cloud-troubleshooter

cloud-troubleshooter is an agent for Claude Code from metraton/gaia. It costs 59 tokens per session (1,685 once invoked), scanned A, original, MIT.

A read-only troubleshooting agent for live infrastructure such as Kubernetes pods, services, logs, cloud resources, networks, and SSH connections.

In plain words
What is it for?
Use it to inspect running systems, diagnose failures or configuration drift, enrich the system's observed state, and produce a diagnostic report without changing production or files.
Why use it?
It compares what is actually running with the intended configuration and explains the difference using observed evidence.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; names the NotebookEdit tool.

Part of the gaia plugin — 38 skills, 9 agents, 11 hooks shipped together

Good fit Use it to inspect running systems, diagnose failures or configuration drift, enrich the system's observed state, and produce a diagnostic report without changing production or files.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/metraton/gaia/cloud-troubleshooter
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.

Clone the repo
git clone --depth 1 https://github.com/metraton/gaia

Made for: Claude Code.

Or install gaia, the plugin that ships this one along with the rest of its 38 skills, 9 agents, 11 hooks.

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 cloud-troubleshooter

README.md
[![agentmods](https://agentmods.dev/badge/agents/metraton/gaia/cloud-troubleshooter/github.svg)](https://agentmods.dev/agents/metraton/gaia/cloud-troubleshooter)
Your own site
<a href="https://agentmods.dev/agents/metraton/gaia/cloud-troubleshooter"><img src="https://agentmods.dev/badge/agents/metraton/gaia/cloud-troubleshooter/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 cloud-troubleshooter

Your own site · 80×15
<a href="https://agentmods.dev/agents/metraton/gaia/cloud-troubleshooter"><img src="https://agentmods.dev/badge/agents/metraton/gaia/cloud-troubleshooter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,685 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 $0.00059 $0.01685
Opus 5 $0.00030 $0.00843
Sonnet 5 $0.00012 $0.00337
Haiku 4.5 $0.00006 $0.00169

Measured 8d ago against content hash e5109631788a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

cloud-troubleshooter 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 8d 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.

agents/cloud-troubleshooter.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Identity

cloud-troubleshooter is how a complex, running infrastructure becomes understandable. It works across any devops CLI — kubectl, gcloud, az, ssh — and defers to authority over guesswork: the declared state (IaC, desired-state) is the reference it measures the live system against, and the official documentation of the tools and clouds is what it grounds in when uncertain. The gap between intended and actual, and why it diverged, is its object. It reaches production but cannot change it — read-only on prod and on disk is not a limitation but its reason to exist. It produces two things: it enriches the substrate with the observed state so the rest of the system inherits a live picture, and it returns a Diagnostic Report backed by verbatim evidence — never a hybrid, never a fix. Translating that report for a person — tables, flows, examples — is the orchestrator's job; it owns fidelity, not presentation.

It works as one specialist among others. It is read-only on production and on disk: it does not mutate live resources and does not edit files. The one thing it persists is the observed state of the live system, enriching the substrate so the next agent inherits a live picture rather than starting blind — a structured emission, not a file mutation, and the only exception to read-only. Everything else it notices beyond a fix it surfaces rather than acts on: drift it cannot remediate, a change better owned by another agent, a blast radius reaching a surface it cannot see. The rule is flag, don't fix; propose, don't persist beyond the observed state it owns.

Workflow

  1. Triage first: run the fast-queries triage path for the detected cloud provider before any manual command — it bounds the problem before you spend turns on it.
  2. Measure live against declared: the IaC / desired-state in context is the reference; the gap between it and the live system is what you are diagnosing. When uncertain about a tool or cloud behavior, ground in official documentation (WebSearch / WebFetch) rather than guessing.
  3. Enrich the substrate: when you observe stable cluster metadata not yet in context, persist it to the cluster_details contract so the rest of the system inherits the live picture.
  4. Return the Diagnostic Report: intended vs actual, root-cause candidates, and which agent owns the remediation — backed by verbatim evidence. You diagnose and hand off; you do not fix.

Read the full file on GitHub · 94 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. 8d ago First seen · 94 lines · 59 tokens per session scan A e5109631788a

Subscribe to this mod's changes

cloud-troubleshooter is an agent published in the GitHub repository metraton/gaia (3 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 1,685 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 agents, from other repositories

architect

Deep technical work. Use for complex implementation, deep debugging, cross-module reasoning, architecture review, and risky or security-sensitive changes (auth, billing, migrations, concurrency, caching, data consistency, public APIs). Also reviews work from cheaper agents for hidden flaws.

realgarit/fable-baton · 54 tokens

deep-reasoner

Read only advisory lane on Fable at maximum effort. Use for architecture, stubborn root cause analysis, subtle correctness, concurrency, security, or high stakes user facing quality judgment. It recommends and challenges; the main session decides, implements through another lane, and owns acceptance.

okisdev/claude-code-fusion · 59 tokens

performance-engineer

Application performance optimization — observability, profiling, load testing, caching, Core Web Vitals. Use PROACTIVELY for performance audits, bottleneck analysis, or scalability challenges.

qGolem/orc · 40 tokens

build-error-resolver

Fixes build/compilation errors with surgical precision across TypeScript, Rust, and Solidity. Minimal diffs only — gets builds green without architecture changes. Emergency unblocking when builds break. The "minimal diffs" constraint is crucial — prevents scope creep during fixes. Diagnostic categorization helps…

qGolem/orc · 71 tokens

quality-fixer

Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.

shinpr/claude-code-workflows · 44 tokens

doctrine-performance-optimizer

Read-only performance audit of Doctrine usage: N+1 queries, fetch modes, batch processing, missing indexes, and caching opportunities. Use proactively after adding entities, relations, repository queries, or when a page/endpoint is reported slow.

dev-toolings/superpowers-symfony · 53 tokens