Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/bittencourtthulio/expxdevWrote 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/bittencourtthulio/expxdev/onboarding)<a href="https://agentmods.dev/commands/bittencourtthulio/expxdev/onboarding"><img src="https://agentmods.dev/badge/commands/bittencourtthulio/expxdev/onboarding/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/bittencourtthulio/expxdev/onboarding"><img src="https://agentmods.dev/badge/commands/bittencourtthulio/expxdev/onboarding.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 | $0.00090 | $0.01898 |
| Opus 5.5 | $0.00036 | $0.00759 |
| Sonnet 5.5 | $0.00018 | $0.00380 |
| Haiku 4.5 | $0.00009 | $0.00190 |
Grade A, and why
onboarding 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 today.
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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é o roteador de onboarding do método Expx. Não faz mapeamento nenhum você mesmo: só decide, camada por camada, se o mapeamento inicial dela já existe, se ela está instalada, e — quando as duas coisas baterem — aciona o comando de verdade daquela camada.
Por que este comando existe
Cada camada (stackx, designx, legadox, memox, prodx) já sabe
detectar e gerar o próprio mapeamento inicial. O que faltava era quem
perguntasse, na primeira vez que alguém abre um projeto com várias camadas
instaladas: "o que já foi mapeado, o que falta, e em que ordem eu rodo o
resto?" — em vez da pessoa descobrir isso comando por comando.
Este roteador não duplica nenhum critério de detecção. Ele só lê o que cada camada já expõe (a presença do artefato que ela produz, ou — no caso do legadox — a confirmação de quem está rodando) e chama o comando real.
1. Descubra o que está instalado
test -d .claude/skills/stackx && echo "stackx instalado"
test -d .claude/skills/designx && echo "designx instalado"
test -d .claude/skills/legadox && echo "legadox instalado"
test -d .claude/skills/memox && echo "memox instalado"
test -d .claude/skills/prodx && echo "prodx instalado"
Se nenhuma das cinco estiver instalada, diga isso em uma linha e pare — não
há nada para este comando orquestrar. As demais camadas (runx, sprintx,
mergex, buildx) nunca entram nesta lista: elas não produzem mapeamento
inicial próprio, só consomem o que estas cinco geram.
2. Para cada camada instalada, verifique se já foi mapeada
test -f docs/produto/PRODUTO.md && echo "prodx: mapeado" || echo "prodx: pendente"
test -f docs/stack/CONVENCOES.md && echo "stackx: mapeado" || echo "stackx: pendente"
test -f docs/design-system/DESIGN-SYSTEM.md && echo "designx: mapeado" || echo "designx: pendente"
test -f docs/legado/PERFIL.md && echo "legadox: mapeado" || echo "legadox: pendente"
test -f .expx/memoria/indice.json && echo "memox: mapeado" || echo "memox: pendente"
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.
- today First seen · 123 lines · 90 tokens per session scan A 1a4b603ccc5d
onboarding is a command published in the GitHub repository bittencourtthulio/expxdev (3 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 1,898 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-11-07.
onboarding compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| onboardingbittencourtthulio/expxdev | Command | 3 | 1mo ago | MIT | A | 90 | Claude Code |
| follow-updamusix/atomic-claude | Command | 115 | 5d ago | MIT | A | 0 | Claude Code |
| vs-stopmtarcure/claude-vibe-squad | Command | 228 | 9d ago | MIT | A | 0 | Claude Code |
| startstriderZA/OpenCodeGameStudios | Command | 114 | 2d ago | MIT | A | 8 | Claude Code |
| amp-downloadagentmessaging/claude-plugin | Command | 5 | 5d ago | Apache-2.0 | A | 0 | Claude Code |
| todo.templateevan043/claude-cli-advanced-starter-pack | Command | 61 | 3mo ago | MIT | A | 0 | Claude Code |
| dedupecoltonbearden/carrel | Command | 2 | 3d ago | MIT | A | 24 | Claude Code |