reversa-debugger-debate

reversa-debugger-debate is a skill for Claude Code, Codex from sandeco/reversa. It costs 65 tokens per session (1,471 once invoked), scanned A, original, MIT.

An optional multi-agent debate workflow for deciding how to understand or repair a recorded bug, or whether the specification is correct. Several independent agents discuss the evidence, and a separate judge produces one recommendation.

In plain words
What is it for?
Use it for difficult bug diagnosis, choosing a repair strategy, or resolving disagreements between the code, tests, and written specification.
Why use it?
It provides competing explanations and a reviewed decision when a bug is difficult or disputed. The process keeps its estimated cost and execution state visible.

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 for difficult bug diagnosis, choosing a repair strategy, or resolving disagreements between the code, tests, and written specification.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sandeco/reversa/reversa-debugger-debate
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 · 1,564 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-debugger-debate
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-debugger-debate

README.md
[![agentmods](https://agentmods.dev/badge/skills/sandeco/reversa/reversa-debugger-debate.svg)](https://agentmods.dev/skills/sandeco/reversa/reversa-debugger-debate)
Your own site
<a href="https://agentmods.dev/skills/sandeco/reversa/reversa-debugger-debate"><img src="https://agentmods.dev/badge/skills/sandeco/reversa/reversa-debugger-debate.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,471 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00065 $0.01471
Opus 5 $0.00032 $0.00736
Sonnet 5 $0.00013 $0.00294
Haiku 4.5 $0.00006 $0.00147

Measured 8d ago against content hash f29a07141eb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

reversa-debugger-debate 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.

agents/reversa-debugger-debate/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Você é o moderador do debate. Vários agentes independentes que se criticam produzem decisões mais robustas que uma única passada, e um juiz separado com rubrica congelada impede que o debate vire eco. Sua missão é rodar esse protocolo com custo transparente e estado auditável, e entregar UMA recomendação sintetizada. Protocolo completo em references/debate-protocol.md.

Antes de começar

  1. Leia .reversa/state.json (output_folder, chat_language, doc_language)
  2. Resolva o bug alvo (ID canônico ou display_number). Sem bug registrado, aborte apontando /reversa-debugger. Leia o bug.md, as evidências e a spec efetiva vinculada
  3. Se visibility: restricted: harness externos ficam PROIBIDOS neste debate e nenhum detalhe explorável sai da pasta do bug

Setup (entradas travadas para a execução inteira)

  1. Modo (se não veio no argumento, pergunte via menu):

    • diagnosis: múltiplas hipóteses causais; debatedores disputam qual hipótese as evidências sustentam e quais probes discriminam
    • repair: causa suficientemente confirmada; disputam a estratégia (menor mudança coerente, menor risco, reversibilidade)
    • spec: código, testes e spec divergem; disputam qual representa a regra correta. Termina em RECOMENDAÇÃO de veredito, a decisão é humana
  2. N (solvers, padrão 3) e R (rodadas, padrão 2). Se o usuário não informar, use o padrão e avise.

  3. Debatedores externos: detecte harness CLI instalados (ex.: codex, gemini, opencode no PATH). Se houver, AVISE a possibilidade, mas só inclua com aceite explícito:

    Detectei <lista> instalado(s). Debatedores externos trazem diversidade real de modelo.
    
      [1] Só agentes locais (padrão)
      [2] Incluir <harness> como debatedor (ocupa uma das N cadeiras)
      [3] Incluir <harness> como avaliador (critic: avalia propostas, não concorre)
      [4] Outro
    

    Antes de oferecer, faça o probe: a CLI responde em modo não interativo? Está autenticada? Sem confirmação de operação read-only, o debatedor externo recebe apenas material copiado para debate/ (nunca acesso mutável ao projeto).

  4. Custo e demora, sempre antes de rodar: mostre a conta real (solvers x rodadas + critics x rodadas + 1 juiz) e avise que o loop demora porque cada rodada chama todos os debatedores. Só prossiga com aceite.

Read the full file on GitHub · 76 lines

Files

What ships with it

2 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.

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. 8d ago First seen · 76 lines · 65 tokens per session scan A f29a07141eb3

Subscribe to this mod's changes

reversa-debugger-debate is a skill published in the GitHub repository sandeco/reversa (1,564 stars, last pushed 4d ago), licensed MIT. It adds 65 tokens to every session and 1,471 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.

Related

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…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

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.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

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…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens