ag-mesa-redonda

ag-mesa-redonda is a skill for Claude Code from andregusman-raiz/a-gusman-claude. It costs 58 tokens per session (1,546 once invoked), scanned A, original, MIT.

A structured discussion between two to four specialist viewpoints, such as a project manager, architect, QA tester, or security reviewer, about a technical choice. It produces a documented decision record, including reasons and disagreements.

In plain words
What is it for?
Use it to compare options such as Redis versus Vercel KV, monorepo versus polyrepo, or REST versus GraphQL. It helps create an architecture decision record (ADR), a short document explaining what was chosen and why.
Why use it?
It reduces the risk of making an important design choice from one narrow viewpoint or from guesses about the codebase. The recorded reasoning also makes the decision easier to review later.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions CLAUDE.md.

Good fit Use it to compare options such as Redis versus Vercel KV, monorepo versus polyrepo, or REST versus GraphQL. It helps create an architecture decision record (ADR), a short document explaining what was chosen and why.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/andregusman-raiz/a-gusman-claude/ag-mesa-redonda
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 andregusman-raiz/a-gusman-claude --skill ag-mesa-redonda
Clone the repo
git clone --depth 1 https://github.com/andregusman-raiz/a-gusman-claude

Made for: Claude Code.

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 ag-mesa-redonda

README.md
[![agentmods](https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-mesa-redonda/github.svg)](https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-mesa-redonda)
Your own site
<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-mesa-redonda"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-mesa-redonda/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.

agentmods 80×15 button for ag-mesa-redonda

Your own site · 80×15
<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-mesa-redonda"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-mesa-redonda.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,546 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 4
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 $0.00058 $0.01546
Opus 5 $0.00029 $0.00773
Sonnet 5 $0.00012 $0.00309
Haiku 4.5 $0.00006 $0.00155

Measured 9d ago against content hash 1ff22c0584b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ag-mesa-redonda 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 9d 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.

skills/ag-mesa-redonda/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ag-mesa-redonda — Debate Multi-Agente

Reasoning protocol (tier topo — Fable, equivalente a reasoning_effort=xhigh): Cada perspectiva DEVE Exhaust 3+ argumentos antes de concluir; Verify com referencia ao codigo/contexto real (nao especulativo); Falsify (cada perspectiva precisa atacar o ponto fraco da oposta); Connect cadeia de consequencias. Output sem dissenting opinion explicita = trabalho raso = refazer. Detalhes: .claude/rules/deep-reasoning-directive.md.

Quem voce e

Voce e o moderador de uma mesa redonda tecnica. Seu trabalho e simular um debate entre 2-4 perspectivas especializadas sobre uma decisao tecnica, garantindo que TODAS as vozes sejam ouvidas antes de chegar a uma conclusao.

Invocacao

/ag-mesa-redonda "Redis vs Vercel KV para cache de sessao"
/ag-mesa-redonda "Monorepo vs polyrepo para microsservicos"
/ag-mesa-redonda "SSR vs SSG vs ISR para paginas de produto"
/ag-mesa-redonda --perspectivas pm,arq,qa "migrar de REST para GraphQL"

Como funciona

Fase 1: Framing (moderador)

  1. Ler o topico/decisao do $ARGUMENTS
  2. Identificar as perspectivas relevantes (auto-detectar ou usar --perspectivas)
  3. Coletar contexto: ler arquivos relevantes do projeto (CLAUDE.md, SPEC, ADRs existentes)
  4. Formular a pergunta central: "Dado [contexto], devemos [opcao A] ou [opcao B]?"

Fase 2: Abertura (cada perspectiva apresenta posicao)

Cada perspectiva fala UMA VEZ, com sua posicao inicial:

Perspectivas disponiveis:

Perspectiva Estilo de pensamento Prioriza
PM (Produto) "Qual entrega mais valor ao usuario no menor tempo?" Velocidade, UX, iteracao
ARQ (Arquiteto) "Qual decisao resiste a 10x de escala sem rewrite?" Sustentabilidade, patterns, acoplamento
QA (Qualidade) "Como isso pode quebrar em producao as 3h da manha?" Edge cases, testabilidade, observabilidade
SEC (Seguranca) "Qual superficie de ataque isso cria?" Vulnerabilidades, compliance, blast radius
DX (Dev Experience) "O dev junior consegue contribuir sem medo?" Simplicidade, docs, onboarding
OPS (Operacoes) "Quanto custa rodar e manter isso?" Custo, deploy, monitoramento

Read the full file on GitHub · 147 lines

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. 9d ago First seen · 147 lines · 58 tokens per session scan A 1ff22c0584b6

Subscribe to this mod's changes

ag-mesa-redonda is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (19 stars, last pushed 4d ago), licensed MIT. It adds 58 tokens to every session and 1,546 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.

Related

Other skills, from other repositories

taiyi-ui-design

A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.

Dong90/oh-my-taiyiforge · 35 tokens

taiyi-evolve

A workflow skill that compares the implemented code with the frozen design after development and testing. It records architecture changes and proposes updates to DESIGN.md, the document describing the intended system structure.

Dong90/oh-my-taiyiforge · 37 tokens

taiyi-diagram-c4

A code-scanning tool that builds C4 architecture documents from a repository. It separates facts observed in the code from conclusions inferred about the design and uses Mermaid diagrams as the source format.

Dong90/oh-my-taiyiforge · 48 tokens

retrospective-audit

Stage B of /prflow:retrospective-weekly: given a most-recent-first subset of one recurring pattern's occurrence-PR context bundles (bounded by auditbundlecap), re-derive the root cause and return one JSON object carrying a ranked findings array (one to three sub-patterns) — no edits, no worktree. Invoked as a subagent…

The01Geek/prflow · 91 tokens

docs

Use when documentation generally needs to catch up with a branch before pushing or merging, covering internal developer docs, external customer-facing docs, and release notes together — "update the docs", "do a docs pass before I merge", "make sure everything's documented". Prefer this when no single documentation…

The01Geek/prflow · 97 tokens

tmux-lane-orchestrator

Manage one tmux agent lane from its matching ops pane, inspect live pane state and Codex logs on cold start, and produce concise manager summaries for OpenClaw and adjacent project work.

vincentkoc/dotskills · 46 tokens