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-to-dogit 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-to-do)<a href="https://agentmods.dev/skills/sandeco/reversa/reversa-to-do"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-to-do/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-to-do"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-to-do.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 | $0.00043 | $0.01044 |
| Opus 5 | $0.00022 | $0.00522 |
| Sonnet 5 | $0.00009 | $0.00209 |
| Haiku 4.5 | $0.00004 | $0.00104 |
Grade A, and why
reversa-to-do 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é o decompositor. Sua missão é transformar o roadmap.md num actions.md executável, com tarefas atômicas, IDs estáveis e marcação clara do que pode rodar em paralelo.
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/
Verificações Iniciais
- Leia
.reversa/active-requirements.json1.1. Se ausente, aborte apontando/reversa-requirements - Verifique a existência de
feature-dir/roadmap.md2.1. Se ausente, aborte com mensagem clara apontando/reversa-plan. Não tente preencher o roadmap aqui - Carregue também
feature-dir/data-delta.mdefeature-dir/interfaces/*se existirem - Aplique
before-to-doda forma padrão
Estratégia de decomposição
- Use as cinco fases padrão na ordem: 1.1. Preparação (setup, scaffolding, migrações iniciais, configuração) 1.2. Testes (testes que precisam existir antes ou logo após o núcleo, se a equipe pratica TDD) 1.3. Núcleo (lógica central da feature) 1.4. Integração (cola com outras partes do sistema, contratos externos, hooks) 1.5. Polimento (logs, telemetria, mensagens, documentação curta)
- Para cada item do
roadmap.md, derive uma ou mais ações - Quebre cada ação até o ponto em que possa ser executada num único bloco coerente, sem precisar trocar de assunto
- Atribua ID
T001,T002, ..., zero-padded com três dígitos - Marque com
[//]no início da linha as tarefas que tocam arquivos diferentes E não dependem umas das outras - Em coluna explícita, registre dependências por ID (ex.:
T005 depende de T001, T003) - Em coluna explícita, registre o arquivo alvo principal (
src/payments/pdf.js, por exemplo) - Em coluna
confidência, herde 🟢 / 🟡 / 🔴 da decisão correspondente no roadmap
Critérios de "atômico"
- Uma ação é atômica quando pode ser concluída por um agente em um turno, sem precisar de feedback humano no meio
- Se uma ação tem mais de cinco subpontos lógicos, quebre
- Se uma ação toca mais de três arquivos não relacionados, quebre
- Se uma ação inclui "e também", "depois", "em seguida", quebre
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 · 90 lines · 43 tokens per session scan A 967bc76093f4
reversa-to-do is a skill published in the GitHub repository sandeco/reversa (1,589 stars, last pushed 4d ago), licensed MIT. It adds 43 tokens to every session and 1,044 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
magpie-security-issue-import-from-md
Open one or more tracking issues from a markdown file containing a batch of security findings. Each finding becomes one tracker landing in the Needs triage board column. The file itself is the full report — there is no inbound reporter to reply to and no PR to inspect.
remove
Remove a deployed framework or addon from the current workspace.