zihin-diagnostico

zihin-diagnostico is a skill for Claude Code from zihin-ai/zihin-mcp. It costs 61 tokens per session (918 once invoked), scanned A, original, MIT.

A decision guide for diagnosing Zihin agents, including wrong answers, failing tools, high cost or delay, stopped agents, and broken multi-agent setups. Zihin is the agent platform this guide is written for.

In plain words
What is it for?
Use it to inspect agent metrics, tool resolution, external MCP servers, authentication, caching, fallback models, sessions, and infrastructure problems.
Why use it?
It gives an investigation order based on the observed symptom instead of guessing which component is at fault. It helps connect errors, tool status, usage, cost, and response time to likely causes.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the zihin plugin — 6 skills, 1 MCP server shipped together

Good fit Use it to inspect agent metrics, tool resolution, external MCP servers, authentication, caching, fallback models, sessions, and infrastructure problems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zihin-ai/zihin-mcp/zihin-diagnostico
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 zihin-ai/zihin-mcp --skill zihin-diagnostico
Clone the repo
git clone --depth 1 https://github.com/zihin-ai/zihin-mcp

Made for: Claude Code.

Or install zihin, the plugin that ships this one along with the rest of its 6 skills, 1 MCP server.

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 zihin-diagnostico

README.md
[![agentmods](https://agentmods.dev/badge/skills/zihin-ai/zihin-mcp/zihin-diagnostico/github.svg)](https://agentmods.dev/skills/zihin-ai/zihin-mcp/zihin-diagnostico)
Your own site
<a href="https://agentmods.dev/skills/zihin-ai/zihin-mcp/zihin-diagnostico"><img src="https://agentmods.dev/badge/skills/zihin-ai/zihin-mcp/zihin-diagnostico/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.

agentmods 80×15 button for zihin-diagnostico

Your own site · 80×15
<a href="https://agentmods.dev/skills/zihin-ai/zihin-mcp/zihin-diagnostico"><img src="https://agentmods.dev/badge/skills/zihin-ai/zihin-mcp/zihin-diagnostico.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 918 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 $0.00061 $0.00918
Opus 5 $0.00030 $0.00459
Sonnet 5 $0.00012 $0.00184
Haiku 4.5 $0.00006 $0.00092

Measured 11d ago against content hash f2c095520c36, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

zihin-diagnostico 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 11d 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.

plugin/skills/zihin-diagnostico/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Diagnóstico de agentes

Comece SEMPRE pelo sintoma, não pela ferramenta. Ordem de investigação:

1. Visão geral do agente

get_agent_metrics (period 1d/7d/30d) — calls, errors, success_rate, tokens, custo, latência p50/p95 (agregado em SQL, sem cap de linhas), uso de tools e sessões recentes. Se tools.sample_truncated: true, os agregados de tools refletem a amostra das últimas 2000 chamadas, não o período inteiro.

Interpretação rápida:

  • errors altos + success_rate baixo → veja o passo 2 (tools) e 5 (infra).
  • custo alto → cheque modelo em uso (get_agent), fallback_chain e volume de sessões; considere teto (zihin://skills/governanca-e-operacao).
  • p95 alto → tools lentas (passo 2) ou modelo pesado.

2. Tools resolvendo?

list_agent_tools — cada tool aparece com status resolved ou error.

Assinatura clássica: usuário final recebe "Tool not found", mas a telemetria mostra a execução como sucesso → o MCP server externo está inativo/erro e as tools sumiram do runtime. Correção: test_mcp_server (ping + auth) → corrigir endpoint/credencial se preciso → invalidate_mcp_cache (cache tem TTL 5 min; invalidar força reload).

Para api_config/db_config com erro: validate_agent_schemas aponta o schema quebrado; lembre da regra endpoint.name == tool_definition.name.

3. Execução específica

get_execution_diagnostics — trace da execução: modelo usado, iterações, tool calls com input/output, erros por passo.

4. Multi-agente (orchestrator)

  • Com root_execution_id: get_execution_trace — árvore supervisor→subagentes com custo por nó.
  • ⚠️ Em sessão MULTI-TURNO o trace por execução pode não fechar a árvore — use get_session_agent_tree (linhagem por sessão-pai, cobre todos os turnos).
  • Galho falhou mas supervisor reportou sucesso? Confira na árvore os subagentes com erro (ex.: invoke_agent chamado com nome de tool em vez de UUID de agente → "Invalid uuid").

5. Erro é do agente ou da infra?

get_tenant_health — erros SEM agent_id (rate limit do provider, auth de chave LLM, infra), agrupados por código canônico. Se os erros do tenant sobem mas get_agent_metrics mostra errors=0, o problema é infra/provider — não mexa no agente.

Read the full file on GitHub · 55 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. 11d ago First seen · 55 lines · 61 tokens per session scan A f2c095520c36

Subscribe to this mod's changes

zihin-diagnostico is a skill published in the GitHub repository zihin-ai/zihin-mcp (0 stars, last pushed 10d ago), licensed MIT. It adds 61 tokens to every session and 918 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.

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