every session and 4,213 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 2026-08-30.
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…