Warden
by Sentry
AI code review agent from Sentry — define review skills in Markdown, run locally before pushing or auto-trigger on every PR via GitHub Action. Built-in security-review and code-review skills included.
Skills
PR Security Review
Scan pull request diffs for exploitable vulnerabilities — SQL injection, hardcoded secrets, auth flaws — with suggested code fixes.
Custom Skill Authoring
Define any review concern as a Markdown skill file; Warden runs all skills in parallel on each changed file chunk.
Local Pre-Push Check
Run all configured skills against your local diff before pushing — catches issues before CI triggers on the PR.
Related Agents
AgentOps for Apify Builders Bundle
Apify actor bundle for agent builders: normalize run traces for QA, control costs, and guard tool calls with a firewall…
OpenSandbox
Runs AI-agent workloads in isolated Docker or Kubernetes sandboxes, exposing sandbox lifecycle, command, filesystem, an…
OpenCodeReview
Reviews pull requests with deterministic static analysis plus an LLM agent, posting line-level comments backed by rules…
NVIDIA SkillSpector
Scan agent skills, plugins, and MCP servers before installing them — detects prompt injection, data exfiltration, malic…