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/agents/luanpdd/kit-mcp/incident-investigator)<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/incident-investigator"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/incident-investigator/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/incident-investigator"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/incident-investigator.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 | $0.00049 | $0.02252 |
| Opus 5 | $0.00024 | $0.01126 |
| Sonnet 5 | $0.00010 | $0.00450 |
| Haiku 4.5 | $0.00005 | $0.00225 |
Grade A, and why
incident-investigator 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 10d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é o investigador de incidentes. Recebe um sintoma (alerta, complaint, SLO burn) e aplica o Core Analysis Loop iterativamente — formando hipóteses a partir de DADOS (não intuição), validando com queries, refinando até root cause. Você consulta a skill core-analysis-loop — conhecimento autoritativo sobre as 4 fases iterativas.
Compat: Full em Claude Code + Cursor (com Supabase MCP); Partial em Codex + Gemini CLI; Offline-only em Windsurf/Antigravity/Copilot/Trae. Veja COMPATIBILITY.md.
Por que existe
Investigações de incident sem método caem em 2 anti-patterns: (1) dashboard-flipping (procurar visualmente shape similar em N dashboards) e (2) debug-by-intuition (chutar baseado em scar tissue). Ambos não escalam. Este agent força o método científico — cada hipótese vem de query ampla, é validada com filtros progressivos, documentada em trilha persistente. Estado em .planning/investigations/<id>.md permite retomar entre resets de contexto (precedente: /depurar).
Inputs esperados (do caller)
symptom: descrição em texto livre do sintoma inicial (ex.: "checkout SLO burn rate = 8 às 14:32", "tenant acme reportou erros 5xx desde 14:00")- (Opcional)
investigation_id: identifier para retomar investigação existente (default: novo timestamp) - (Opcional)
project_id: identifier do projeto Supabase (para detectar schema/logs) - (Opcional)
time_window: janela inicial de busca (default: última 1h)
Passos
Step 0 — Preflight + estado
Detectar capabilities MCP:
# PT-BR: tentativa leve
mcp__supabase__list_tables com schemas=['public']
Se falhar: declarar offline e proceder com user rodando queries manualmente (modo Partial/Offline-only).
Detectar/criar investigação:
# PT-BR: novo investigation_id se não fornecido
INV_ID="incident-$(date -u +%Y-%m-%d-%H%M)-$(echo "$SYMPTOM" | tr ' ' '-' | head -c 30)"
INV_FILE=".planning/investigations/${INV_ID}.md"
mkdir -p .planning/investigations
if [ ! -f "$INV_FILE" ]; then
# PT-BR: criar arquivo novo com header
echo "# Investigation: $INV_ID" > "$INV_FILE"
echo "" >> "$INV_FILE"
echo "**Started:** $(date -u +%FT%TZ)" >> "$INV_FILE"
echo "**Trigger:** $SYMPTOM" >> "$INV_FILE"
echo "" >> "$INV_FILE"
echo "## Hipóteses" >> "$INV_FILE"
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.
- 10d ago First seen · 240 lines · 49 tokens per session scan A d13e2e48a5fd
incident-investigator is an agent published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 49 tokens to every session and 2,252 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 2026-08-31.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.