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-codinggit 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-coding)<a href="https://agentmods.dev/skills/sandeco/reversa/reversa-coding"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-coding/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-coding"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-coding.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 | $0.00064 | $0.03076 |
| Opus 5.5 | $0.00026 | $0.01230 |
| Sonnet 5.5 | $0.00013 | $0.00615 |
| Haiku 4.5 | $0.00006 | $0.00308 |
Grade A, and why
reversa-coding 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 1mo 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é o executor. Sua missão é transformar actions.md em código real, fase por fase, respeitando paralelismo e dependências. Ao terminar, deixar dois rastros para auditoria futura: legacy-impact.md (o que foi mexido no legado) e regression-watch.md (o que precisa continuar verdadeiro nas próximas extrações).
Antes de começar
- Leia
.reversa/state.jsonpara resolveroutput_foldereforward_folder - Use os valores reais nos lugares onde o texto mencionar
_reversa_sdd/ou_reversa_forward/
Âncora de contexto: legado ou greenfield
Esse skill EXIGE uma âncora de contexto em _reversa_sdd/, senão os dois artefatos centrais (legacy-impact.md e regression-watch.md) perdem o valor e o ciclo forward vira um framework genérico qualquer. Duas âncoras são válidas:
- Legado:
_reversa_sdd/contémarchitecture.mdEdomain.md(extração do Time de Descoberta via/reversa). Comportamento clássico. - Greenfield:
_reversa_sdd/contémprd.mdE pelo menos uma spec em_reversa_sdd/sdd/(artefatos do/reversa-new). Projeto novo é caso válido, o pipeline não bloqueia por ausência da extração. Os artefatos do skill se adaptam conforme descrito nas seções de geração.
Se existirem as duas âncoras (projeto que rodou /reversa e /reversa-new), use a de legado como principal e as specs SDD como complemento.
A verificação continua estrita quando NENHUMA âncora existe: o skill aborta com mensagem clara, NÃO oferece opção de prosseguir mesmo assim, NÃO escreve nada em disco.
Verificações Iniciais
- Leia
.reversa/active-requirements.json1.1. Se ausente, aborte com mensagem apontando/reversa-requirements - Verifique a existência de
feature-dir/actions.md2.1. Se ausente, aborte com mensagem apontando/reversa-to-do - Verifique a âncora de contexto:
3.1. Âncora de legado:
_reversa_sdd/existe E contémarchitecture.mdEdomain.md. Se satisfeita, registre internamente o cenário como legado e siga para o passo 4. 3.2. Âncora greenfield:_reversa_sdd/existe E contémprd.mdE pelo menos um arquivo.mdem_reversa_sdd/sdd/. Se satisfeita (e a de legado não), registre o cenário como greenfield, informe ao usuário ("Sem extração de legado, vou ancorar nos artefatos do/reversa-new:prd.mde specs SDD.") e siga para o passo 4. 3.3. Se NENHUMA das duas âncoras estiver satisfeita, aborte com a mensagem:
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.
- 1mo ago Changed · +21 lines e4dfb96acf20
- 1mo ago Changed c419a9432904
- 1mo ago First seen · 152 lines · 64 tokens per session scan A 414a907eeb58
reversa-coding is a skill published in the GitHub repository sandeco/reversa (1,784 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 3,076 once invoked, about $0.0003 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…