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/commands/triagem-de-pr.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/commands/melgarafael/deskcommcrm/triagem-de-pr)<a href="https://agentmods.dev/commands/melgarafael/deskcommcrm/triagem-de-pr"><img src="https://agentmods.dev/badge/commands/melgarafael/deskcommcrm/triagem-de-pr/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/commands/melgarafael/deskcommcrm/triagem-de-pr"><img src="https://agentmods.dev/badge/commands/melgarafael/deskcommcrm/triagem-de-pr.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 | $0.00035 | $0.00718 |
| Opus 5 | $0.00017 | $0.00359 |
| Sonnet 5 | $0.00007 | $0.00144 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
triagem-de-pr 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 3d 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.
What it actually says
Leia o triagem/TRIAGEM.md do origin/main e siga-o à risca:
git fetch origin && git show origin/main:triagem/TRIAGEM.md
O número do PR veio no argumento; se não veio, monte a fila com os dois comandos abaixo — o segundo não é opcional, e está explicado no passe 0-bis:
gh pr list --state open # o mais antigo sem label triagem:*
gh pr list --state closed --limit 20 --json number,author,closedAt,mergedAt \
--jq '.[] | select(.mergedAt == null) | "#\(.number) \(.author.login) \(.closedAt)"'
Seis lembretes que valem antes mesmo de abrir o arquivo:
-
Você lê a doutrina do
origin/main, nunca do disco — e isso inclui oTRIAGEM.md.git fetchprimeiro, e todo config de gate porgit show origin/main:<path>. O checkout onde você está pode estar atrasado, e triar com a régua errada é pior que não triar.Isto já foi cometido dentro deste próprio passe: uma sessão leu o
TRIAGEM.mddo disco, numa branch de trabalho onde ele tinha 15 KB, enquanto o damaintinha 86 KB — e passou a triar sem os passes 3-bis, 3-ter, 8-bis e 12-bis, que são exatamente os que essa sessão precisava. O arquivo que descreve o modo de falha nº 1 é ele mesmo uma vítima do modo de falha nº 1. -
A acolhida vem antes do veredito, em minutos, e não contém avaliação nenhuma. O gargalo medido deste repositório é latência, não qualidade: rejeição histórica é zero.
-
Nenhum pedido ao contribuidor sai sem a medição que prova o defeito, anexada. Já mandamos gente consertar bug que não existia.
-
Você nunca mergeia e nunca fecha PR. Isso é a palavra do mantenedor, reportada em lote.
Uma exceção, e só ela: quando o próprio mantenedor delega o merge nesta mesma instrução. Aí a fronteira do passe 12 se suspende para esta rodada — e não para as seguintes.
-
Merge na
mainnão é entrega — a triagem só termina quando a versão sai (passe 12). O self-hoster puxa imagem por número de versão; PR que para namainnão chega a VPS nenhuma. Na prática: PR que muda comportamento precisa de um fragmento em.changes/(e você o escreve quando falta, creditando o autor), seção## [X.Y.Z]escrita à mão noCHANGELOG.mdé bloqueador, e depois do merge o corte sai porActions → release → Run workflow. O número ninguém digita: ele é calculado do que os fragmentos declararam.
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.
- 3d ago Changed · +20 lines 47f0e6b1e08e
- 11d ago First seen · 24 lines · 35 tokens per session scan A c637525534f0
triagem-de-pr is a command published in the GitHub repository melgarafael/DeskcommCRM (1,019 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 718 once invoked, about $0.0002 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.
Other commands, from other repositories
create-plan
Create a new architecture/feature plan document.
update-plan
Command "update-plan" from spree/spree, covering resolving open questions (required), keeping the trackers in step (required) and recording decisions.
autofix-pr
Monitor a pull request and fix code review and CI issues automatically.
reviews-plans
Review all active architecture plans relevant to the current task.
implement-feature
Implement an approved feature plan with fresh-context slices, TDD, evidence, and PR-ready output.
deploy-release
Prepare and verify a staged or production deployment with rollback and smoke checks.