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/luanpdd/kit-mcpWrote 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/luanpdd/kit-mcp/fio)<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/fio"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/fio.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.00839 |
| Opus 5 | $0.00006 | $0.00419 |
| Sonnet 5 | $0.00003 | $0.00168 |
| Haiku 4.5 | $0.00001 | $0.00084 |
Grade A, and why
fio 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 4d 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
Analisar $ARGUMENTS para determinar o modo:
<mode_list> Se sem argumentos ou $ARGUMENTS estiver vazio:
Listar todos os threads:
ls .planning/threads/*.md 2>/dev/null
Para cada thread, ler as primeiras linhas para mostrar título e status:
## Threads Ativos
| Thread | Status | Última Atualização |
|--------|--------|--------------------|
| fix-deploy-key-auth | ABERTO | 2026-03-15 |
| pasta-tcp-timeout | RESOLVIDO | 2026-03-12 |
| perf-investigation | EM ANDAMENTO | 2026-03-17 |
Se não existirem threads, mostrar:
Nenhum thread encontrado. Crie um com: /fio <descrição>
</mode_list>
<mode_resume> Se $ARGUMENTS corresponder a um nome de thread existente (arquivo existe):
Retomar o thread — carregar seu contexto na sessão atual:
cat ".planning/threads/${THREAD_NAME}.md"
Exibir o conteúdo do thread e perguntar ao usuário o que deseja trabalhar a seguir.
Atualizar o status do thread para IN PROGRESS se estava OPEN.
</mode_resume>
<mode_create> Se $ARGUMENTS for uma nova descrição (nenhum arquivo de thread correspondente):
Criar um novo thread:
-
Gerar slug a partir da descrição:
SLUG=$(node "./.claude/framework/bin/tools.cjs" generate-slug "$ARGUMENTS") -
Criar o diretório de threads se necessário:
mkdir -p .planning/threads -
Escrever o arquivo do thread:
cat > ".planning/threads/${SLUG}.md" << 'EOF' # Thread: {descrição} ## Status: OPEN ## Objetivo {descrição} ## Contexto *Criado a partir de conversa em {data de hoje}.* ## Referências - *(adicionar links, caminhos de arquivo ou números de issue)* ## Próximos Passos - *(o que a próxima sessão deve fazer primeiro)* EOF -
Se houver contexto relevante na conversa atual (trechos de código, mensagens de erro, resultados de investigação), extrair e adicionar à seção Contexto.
-
Commitar:
node "./.claude/framework/bin/tools.cjs" commit "docs: criar thread — ${ARGUMENTS}" --files ".planning/threads/${SLUG}.md" -
Reportar:
## Thread Criado Thread: {slug} Arquivo: .planning/threads/{slug}.md Retome a qualquer momento com: /fio {slug}
</mode_create>
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.
- 4d ago First seen · 127 lines · 13 tokens per session scan A ad8782d32c83
fio is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 7d ago), licensed MIT. It adds 13 tokens to every session and 839 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
checkpoint
Export, refresh, verify, or import a comprehensive cross-topic Project Knowledge Checkpoint for a repository, with privacy checks.
audit
Audit .flow/memory/ entries against the current codebase — Keep / Update / Consolidate / Replace / Delete / Harden per entry.
cache-warm
Pre-calentar caché con contexto probable basado en hora y rol.
finish-work
A project wrap-up command for the auto-embedded framework, which supports structured embedded-software development. It runs automated checks, guides a three-part review, records reusable lessons and session notes, and archives the finished task.
handoff
Create a handoff document for seamless session continuity.
continuar
Recuperar sesión previa y generar reporte de puesta al día.