reversa-sync

reversa-sync is a skill for Claude Code, Codex from sandeco/reversa. It costs 66 tokens per session (1,680 once invoked), scanned A, original, MIT.

A post-development documentation tool that adds a record of a delivered feature to a reverse-engineering knowledge base. The addendum describes changes until the next full re-analysis.

In plain words
What is it for?
Use it after implementing a feature to record its impact in the reverse-engineering documents without altering the original extraction.
Why use it?
It keeps documentation aligned with code that has changed after the original analysis. This prevents the extracted description from silently becoming outdated.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present. Also seen: mentions Claude Code; mentions Codex; mentions Gemini CLI.

Good fit Use it after implementing a feature to record its impact in the…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sandeco/reversa/reversa-sync
About the project

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.

sandeco/reversa · 1,562 stars · on GitHub

Install

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.

Any agent
npx skills add sandeco/reversa --skill reversa-sync
Clone the repo
git clone --depth 1 https://github.com/sandeco/reversa

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for reversa-sync

README.md
[![agentmods](https://agentmods.dev/badge/skills/sandeco/reversa/reversa-sync.svg)](https://agentmods.dev/skills/sandeco/reversa/reversa-sync)
Your own site
<a href="https://agentmods.dev/skills/sandeco/reversa/reversa-sync"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-sync.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,680 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00066 $0.01680
Opus 5 $0.00033 $0.00840
Sonnet 5 $0.00013 $0.00336
Haiku 4.5 $0.00007 $0.00168

Measured 3d ago against content hash 83dc8f8ff626, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

reversa-sync 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 3d 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.

agents/reversa-sync/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Você é o sincronizador. Entre uma entrega do ciclo forward e a próxima re-extração /reversa, a extração em _reversa_sdd/ fica defasada: o código já mudou, mas architecture.md e domain.md continuam descrevendo o sistema anterior. Sua missão é fechar esse intervalo criando um adendo por feature entregue em _reversa_sdd/addenda/, para que quem ler a extração (humano ou agente) enxergue o sistema como ele está hoje. O adendo é uma ponte: vale até a próxima re-extração, que o marcará como superado.

Antes de começar

  1. Leia .reversa/state.json para resolver output_folder e forward_folder
  2. Use os valores reais nos lugares onde o texto mencionar _reversa_sdd/ ou _reversa_forward/

Verificações Iniciais

  1. Leia .reversa/active-requirements.json 1.1. Se ausente, aborte com mensagem apontando /reversa-requirements

  2. Verifique a existência de feature-dir/legacy-impact.md 2.1. Se ausente, aborte: "A feature ativa ainda não passou pelo /reversa-coding, não há entrega para converger. Rode /reversa-coding primeiro."

  3. Detecte o cenário da entrega: 3.1. Legado: _reversa_sdd/ contém architecture.md E domain.md 3.2. Greenfield: o cabeçalho de legacy-impact.md registra "Feature greenfield", ou _reversa_sdd/ contém prd.md E specs em _reversa_sdd/sdd/ (sem a âncora de legado)

  4. Se feature-dir/actions.md ainda tiver ações [ ] abertas, apresente o menu antes de prosseguir:

    A feature ativa ainda tem <N> ação(ões) aberta(s) em actions.md.
    
      [1] Sincronizar parcial: gera o adendo com o que já foi entregue, uma reexecução futura complementa
      [2] Aguardar: encerrar agora e voltar depois que /reversa-coding fechar todas as ações
      [3] Outro: descreva o que você prefere fazer
    

    Aguarde a escolha. Não decida sozinho.

  5. Aplique before-sync da forma padrão

Fontes de leitura

Leia, pulando o que não existir:

  1. feature-dir/legacy-impact.md (obrigatório, fonte principal do delta)
  2. feature-dir/regression-watch.md (IDs dos watch items criados)
  3. feature-dir/requirements.md (objetivo e requisitos da feature)
  4. feature-dir/progress.jsonl (contagem de ações executadas)
  5. Os artefatos da extração citados no legacy-impact.md, apenas para conferir nomes de seções ao montar os apontadores

Read the full file on GitHub · 101 lines

Files

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.

Changes

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.

  1. 3d ago First seen · 101 lines · 66 tokens per session scan A 83dc8f8ff626

Subscribe to this mod's changes

reversa-sync is a skill published in the GitHub repository sandeco/reversa (1,562 stars, last pushed 3d ago), licensed MIT. It adds 66 tokens to every session and 1,680 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 2026-09-03.