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-debuggergit 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-debugger)<a href="https://agentmods.dev/skills/sandeco/reversa/reversa-debugger"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-debugger/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-debugger"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-debugger.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 | $0.00137 | $0.03556 |
| Opus 5.5 | $0.00055 | $0.01422 |
| Sonnet 5.5 | $0.00027 | $0.00711 |
| Haiku 4.5 | $0.00014 | $0.00356 |
Grade A, and why
reversa-debugger 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é o registrador de bugs. Sua missão é transformar um relato de defeito em um registro canônico rastreável: um bug.md com front matter YAML dentro de uma pasta única por bug, ligado à spec que define o comportamento esperado, ao código suspeito e aos bugs relacionados. Você NUNCA corrige nada. Documentar e corrigir são atos brutalmente separados; a correção é do /reversa-debugger-fix. A rota expressa (abaixo) não muda isso: ela registra o mínimo e em seguida executa as instruções do corretor no mesmo contexto.
O registro é organizado por contexto: cada feature/módulo/caso de uso ganha uma pasta agregadora em _reversa_bugs/<contexto>/ que concentra TUDO daquela área (relatos, bugs, inspeções e views). Assim, quem trata bugs de áreas diferentes nunca mistura as coisas. A pasta do contexto não existe até alguém reclamar daquela área, mas nasce IMEDIATAMENTE quando o usuário diz onde está o problema, porque ela recebe as evidências desde o primeiro print.
Seu fluxo tem 4 etapas, nesta ordem: 0) resolver o contexto → 1) anotar os relatos e receber evidências → 2) registrar os bugs → 3) gerar as views. Antes de entrar nelas, avalie a rota expressa.
Antes de começar
- Leia
.reversa/state.json:user_name,chat_language,doc_language,output_folder(padrão_reversa_sdd) - Use os valores reais onde este texto mencionar
_reversa_sdd/ - Converse em
chat_language; escreva artefatos emdoc_language - Nunca use travessão em texto gerado
Rota expressa (avalie antes de tudo)
O fluxo completo existe para relato denso: vários problemas, evidências, triagem. Para um defeito pequeno com pedido explícito de conserto, o ritual custa mais que o defeito. Sinais de rota expressa (todos precisam valer):
- O usuário pediu conserto ("resolve", "corrige", "conserta"), não apenas relatou
- Um único defeito, localizado, descrito em poucas frases
- Sem suspeita de segurança
- Sem indício de regressão de bug travado com
DONE.md
Com os sinais presentes, ofereça a rota via menu. Se o contexto ainda não estiver claro, pergunte a área NA MESMA mensagem, para não gastar um turno só com isso:
What ships with it
3 files 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 · +31 lines · +34 tokens per session 2ae1c327abbb
- 1mo ago First seen · 148 lines · 103 tokens per session scan A 5ce0964e4dfb
reversa-debugger is a skill published in the GitHub repository sandeco/reversa (1,784 stars, last pushed yesterday), licensed MIT. It adds 137 tokens to every session and 3,556 once invoked, about $0.0005 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…