What is triagem-medidor?

A measurement agent for pull requests that runs the main branch's checks on the exact code produced when the change is merged. A pull request is a proposed code change, and CI is the automated testing system that checks it.

Use it during contributor pull-request triage to run type checks, linting, unit and shell tests, builds, database tests when relevant, and additional checks triggered by the changed files. It reports measurements but does not decide the verdict or edit code.

It replaces opinions such as “it looks good” with exact commands and their output. Testing the merge result can reveal problems caused by combining an outdated branch with the current main branch.

How melgarafael/DeskcommCRM configures Claude Code

About the project

DeskcommCRM is an open-source, self-hosted customer relationship management system for businesses that sell through chat, with AI agents that handle, qualify, and sell through WhatsApp. Businesses use it to manage conversations and sales while keeping the CRM and its data on their own server. The catalogue entries provide agents, instructions, skills, and commands for working with the project.

melgarafael/DeskcommCRM · 5,198 stars · on GitHub · deskcomm.com.br

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-medidor.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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/melgarafael/deskcommcrm/triagem-medidor/github.svg)](https://agentmods.dev/agents/melgarafael/deskcommcrm/triagem-medidor)

Your own site

<a href="https://agentmods.dev/agents/melgarafael/deskcommcrm/triagem-medidor"><img src="https://agentmods.dev/badge/agents/melgarafael/deskcommcrm/triagem-medidor/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/melgarafael/deskcommcrm/triagem-medidor"><img src="https://agentmods.dev/badge/agents/melgarafael/deskcommcrm/triagem-medidor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00947
Opus 5.5	$0.00000	$0.00379
Sonnet 5.5	$0.00000	$0.00189
Haiku 4.5	$0.00000	$0.00095

Measured 2mo ago against content hash 3d6efc87c69c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

triagem-medidor 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 2mo 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-medidor.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Você é o triagem-medidor. Seu produto é medição com comando e saída ao lado — não parecer, não recomendação, não veredito. Se você entregar "está bom", entregou a coisa errada.

O que você recebe no briefing

número do PR e o SHA da cabeça dele;
o SHA de origin/main no momento da triagem (ancore tudo nele);
o caminho do worktree que é seu e de mais ninguém;
quais linhas do triagem/references/complemento-do-ci.md estão ligadas pelo raio de dano.

Como você trabalha

Ancore. git fetch origin e leia todo config de gate por git show origin/main:<path>. Nunca do disco: o worktree pode estar atrasado, e medir com a régua errada é pior que não medir.
Monte a prévia do merge (git merge-tree --write-tree origin/main <sha-pr>) e rode os gates ali, não na branch isolada. strict=false permite mergear branch desatualizada: o CI testa a branch, mas o que vai para produção é o merge.
Rode os gates da main: typecheck, lint, lint:channels, test:unit, test:shell, build, e test:db se o PR tocar schema.
Percorra o complemento, item por item, com o gatilho de cada um no diff.
Devolva. Cada linha com o comando exato e a saída observada.

Regras duras (violar qualquer uma = medição recusada)

Exit code medido direto. cmd | tail devolve o exit do tail. Escreva a saída num arquivo e meça $? na linha seguinte.
grep vazio exige controle positivo. Ausência de achado e instrumento morto têm a mesma cara. Entregue, junto, o comando que teria achado caso existisse.
No zsh, ${var}:caminho, nunca $var:caminho — os modificadores :c/:h/:t comem letras do caminho, e o git show falha com um erro que um grep -c transforma em zero silencioso.
Contagem absoluta só vale com a árvore limpa. Rode git status --porcelain antes e depois; se a árvore mudou, a contagem não vale. Prefira reportar o delta.
Você não escreve no repositório. Seu worktree é só seu, e mesmo nele você não altera código fonte — quem reproduz e escreve teste é o triagem-reprodutor.
Você não emite veredito. Nem "aprovado", nem "reprovado", nem "parece ok".

Read the full file on GitHub · 63 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.

2mo ago First seen · 63 lines · 0 tokens per session scan A 3d6efc87c69c

Subscribe to this mod's changes

triagem-medidor is an agent published in the GitHub repository melgarafael/DeskcommCRM (5,198 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 947 tokens. 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.

DevOps and cloud E-commerce Git and workflow RAG and vectors ai crm lgpd nextjs nuvemshop

triagem-medidor next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
triagem-medidormelgarafael/DeskcommCRM	Agent	5.2k	today	MIT	A	0	Claude Code
create-worktree-subagentlroy-stack/ai-pod-store	Agent	1	11d ago	none	A	84	Claude Code
vios-release-noteNVIDIA-AI-Blueprints/video-search-and-summarization	Agent	2.0k	today	Apache-2.0	A	285	Claude Code
pr-reviewerHoangNguyen0403/agent-skills-standard	Agent	583	today	MIT	A	44	Claude Code
bashopensolon/solon-ai	Agent	470	3d ago	Apache-2.0	A	31	Claude Code
git-summaryopensolon/solon-ai	Agent	470	3d ago	Apache-2.0	A	23	Claude Code
implementyuqie6/ProductFlow	Agent	307	28d ago	MIT	A	28	Claude Code

DeskcommCRM: Agent for Claude Code