core-analysis-loop

core-analysis-loop is a skill for Claude Code, Codex from luanpdd/kit-mcp. It costs 53 tokens per session (3,604 once invoked), scanned A, original, MIT.

A method for investigating production problems with repeated, data-backed questions. It starts with the symptom, uses queries to test hypotheses, and records the investigation trail.

In plain words
What is it for?
Use it to investigate incidents, production errors, alerts, SLO burn, and unusual behavior by grouping failures by error type, customer, endpoint, or other useful fields.
Why use it?
It reduces guesswork and prevents engineers from jumping between dashboards without narrowing down the cause. Each query result guides the next step toward the root cause.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to investigate incidents, production errors, alerts, SLO burn, and unusual behavior by grouping failures by error type, customer, endpoint, or other useful fields.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/luanpdd/kit-mcp/core-analysis-loop
Install

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.

Any agent
npx skills add luanpdd/kit-mcp --skill core-analysis-loop
Clone the repo
git clone --depth 1 https://github.com/luanpdd/kit-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for core-analysis-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/luanpdd/kit-mcp/core-analysis-loop.svg)](https://agentmods.dev/skills/luanpdd/kit-mcp/core-analysis-loop)
Your own site
<a href="https://agentmods.dev/skills/luanpdd/kit-mcp/core-analysis-loop"><img src="https://agentmods.dev/badge/skills/luanpdd/kit-mcp/core-analysis-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,604 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00053 $0.03604
Opus 5 $0.00026 $0.01802
Sonnet 5 $0.00011 $0.00721
Haiku 4.5 $0.00005 $0.00360

Measured 4d ago against content hash 93e0dff18e9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

core-analysis-loop 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.

kit/skills/core-analysis-loop/SKILL.md · 354 lines

How it starts

The opening of the file, as written. The whole thing — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Observabilidade — Core Analysis Loop

Quando usar

LLM carrega esta skill ao investigar incidente, debugar comportamento de produção, ou validar hipótese sobre sistema. Trigger phrases:

  • "investigar incidente", "debugar produção"
  • "qual a causa raiz", "root cause analysis"
  • "core analysis loop"
  • "debug from first principles"
  • "alerta disparou — onde começo?"
  • "SLO burn — como descobrir o que quebrou?"

Regras absolutas

  • Hipóteses vêm de DADOS, não intuição — você não precisa conhecer o sistema. Comece com query SELECT * WHERE result.success = false LIMIT 10 e itere.
  • NUNCA chute "deve ser X" — toda hipótese é validada com query antes de aceitar. Se você está confiante mas não verificou, pare e verifique.
  • GROUP BY iterativo — sempre comece amplo e estreite. Erro 5xx → group by error.type → group by tenant_id → group by endpoint → root cause.
  • Cardinalidade alta é sua amiga — debug por user_id específico é só possível se você instrumentou alta cardinalidade (skill structured-events).
  • Documente a trilha — cada hipótese, query, resultado, próxima hipótese. incident-investigator salva em .planning/investigations/<id>.md.
  • Pare quando achar root cause — não vá além. "Tenant X em endpoint Y excedeu rate limit" é root cause; o "porquê tenant X excedeu" é um próximo loop separado.
  • Refute hipóteses agressivamente — busque evidência CONTRA, não A FAVOR. Bias de confirmação é o inimigo.
  • Não confie em dashboards — eles foram criados para problemas conhecidos. Você está investigando algo emergente.

As 4 fases do Core Analysis Loop

┌────────────────────────────────────────────────────────────────┐
│                                                                │
│   ┌──────────────────┐                                         │
│   │ 1. SINTOMA       │  Algo está errado (alerta, complaint,   │
│   │                  │  SLO burn, métrica anômala)             │
│   └────────┬─────────┘                                         │
│            ↓                                                   │
│   ┌──────────────────┐                                         │
│   │ 2. HIPÓTESE      │  Olhar para os DADOS (não intuição):    │
│   │    DE DADOS      │  query inicial ampla; ver o que aparece │
│   └────────┬─────────┘                                         │
│            ↓                                                   │
│   ┌──────────────────┐                                         │
│   │ 3. VALIDAÇÃO     │  Refinar com GROUP BY + WHERE.          │
│   │    POR QUERY     │  Tem evidência? Sim → próxima hipótese  │
│   └────────┬─────────┘  Não → volta para 2 com hipótese nova   │
│            ↓                                                   │
│   ┌──────────────────┐                                         │
│   │ 4. ITERAR        │  Foi para 2 (refinou hipótese)          │
│   │    OU PARAR      │  ou parar (achou root cause)            │
│   └──────────────────┘                                         │
│                                                                │
└────────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 354 lines

Changes

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.

  1. 4d ago First seen · 354 lines · 53 tokens per session scan A 93e0dff18e9e

Subscribe to this mod's changes

core-analysis-loop is a skill published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 3,604 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 2026-09-03.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens