Agent Roast
MCP serverOffline review that flags agent changes which weaken tests, assertions or CI
Runs locally- Open source
- 4 Hacker News points
- Developer tools
Offline review that flags agent changes which weaken tests, assertions or CI
Runs locally
Automatically discover CI/CD and automation skills when working with GitHub Actions, Jenkins, GitLab CI, pipelines, continuous integration,

Automatically discover cloud, infrastructure, deployment, and container skills when working with AWS, GCP, Azure, Docker, Kubernetes, Terraf

Use when the user has concrete failing cases in code or a guardrail/classifier/filter/prompt/API they own — a red-team failure catalogue OR

Review a Buildable prototype against its app spec and quality rubric for build correctness, workflow completeness, state coverage, accessibi
One MCP gateway for all your MCP servers, with code mode, permissions and audit
Not checked yetColor tools for AI agents: contrast fixes, Material 3 themes, palettes and CSS matching
Runs locallyWrite, check and dry-run Lugh agent programs with policy, budgets and approvals
Runs locallyMessaging and advisory locks so several Claude Code sessions can share one repository
Runs locally
Pulls transcripts, chapters and metadata from videos so agents can read and cite them
Runs locallyRun WordPress hosting from an assistant: backups, staging, updates, PHP and domains
Open-source relay that lets your AI agent ask people you know, with human approval
Not checked yetRead-only audit of agent skills in one workspace, plus a package manager for them
Runs locallySupport chat that lets people search your docs and file bugs from Claude Code or Cursor
Not checked yetRead-only access to a Git-based ledger of decisions and which code changes touch them
Runs locally
Search and read Flood's React components, recipes, tokens and design guidance
Ring, mute and set the volume of a real WiFi siren light from your AI agent
Not checked yetOffline, version-exact docs for the OGE UI Angular and React components
Runs locallyRun WCAG 2.2 accessibility audits and vision simulations on any URL from an agent
Runs locallyShared, audited git, test and workflow tools for MCP coding apps that never push
Runs locallySearches your own code, PDFs and Office files and returns exact source citations
Runs locallyA design library for coding agents: 738 guidance items, rule checks and project memory
Builds Draw.io flowcharts with attached connectors from structured node lists
Runs locallyEncodes Mermaid diagrams into share tokens and recovers the source from them
Runs locallyDead code, duplication and complexity analysis for TypeScript and JavaScript repos
Runs locally78 tools for GitFlic merge requests, issues, releases, packages and CI
Runs locallyGives MCP clients access to your PlatypusDB database connections, scoped per agent
Runs locallyDeploy and manage apps, Postgres, auth, storage and domains on Helm7 from an AI agent
A lockfile for MCP tools: blocks changed tool definitions and signs a receipt per call
Runs locallyConnects ChatGPT or the Frontman editor to a WordPress site to edit content with AI