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.
npx agentmods add commands/luanpdd/kit-mcp/capturar-payloadsgit 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/capturar-payloads)<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/capturar-payloads"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/capturar-payloads.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 | $0.00048 | $0.02196 |
| Opus 5 | $0.00024 | $0.01098 |
| Sonnet 5 | $0.00010 | $0.00439 |
| Haiku 4.5 | $0.00005 | $0.00220 |
Grade A, and why
capturar-payloads 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 2d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cria/Atualiza:
- Patch na Edge Function adicionando log dedicado controlado por env
CAPTURE_PAYLOADS=true supabase/functions/_shared/payload-capture.ts— sanitização canônicatests/characterization/<edge-fn>/fixtures/payload-NN.json— fixtures sanitizados após drenagem
Após: o user tem fixtures BASEADOS EM DISTRIBUIÇÃO REAL de produção, não em sintéticos. Cobertura comportamental cresce significativamente.
Workflow esperado:
Dia 0: /capturar-payloads <fn> --mode=instrument
Dia 0: Você faz deploy + setar CAPTURE_PAYLOADS=true em env
Dia 1-7: produção captura naturalmente
Dia 7: /capturar-payloads <fn> --mode=drain
Dia 7: Fixtures criados em tests/characterization/<fn>/fixtures/
Dia 7: /caracterizar <fn> --fixtures-dir tests/characterization/<fn>/fixtures
Exemplos:
/capturar-payloads supabase/functions/webhook-stripe/index.ts # full mode 7 dias
/capturar-payloads supabase/functions/process-orders/index.ts --days 14 # janela maior
/capturar-payloads supabase/functions/process-orders/index.ts --mode=instrument # só patch
/capturar-payloads supabase/functions/process-orders/index.ts --mode=drain # só drenagem
Pré-requisitos:
- Edge Function deployada em Supabase (modo drain depende de logs em prod)
- MCP Supabase conectado para drenagem automatizada (alternativa:
supabase functions logsCLI) - Tier full em IDEs com MCP; tier partial degrada para instrumentação only
Quando preferir este comando vs /caracterizar direto:
- Edge Function tem alto traffic (≥ 100 req/dia) — distribuição real cobre edge cases que sintético não pega
- Edge Function tem contrato externo crítico (webhook de Stripe/GitHub) — fidelidade absoluta requer payloads reais
- Equipe quer baseline empírico antes de refactor — payloads reais > inputs sintéticos
1. Parsear argumentos
EDGE_FN_PATH=$(echo "$ARGUMENTS" | awk '{print $1}')
CAPTURE_DAYS=$(echo "$ARGUMENTS" | grep -oE -- '--days [0-9]+' | awk '{print $2}')
MAX_PAYLOADS=$(echo "$ARGUMENTS" | grep -oE -- '--max-payloads [0-9]+' | awk '{print $2}')
MODE=$(echo "$ARGUMENTS" | grep -oE -- '--mode[= ][^ ]+' | sed 's/--mode[= ]//')
SANITIZE_KEYS=$(echo "$ARGUMENTS" | grep -oE -- '--sanitize-keys [^ ]+' | awk '{print $2}')
[ -z "$CAPTURE_DAYS" ] && CAPTURE_DAYS=7
[ -z "$MAX_PAYLOADS" ] && MAX_PAYLOADS=100
[ -z "$MODE" ] && MODE="full"
if [ -z "$EDGE_FN_PATH" ]; then
echo "ERROR: edge_function_path obrigatório"
echo "Uso: /capturar-payloads <path> [opções]"
exit 1
fi
if [ ! -f "$EDGE_FN_PATH" ]; then
echo "ERROR: arquivo não encontrado: $EDGE_FN_PATH"
exit 1
fi
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.
- 2d ago First seen · 194 lines · 48 tokens per session scan A e6b83b45d8a3
capturar-payloads is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 6d ago), licensed MIT. It adds 48 tokens to every session and 2,196 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 2026-09-03.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.