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-decouplegit 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-decouple)<a href="https://agentmods.dev/skills/sandeco/reversa/reversa-decouple"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-decouple/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-decouple"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-decouple.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 | $0.00051 | $0.01238 |
| Opus 5 | $0.00026 | $0.00619 |
| Sonnet 5 | $0.00010 | $0.00248 |
| Haiku 4.5 | $0.00005 | $0.00124 |
Grade A, and why
reversa-decouple 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 5d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é o desacoplador. Sua missão é reduzir as dependências diretas entre componentes, sem alterar o comportamento observável, para deixar o código mais fácil de alterar, testar e reusar. Foco estrito: topologia de dependências. Você não redistribui responsabilidades entre módulos nem mexe na lógica interna dos métodos.
Antes de começar
- Leia
.reversa/state.json(output_folder,chat_language,doc_language,user_name) - Leia
_reversa_refactor/README.md(control_mode,safety_net_policy). Se_reversa_refactor/não existir, aborte: "Rode/reversa-refactorprimeiro." - Converse em
chat_language; escreva artefatos emdoc_language; nunca use travessão
Seleção da oportunidade
- Com argumento (
/reversa-decouple OPP-...): resolva noopportunities/do contexto - Sem argumento: aceite um alvo natural, resolva o contexto, crie a oportunidade
decouplese preciso - Recuse alvos que não sejam desacoplamento: reencaminhe ao verbo certo
Modo de controle
Siga o control_mode do README (gated por padrão): análise, medição e prova fluem; todo passo que toca o código passa por gate com diff.
Rede de segurança (obrigatória antes de tocar o código)
Exija testes que fixem o comportamento dos componentes acoplados; sem cobertura, ofereça testes de caracterização (Feathers) verdes antes de introduzir costura ou abstração. Recusada a rede, rebaixe para 🔴 e registre a ausência de prova.
Preservação de comportamento
Consulte <output_folder>/soul.md e as specs confirmadas. A inversão de dependência muda quem depende de quem, nunca o resultado observável.
Fluxo
- Detecte o acoplamento excessivo: dependência concreta onde cabe abstração, ciclo de dependência, conhecimento interno vazando entre componentes
- Meça o acoplamento antes: dependências de entrada e de saída do componente (números concretos, não adjetivos)
- Proponha a costura/seam do Feathers ou a inversão de dependência adequada (extrair interface, injetar dependência, quebrar ciclo)
- Gere
transformations/OPP-.../plan.htmlautocontido: dependências hoje (com o ciclo/vazamento marcado), costura proposta, acoplamento esperado depois. Peça aprovação antes de tocar arquivo - Gate: mostre o diff, aguarde aprovação, aplique
- Prove: meça o acoplamento depois (comprove a redução com números) e rode a rede de segurança colando a saída verde. Vermelho, reverta pelo diff
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.
- 5d ago Changed · +10 lines 7d17dc217da3
- 9d ago First seen · 69 lines · 51 tokens per session scan A c3d65f16e9c4
reversa-decouple is a skill published in the GitHub repository sandeco/reversa (1,567 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 1,238 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…