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/.agents/skills/deskcomm-contribuir/SKILL.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/skills/melgarafael/deskcommcrm/deskcomm-contribuir)<a href="https://agentmods.dev/skills/melgarafael/deskcommcrm/deskcomm-contribuir"><img src="https://agentmods.dev/badge/skills/melgarafael/deskcommcrm/deskcomm-contribuir/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/skills/melgarafael/deskcommcrm/deskcomm-contribuir"><img src="https://agentmods.dev/badge/skills/melgarafael/deskcommcrm/deskcomm-contribuir.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 | $0.00169 | $0.04077 |
| Opus 5.5 | $0.00068 | $0.01631 |
| Sonnet 5.5 | $0.00034 | $0.00815 |
| Haiku 4.5 | $0.00017 | $0.00408 |
Grade B, and why
deskcomm-contribuir scanned grade B with 2 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 1mo 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
for g in ${r:+"$r/.agents/skills"} ~/.claude/skills ~/.agents/skills ~/.gemini/config/skills; do Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
A doutrina do repo: `curl` não prova experiência; Playwright dirigindo o front, num banco fresco do How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contribuir para o DeskcommCRM sem retrabalho
Quem contribui aqui quase nunca erra por falta de capacidade — erra por não saber a régua. A régua
existe, mas está espalhada em três documentos (CLAUDE.md, CONTRIBUTING.md e o procedimento de
triagem, com mais de 100 KB) e é aplicada depois do PR, por quem mantém. Este guia aplica a
mesma régua antes, do seu lado, para o PR chegar pronto. Taxa histórica de recusa de PR de
fork: zero. O que trava é retrabalho — e retrabalho se evita medindo.
Como você age
- Aconselha, não bloqueia. Você mede e mostra; só os hooks de git bloqueiam, e só o que é
irreversível (push na
main, migration sem a tripla). Uma pessoa que quer seguir mesmo assim segue — sabendo o que vai acontecer na triagem. - Mede na fonte, nunca copia número. A lista de checks obrigatórios, quantas specs rodam e o que o CI cobre mudam toda semana; cada afirmação vem com o comando que a produziu.
- Declara o que não mediu. Um PR que diz "não rodei o e2e porque não tenho Docker" é melhor que um que marca tudo. O mantenedor prova o que ficou faltando; a régua pública é essa.
- Sabota antes de dizer "testado". Teste que não fica vermelho quando o conserto sai não guarda nada.
Passo 0 — quem está contribuindo
Este passo vem antes de trazer a main (Passo 1), então não conte com o script estar no clone:
um fork anterior a 2026-09-10 ainda não o tem, e o guia pode ter vindo da instalação global. O
comando abaixo procura o script na raiz do clone (vale de qualquer subpasta dele) e, se não achar,
nas três pastas globais em que o instalar-guias.sh põe os guias. Cole como está, de onde você
estiver:
r="$(git rev-parse --show-toplevel 2>/dev/null)"; s=""
for g in ${r:+"$r/.agents/skills"} ~/.claude/skills ~/.agents/skills ~/.gemini/config/skills; do
[ -f "$g/deskcomm-contribuir/scripts/quem-sou.sh" ] && { s="$g/deskcomm-contribuir/scripts/quem-sou.sh"; break; }
done
if [ -n "$s" ]; then bash "$s"; else
echo "NÃO MEDIDO — não achei o quem-sou.sh ${r:+no clone $r }nem nas pastas globais dos guias." >&2
echo "Instale os guias pelo comando de uma linha do README (https://github.com/melgarafael/DeskcommCRM#readme) e rode de novo." >&2
false
fi
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 323 B
- references/depois-do-pr.md 3.4 KB
- references/erros-recorrentes.md 4.1 KB
- references/pre-voo.md 7.8 KB
- references/receita-e2e-local.md 4.7 KB
- scripts/armar-hooks.sh 2.0 KB runs code
- scripts/hooks/avisar-identidade.sh 1.1 KB runs code
- scripts/hooks/check-migration-triple.sh 12 KB runs code
- scripts/hooks/pre-commit 338 B
- scripts/hooks/pre-push 1.4 KB
- scripts/hooks/sessao.sh 1.4 KB runs code
- scripts/pre-voo.sh 19 KB runs code
- scripts/quem-sou.sh 2.4 KB runs code
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.
- 1mo ago Changed 06567377766b
- 1mo ago Changed · +28 lines 7f5492e51578
- 1mo ago Changed · +12 lines · -8 tokens per session 48840e70c879
- 1mo ago Changed · +31 lines · +177 tokens per session scan A → B bb22744c482b
- 1mo ago First seen · 173 lines · 0 tokens per session scan A 645769e6c699
deskcomm-contribuir is a skill published in the GitHub repository melgarafael/DeskcommCRM (5,198 stars, last pushed today), licensed MIT. It adds 169 tokens to every session and 4,077 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-12.
deskcomm-contribuir compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| deskcomm-contribuirmelgarafael/DeskcommCRM | Skill | 5.2k | today | MIT | B | 169 | Codex |
| summarize-changesakanthed/SecureAI-Scan | Skill | 25 | 5d ago | MIT | A | 18 | Claude Code |
| review-implement-phaseprisma/orm | Skill | 48k | yesterday | Apache-2.0 | A | 38 | Claude Code |
| github-pr-workflowpaperclipai/paperclip | Skill | 111k | today | MIT | A | 39 | Claude Code, Codex |
| review-deltatirth8205/code-review-graph | Skill | 33k | 8d ago | MIT | A | 24 | Claude Code |
| github-contributordaymade/claude-code-skills | Skill | 1.5k | yesterday | MIT | A | 105 | Claude Code, Codex |
| hero-diff-highlightUnclecheng-li/AI_Animation | Skill | 1.7k | 11d ago | MIT | A | 0 | Claude Code, Codex |