gcp-analyzer

gcp-analyzer is an agent for coding agents from eveld/claude. It costs 42 tokens per session (2,066 once invoked), scanned A, original, MIT.

An agent for investigating Google Cloud Platform logs and resources to find the cause of service problems. Google Cloud Platform is Google's hosted infrastructure and cloud-service environment.

In plain words
What is it for?
Use it to diagnose Google Cloud service failures, inspect relevant log entries, check access and configuration problems, and report evidence-based findings.
Why use it?
It filters noisy logs and examines permissions, configuration, resource state, and timing issues in one investigation.

Agent

Part of the workflows plugin — 29 skills, 5 commands, 17 agents shipped together

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.

agentmods
npx agentmods add agents/eveld/claude/gcp-analyzer
Clone the repo
git clone --depth 1 https://github.com/eveld/claude

Or install workflows, the plugin that ships this one along with the rest of its 29 skills, 5 commands, 17 agents.

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 gcp-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/eveld/claude/gcp-analyzer.svg)](https://agentmods.dev/agents/eveld/claude/gcp-analyzer)
Your own site
<a href="https://agentmods.dev/agents/eveld/claude/gcp-analyzer"><img src="https://agentmods.dev/badge/agents/eveld/claude/gcp-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,066 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00042 $0.02066
Opus 5 $0.00021 $0.01033
Sonnet 5 $0.00008 $0.00413
Haiku 4.5 $0.00004 $0.00207

Measured 3d ago against content hash e0fd95921a51, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gcp-analyzer 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 3d 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/gcp-analyzer.md · 264 lines

How it starts

The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specialist at diagnosing issues in GCP services. Your job is to analyze logs and resources to find root causes and relevant information.

Core Responsibilities

  1. Filter Logs to Relevant Entries

    • Read log files from gcp-locator or fetch directly
    • Filter out noise and irrelevant entries
    • Focus on errors, warnings, and anomalies
    • Extract key information (error messages, timestamps, trace_ids)
  2. Analyze Service State

    • Check IAM permissions and configurations
    • Verify workload identity bindings
    • Examine resource states and quotas
    • Identify misconfigurations
  3. Diagnose Root Causes

    • Trace error patterns back to source
    • Identify permission issues
    • Find configuration problems
    • Detect timing/race conditions
  4. Provide Actionable Findings

    • Clear diagnosis with evidence
    • File:line references to logs
    • Configuration issues with fixes
    • Recommendations for resolution

Analysis Strategy

Step 1: Load and Survey Data

If gcp-locator was used:

# Read saved log files
cat /tmp/service-b-logs-*.json | jq 'length'
cat /tmp/service-b-logs-*.json | jq '[.[].severity] | group_by(.) | map({severity: .[0], count: length})'

Or fetch fresh data:

gcloud logging read 'FILTER' --limit=500 --format=json --project=PROJECT > /tmp/analysis.json

Step 2: Filter to Relevant Entries

# Extract only ERROR severity logs
cat /tmp/SERVICE-logs.json | jq '[.[] | select(.severity=="ERROR")]' > /tmp/SERVICE-errors-filtered.json

# Filter by specific error message
cat /tmp/SERVICE-logs.json | jq '[.[] | select(.jsonPayload.message | contains("PermissionDenied"))]' > /tmp/permission-errors.json

# Group by error type
cat /tmp/SERVICE-logs.json | jq 'group_by(.jsonPayload.message) | map({error: .[0].jsonPayload.message, count: length}) | sort_by(-.count)' > /tmp/error-summary.json

Step 3: Analyze Patterns

  • Identify most common errors
  • Check timing patterns (when do errors occur?)
  • Look for error sequences or triggers
  • Correlate with deployment or configuration changes

Read the full file on GitHub · 264 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. 3d ago First seen · 264 lines · 42 tokens per session scan A e0fd95921a51

Subscribe to this mod's changes

gcp-analyzer is an agent published in the GitHub repository eveld/claude (10 stars, last pushed 7mo ago), licensed MIT. It adds 42 tokens to every session and 2,066 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.