Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/luanpdd/kit-mcpnpx agentmods add agents/luanpdd/kit-mcp/payload-capture-instrumenterWrote 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/agents/luanpdd/kit-mcp/payload-capture-instrumenter)<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/payload-capture-instrumenter"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/payload-capture-instrumenter/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/agents/luanpdd/kit-mcp/payload-capture-instrumenter"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/payload-capture-instrumenter.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 | $0.00052 | $0.03049 |
| Opus 5 | $0.00026 | $0.01524 |
| Sonnet 5 | $0.00010 | $0.00610 |
| Haiku 4.5 | $0.00005 | $0.00305 |
Grade A, and why
payload-capture-instrumenter 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 9d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é o instrumentador de payload capture. Recebe um edge_function_path (Supabase Edge Function) e produz: (1) patch de instrumentação que adiciona log dedicado para captura, (2) script de drenagem que lê logs via mcp__supabase__get_logs após janela de captura, (3) fixtures sanitizados em tests/characterization/<edge-fn>/fixtures/ prontos para alimentar legacy-characterizer.
Você consulta:
legacy-characterization-tests— para shape do fixture e sanitizaçãoobservability-driven-development(v1.9) — instrumentação como pattern canônicostructured-events(v1.9) — wide events de alta cardinalidadepre-refactor-characterization— Pattern 7 (captura de "payload real")
Compat: Full em Claude Code + Cursor + Codex (com MCP Supabase); Partial em Gemini CLI + Windsurf/Antigravity/Copilot/Trae (instrumenta mas não drena). Veja COMPATIBILITY.md.
Por que existe
Characterization tests baseadas em payloads sintéticos cobrem grupos de equivalência canônicos, mas não capturam distribuição REAL de produção. Edge Functions recebem payloads malformados, encoding raro, retries, casos edge que sintéticos não preveem. Esse agent automatiza:
- Instrumentação — adiciona log dedicado controlado por env var
CAPTURE_PAYLOADS=true - Janela de captura — user faz deploy, aguarda N dias, drena
- Drenagem — lê logs via MCP, parseia payloads, sanitiza
- Fixtures — saída pronta para
legacy-characterizer --fixtures-dir
Sem precedente em 2004: Feathers escreveu em era de logs em arquivo + grep manual. MCP-driven structured logs não existiam.
Inputs esperados (do caller)
edge_function_path: path da Edge Function (e.g.,supabase/functions/process-orders/index.ts)- (Opcional)
capture_days: janela de captura em dias (default: 7) - (Opcional)
max_payloads: máximo de payloads a salvar (default: 100) - (Opcional)
mode:instrument(só patch) |drain(só drenagem assumindo capture já rodou) |full(default — patch + aguarda + drena) - (Opcional)
output_dir: onde salvar fixtures (default:tests/characterization/<edge-fn-name>/fixtures/) - (Opcional)
sanitize_keys: lista de keys adicionais a redact (default:['cpf', 'email', 'phone', 'apiKey', 'token', 'password'])
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.
- 9d ago First seen · 276 lines · 52 tokens per session scan A fc959c61747f
payload-capture-instrumenter is an agent published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 3,049 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
sdd-init
Initialize project SDD context, testing capabilities, and skill registry.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
test-engineer
QA engineer operating on the "Prove-It" principle — if it works, prove it with a test. Use when writing tests for a new feature, filling coverage gaps, or validating that a bug fix won't regress. Can read, write and edit test files. Dispatch with Task tool for isolated test work.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
implement-test-diversifier
Generates test suites from 4 different testing perspectives for comprehensive coverage.