Log Reader — DevOps & Infrastructure agent for Claude Code
Use proactively to read logs, test output, stack traces, CI/CD pipeline output, kubectl/helm/argocd output, PHPUnit/Behat/Playwright results.
How to install Log Reader
Installs to ~/.claude/agents/vanssata-claude-agentic-sdlc-module-log-reader.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/vanssata/claude-agentic-sdlc-module/HEAD/agents/log-reader.md -o ~/.claude/agents/vanssata-claude-agentic-sdlc-module-log-reader.md Restart Claude Code, or start a new session, for it to be picked up.
What Log Reader does
name: log-reader description: Use proactively to read logs, test output, stack traces, CI/CD pipeline output, kubectl/helm/argocd output, PHPUnit/Behat/Playwright results. Returns only the relevant errors and a short diagnosis, never the raw output. tools: Read, Grep, Glob, Bash disallowedTools: Write, Edit model: sonnet effort: medium color: cyan
You read logs and command output so the main agent does not have to.
For every task return exactly:
- Failing component (service, pod, test
Alternatives in DevOps & Infrastructure
- Shep File Relocator — Moves ONE file from one clean-architecture layer to another (typically a pure helper from infrastructure/ → do 247 ★
- Deploy Checker — Validate everything before deployment 80 ★
- AWS Log Reader — Use this agent when you need to analyze, summarize, or extract information from AWS logs (CloudWatch, S3 acces 28 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Example CI Investigator
Classify a concrete CI failure or review-check discrepancy from logs and workflow files. Read-only diagnosis;
Deploy Runner
Runs a long-lived AgentCore Hub deploy script (5–15 min) and reports a short summary. Use this from the /agent
Helm Debugger
MUST BE USED PROACTIVELY for any Helm chart or Kubernetes debugging. Validates charts, diagnoses deployment fa
Deploy QA
Post-deploy verification in a real browser using the Playwright MCP tools - smoke tests of key journeys, conso
Staging Log Verifier
Use this agent to fetch staging service logs for a deploy window, scan them for errors, warnings, and stack tr
Grind
Runs multi-step shell work — fleet/ssh sweeps, build+deploy, test-harness runs, service polls. Use when the ne
Related Skills
Kubectl Guard For Claude Code
A PreToolUse hook for Claude Code that restricts what an AI agent can do with kubectl and helm through the Bas
Select Representative Traces
GRACE Phase 2 - Diagnosis summarization, high-priority component selection, representative trace selection
Iso 24495 Skill
ISO 24495-1 plain language rules as a Claude Code skill — bilingual: English + Traditional Chinese (繁體中文淺白改寫).