Log Reviewer — Security agent for Claude Code
Audit roku-log usage in a JellyRock BS/BRS file or function.
How to install Log Reviewer
Installs to ~/.claude/agents/jellyrock-jellyrock-log-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/jellyrock/jellyrock/HEAD/.claude/agents/log-reviewer.md -o ~/.claude/agents/jellyrock-jellyrock-log-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Log Reviewer does
name: log-reviewer description: "Audit roku-log usage in a JellyRock BS/BRS file or function. Defaults to AUDIT-ONLY: lists logging gaps without proposing additions. When explicitly asked to propose fixes, only proposes critical-error-path additions (silent error paths, untracked state changes that would make a class of bug invisible). NEVER blanket-adds entry-logs, variable-trace logs, or function-trace style logging — that anti-pattern is hard-prohibited. Use when you want a quick read on
Alternatives in Security
- Impeccable Agent — Autonomous executor for non-interactive impeccable commands 530 ★
- Ark Security Patcher — Fix security vulnerabilities in Ark by researching CVEs, analyzing impact, proposing mitigations, implementing 419 ★
- Code Reviewer Quality — Use this agent as the second stage of a code review, after spec compliance is confirmed — evaluating code qual 186 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
SecOps Orchestrator
Orchestrates LibreSecOps Grok skills for defensive security — threat model, defaults, deps, secrets, access, l
Observability Logging
Garante uso consistente de Serilog estruturado — CorrelationId, níveis por camada, separação entre log e audit
Observability Specialist
Observability specialist owning audit-log shape, telemetry surfaces, metrics emission, the SLSA provenance + s
Audit Drift
Detects SEO regressions by comparing current crawl against a stored baseline using 17 comparison rules at 3 se
Gsc Overview
GSC site overview agent. Resolves permission level, lists sitemaps and their error/warning counts, probes the
Security Analyst
Security vulnerability analyst for authentication, authorization, secrets, input validation. Use proactively w
Related Skills
Update Rules
Interactively propose ALLOW/ASK rule additions for agent-sentinel from recent LLM_JUDGE log entries
Catalog Add
Research one stack, verify the candidates, and propose the additions as a pull request
Knowledge Ops
Use when explicitly asked to add, edit, delete, list, or sync indexed knowledge sources for Lumina through the