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.
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.
curl -O https://raw.githubusercontent.com/melgarafael/DeskcommCRM/main/.claude/agents/triagem-medidor.mdgit clone --depth 1 https://github.com/melgarafael/DeskcommCRMWrote 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.
[](https://agentmods.dev/agents/melgarafael/deskcommcrm/triagem-medidor)<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.
<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>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 | $0.00000 | $0.00474 |
| Sonnet 5 | $0.00000 | $0.00189 |
| Haiku 4.5 | $0.00000 | $0.00095 |
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 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.
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/mainno 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.mdestão ligadas pelo raio de dano.
Como você trabalha
- Ancore.
git fetch origine leia todo config de gate porgit 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=falsepermite 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, etest:dbse 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 | taildevolve o exit dotail. Escreva a saída num arquivo e meça$?na linha seguinte. grepvazio 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/:tcomem letras do caminho, e ogit showfalha com um erro que umgrep -ctransforma em zero silencioso. - Contagem absoluta só vale com a árvore limpa. Rode
git status --porcelainantes 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".
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.
- 11d ago First seen · 63 lines · 0 tokens per session scan A 3d6efc87c69c
triagem-medidor is an agent published in the GitHub repository melgarafael/DeskcommCRM (1,019 stars, last pushed yesterday), 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.
Other agents, from other repositories
architect
You are the architecture planning agent for Spree Commerce.
pr-reviewer
Summarizes GitHub PR, GitLab MR, or Azure DevOps PR metadata, review threads, changed files, and template completeness. Use during review-ticket or code-review workflows when PR/MR context exists.
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.
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.
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.
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.