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-depth-inspectiongit 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-depth-inspection)<a href="https://agentmods.dev/skills/sandeco/reversa/reversa-depth-inspection"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-depth-inspection/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-depth-inspection"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-depth-inspection.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 | $0.00069 | $0.01524 |
| Opus 5 | $0.00034 | $0.00762 |
| Sonnet 5 | $0.00014 | $0.00305 |
| Haiku 4.5 | $0.00007 | $0.00152 |
Grade A, and why
reversa-depth-inspection 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 10d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é o inspetor profundo. Quando uma feature "vive dando problema", um bug pontual não basta: sua missão é varrer a feature inteira com lentes especializadas e transformar cada defeito confirmado em um bug registrado e rastreável. Você só diagnostica. Nunca corrige.
Antes de começar
- Leia
.reversa/state.json(output_folder,chat_language,doc_language) - Se
_reversa_bugs/não existir, execute o bootstrap do registro descrito no/reversa-debugger(APENAS README com closure policy e taxonomy.yaml; nenhuma pasta vazia) 2.1. Resolva o contexto (pasta agregadora da feature/módulo/caso de uso) como no/reversa-debugger: case a fala do usuário com as pastas de contexto existentes em_reversa_bugs/e com o taxonomy.yaml, confirme via menu, e só crie_reversa_bugs/<contexto>/quando a varredura de fato produzir artefatos - Pergunte a feature alvo se não veio no argumento, oferecendo as features conhecidas do
taxonomy.yamlcomo opções + "Outro"
Etapa 1: mapa da feature
Monte e apresente o mapa antes de varrer:
- Specs: seções de
_reversa_sdd/que definem a feature (spec efetiva: original + adendos vigentes) - Código: arquivos e símbolos que a implementam (siga imports e chamadas a partir dos pontos de entrada)
- Testes: o que já cobre a feature
- Dados: tabelas, caches, filas e contratos externos tocados
- Bugs existentes da feature (via catálogo): a inspeção não redescoberta o que já está registrado
Etapa 2: lentes
Dispare as lentes como subagentes paralelos quando o harness suportar; senão, execute em sequência. Cada lente recebe o mapa e SÓ PRODUZ ACHADOS, nunca registra bugs nem altera nada.
Lentes obrigatórias:
| Lente | O que procura |
|---|---|
| Conformidade com spec | Divergências entre o comportamento implementado e a spec efetiva |
| Fluxo de dados | Valores que nascem, se transformam e persistem errado (nulos, arredondamento, encoding, timezone) |
| Contratos e integrações | Chamadas externas, APIs e filas com contrato violado ou falha sem tratamento |
| Estados de erro e edge cases | Caminhos infelizes: entradas vazias, limites, permissões, cancelamentos |
| Cobertura de testes | Regras da spec sem teste; testes que passam sem provar nada |
| Concorrência e consistência | Transações, idempotência, retries, condições de corrida, cache, ordenação de eventos |
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.
- 10d ago First seen · 100 lines · 69 tokens per session scan A 198f65ed9e6c
reversa-depth-inspection is a skill published in the GitHub repository sandeco/reversa (1,571 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 1,524 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
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
gsd-ns-review
Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
gitnexus
A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.
cleanup-code-inspections
Reduce technical debt and improve code quality by systematically resolving static analysis warnings.
dorodango
Polishes working code through successive quality passes in fresh subagents. Use after tests pass when code needs multi-dimension refinement before release.