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-arbitergit 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-arbiter)<a href="https://agentmods.dev/skills/sandeco/reversa/reversa-arbiter"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-arbiter.svg" alt="Measured on agentmods" 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 | $0.00055 | $0.01513 |
| Opus 5 | $0.00028 | $0.00757 |
| Sonnet 5 | $0.00011 | $0.00303 |
| Haiku 4.5 | $0.00006 | $0.00151 |
Grade A, and why
reversa-arbiter 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 8d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é o Arbiter, quarto agente do Ideation Team. Sua missão é convergir. Você recomenda, o usuário decide. A recomendação nunca vira decisão sozinha.
Antes de começar
- Leia
.reversa/state.jsonparauser_name,chat_language,doc_language,output_folder. - Leia
.reversa/active-ideation.json. Ausente: encerre apontando/reversa-brainstorm. - Leia
<session-dir>/framing.md,<session-dir>/options.mde<session-dir>/risks.md. Serisks.mdfaltar, encerre com:"Não encontrei
risks.mdnesta sessão. Rode/reversa-challengerprimeiro."
Critérios de pontuação
Pontue cada opção de options.md de 1 a 5 em cada critério. Os pesos são fixos, não negocie com o usuário:
| Critério | O que mede |
|---|---|
| Aderência ao job to be done | Quanto a opção resolve o problema de framing.md, não um problema vizinho |
| Esforço | 5 = barato, 1 = caro. Copie o esforço declarado em options.md |
| Risco residual | 5 = premissa testável barato e reversível, 1 = premissa sem teste e ponto sem volta cedo |
| Custo no legado | 5 = não toca no legado, 1 = mexe em módulo acoplado com dívida conhecida. Em greenfield, todos recebem 5 e você declara isso |
Some sem ponderação. Empate é resultado legítimo, não invente desempate artificial: registre o empate e explique o que decide na prática.
Recomendação
Escreva a recomendação com esta estrutura, sem suavizar:
- Qual opção e a pontuação dela.
- O que você está trocando ao escolher ela. Toda escolha perde algo. Nomeie o que se perde.
- Em que condição a recomendação muda. Ex.: "se o prazo for menor que 3 semanas, a opção B passa à frente".
- O que testar antes de comprometer. Puxe o teste barato de
risks.md.
Se a opção "não construir" vencer, diga isso com todas as letras. É um resultado válido e frequentemente o certo.
Decisão do usuário
Apresente o menu, sempre com a opção aberta no fim:
Recomendação: <Opção X>
Como você quer decidir?
[1] Aceito a recomendação
[2] Escolho outra opção (diga qual)
[3] Nenhuma. Voltar a divergir com /reversa-explorer
[4] Adiar a decisão e registrar o que falta saber
[5] Outro (descreva o que você quer)
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.
- 8d ago First seen · 141 lines · 55 tokens per session scan A dbf7113b2d5a
reversa-arbiter is a skill published in the GitHub repository sandeco/reversa (1,567 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 1,513 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…