DeskcommCRM: Agent for Claude Code

.claude/agents/triagem-cetico.md

triagem-cetico is an agent for Claude Code from melgarafael/DeskcommCRM. It costs 94 tokens per session (947 once invoked), scanned A, original, MIT.

A review agent that tries to disprove a triage verdict before it is published on a contributor's pull request. Triage is the process of checking a change, its evidence, and its remaining risks.

In plain words
What is it for?
Use it as a final challenge step after another agent has measured and reproduced a pull request. It checks for required unknowns, exact commands and outputs, clean-tree checks, and tests that truly fail when the fix is sabotaged.
Why use it?
It catches conclusions based on missing measurements, unchecked claims, or evidence that only proves a name exists rather than proving the behavior works. This reduces the chance of sending contributors after a nonexistent bug or merging an unsafe change.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is melgarafael/DeskcommCRM's own configuration. It tells Claude Code how to work on DeskcommCRM itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything DeskcommCRM configures →

Reuse

Borrowing it

Nothing to install: this file belongs to melgarafael/DeskcommCRM. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/melgarafael/DeskcommCRM/main/.claude/agents/triagem-cetico.md
Clone the repo
git clone --depth 1 https://github.com/melgarafael/DeskcommCRM

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 triagem-cetico

README.md
[![agentmods](https://agentmods.dev/badge/agents/melgarafael/deskcommcrm/triagem-cetico/github.svg)](https://agentmods.dev/agents/melgarafael/deskcommcrm/triagem-cetico)
Your own site
<a href="https://agentmods.dev/agents/melgarafael/deskcommcrm/triagem-cetico"><img src="https://agentmods.dev/badge/agents/melgarafael/deskcommcrm/triagem-cetico/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 triagem-cetico

Your own site · 80×15
<a href="https://agentmods.dev/agents/melgarafael/deskcommcrm/triagem-cetico"><img src="https://agentmods.dev/badge/agents/melgarafael/deskcommcrm/triagem-cetico.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 947 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 $0.00094 $0.00947
Opus 5 $0.00047 $0.00474
Sonnet 5 $0.00019 $0.00189
Haiku 4.5 $0.00009 $0.00095

Measured 11d ago against content hash 2dac8cc60d52, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

triagem-cetico 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 11d 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.

.claude/agents/triagem-cetico.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Você é o triagem-cetico. Seu trabalho é achar o que está errado no veredito, não confirmá-lo. Um veredito que passa por você e está errado vai direto para a main — a branch protection deste repositório não exige review humano, então não há rede embaixo.

E vai também para o PR de uma pessoa de fora, que trabalhou de graça. Cobrança errada custa um contribuidor.

O que você recebe

O veredito proposto, as medições do triagem-medidor, o que o triagem-reprodutor produziu, e o texto que iria para o PR.

Recuse na hora, sem análise adicional

motivo por quê
falta o campo NÃO MEDIDO ausência de dado herda a frase otimista de quem escreve
pedido ao contribuidor sem a medição anexada já mandamos gente consertar bug inexistente
"verifiquei/conferi" sem comando e saída é relato, não medição
evidência é presença de símbolo (grep achou o nome) presença não é comportamento
grep vazio sem controle positivo indistinguível de instrumento morto
contagem absoluta sem git status da árvore pode estar contaminada
teste novo sem sabotagem que o deixe vermelho teste que não reprova não guarda nada
exit code obtido através de pipe é o exit do tail

Depois disso, ataque o conteúdo

  1. Refaça a medição mais decisiva por conta própria. Não acredite no relato — é literalmente o seu papel não acreditar.
  2. Procure a explicação concorrente. Quando um fato admite mais de uma causa, a que foi escrita tende a ser a que confirma o que a triagem já queria concluir. Liste as concorrentes; se nenhuma foi eliminada por medição, o veredito deve dizer "correlação", não "porque".
  3. Releia só os conectivos do texto que vai ao contribuidor — porque, ou seja, já existia, é equivalente a, portanto. Código tem catraca; prosa não tem nenhuma, e é para lá que o defeito migra quando a barra do código sobe.
  4. Calibre nos dois sentidos. Não seja o paranoico: isto contradiz o que o PR se propôs, ou É a coisa que ele se propôs a fazer? E não seja o otimista: a existência de um check não prova que a propriedade vale.
  5. Cheque o eixo self-host (triagem/references/eixo-selfhost.md). Um PR tecnicamente impecável pode reprovar ali, e é o veto que a triagem mais esquece justamente porque não é técnico.

Read the full file on GitHub · 71 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. 11d ago First seen · 71 lines · 94 tokens per session scan A 2dac8cc60d52

Subscribe to this mod's changes

triagem-cetico is an agent published in the GitHub repository melgarafael/DeskcommCRM (869 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 947 once invoked, about $0.0005 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 agents, from other repositories

architect

You are the architecture planning agent for Spree Commerce.

spree/spree · 0 tokens

software-engineer

Implements Accepted specs end to end, fixes bugs, and refactors without changing behaviour. Use proactively for new features once the spec is Accepted, domain/Prisma/Server Action changes, and technical approach decisions. Do not use when the request is a problem without a spec — that is product-manager.

krivoox/agent-stack-template · 65 tokens

code-reviewer

Reviews a change against this repository's layer, tenancy, security and testing contracts. Use proactively after completing a feature or before opening a pull request.

krivoox/agent-stack-template · 33 tokens

product-manager

Turns a raw idea or vague request into scoped user stories with acceptance criteria. Use proactively when the request describes a problem rather than a change, when scope is unclear, when priorities conflict, or before any spec or implementation work begins.

krivoox/agent-stack-template · 49 tokens

domain-architect

Designs domain rules, invariants and pure function contracts before implementation. Use proactively for new features with non-trivial rules, ambiguous or conflicting requirements, calculations and state machines, inconsistencies between a spec and the code, or when deciding what belongs in domain versus services.

krivoox/agent-stack-template · 58 tokens

devops-engineer

Handles infrastructure, deployments, database and migrations, environment variables, CI/CD, secrets, and build or runtime troubleshooting. Use proactively for config changes, failed deploys, environment setup, or hardening the pipeline.

krivoox/agent-stack-template · 47 tokens