AutoGineer
Generated banner for Prod Logs Health Check
Generated logo for Prod Logs Health Check

Prod Logs Health Check

Seth HobsonCommunityCreated by SharrmavishalDistributed by Seth Hobson

  • Subagent
  • Review and audit
  • Cloud and DevOps
  • MIT
  • No issues found
Download ZIP

From the author

Pulls recent production logs filtered for errors, warnings, and anomalies. Use after any deploy, after a load test, or any time you suspect something is going wrong. Treats logs as the only acceptable primary source for incident analysis — never infers from dashboards or script stdout alone.
— the description by Sharrmavishal

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This skill provides a rigorous framework for investigating production incidents by prioritizing raw log data over dashboard visualizations or standard output. It mandates a structured process for retrieving, filtering, and deduplicating log entries to ensure that incident reports are based on actual system behavior rather than potentially misleading UI summaries or incomplete metrics.

What it does

  • Retrieves raw production logs from specified sources.
  • Filters log data to isolate errors, exceptions, timeouts, and retries.
  • Deduplicates log entries to distinguish between single failures and repeated retries.
  • Requires explicit disclosure of log availability and potential data gaps.
  • Groups identified issues by root cause with representative log excerpts.

When to use it

  • Immediately following a production deployment.
  • After executing a load test to verify system stability.
  • When investigating suspected production incidents or performance anomalies.
  • Whenever dashboard data requires verification against source logs.

Advantages

  • Reduces reliance on potentially misleading dashboard abstractions.
  • Ensures incident analysis is grounded in primary source data.
  • Provides a clear methodology for distinguishing unique failures from retry noise.
  • Increases transparency by documenting the scope and limitations of the log analysis.

Usage examples

“Run a health check on the production logs for the last hour.”
The agent retrieves the logs, filters for errors and warnings, deduplicates retries, and provides a summary of unique root causes found in the logs.
“Investigate why the checkout service is failing after the latest deployment.”
The agent pulls the relevant logs, identifies specific stack traces or timeout markers, and reports the distinct failure count versus total occurrences.

Install

  1. Download the subagent as a ZIP:

    https://mp-staging.autogineer.com/agent-skills/wshobson/prod-logs-health-check/download

  2. Extract the subagent file into .claude/agents in your project (use ~/.claude/agents for every project):

    mkdir -p .claude/agents && unzip -j prod-logs-health-check.zip 'prod-logs-health-check/prod-logs-health-check.md' -d .claude/agents

  3. Keep the LICENSE and ATTRIBUTION.md files from the ZIP with your copy.

Documentation by Sharrmavishal

You are this project's production-log health checker. Pull real logs and report what's actually happening, not what a dashboard claims is happening.

Template note: point {{LOG_QUERY}} at the project's real log source (cloud logging, journald, a file, kubectl logs, etc.).

Core rule

Never analyze a production incident from UI data or script stdout alone. Dashboards paginate (you see the last N events, not all), and test harness timing is often wrong for async work.

If logs are not available or you didn't check them, say so explicitly before presenting any finding. Do not present inference as fact.

Steps

1: Pull recent logs
{{LOG_QUERY}}
2: Filter for signal

Grep for:

  • Errors, exceptions, stack traces

  • Timeouts, retries

  • Project-specific failure markers: {{PROJECT_SPECIFIC_MARKERS}}

3: Distinguish unique failures from retries

The same job id appearing 5 times is one failure retried, not five failures. Cross-reference ids before reporting a count.

What to report

  • Time window and how many log lines you pulled (so truncation is visible).

  • Errors grouped by root cause, with a representative excerpt each.

  • Distinct-failure count vs. total occurrences.

  • Anything you could not confirm from logs, stated as an open gap.

Files

Requirements and compatibility

Written for: Claude Code

Works with: Claude Code

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Created by
Sharrmavishal
Publisher
Seth Hobson (Community)
Distributed by
Seth Hobson
Source
wshobson/agents · plugins/operating-kit/agents/prod-logs-health-check.md · commit 4bde316
Licence
MIT License (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Sharrmavishal or Seth Hobson.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download prod-logs-health-check.zip