Break your AI before they do. Join Discord: https://discord.gg/8A6mFckxZ
Skill Claude CodeCodex
Use when connecting Codex, Claude Code, OpenCode, OpenClaw, coding-agent CLIs, agent gateways, workspaces, sandbox policies, provider files, or trace capture to Promptbeat as an evaluation target.
Skill Claude CodeCodex
Use when Promptbeat validate, config inspect, generate, run, eval, report, provider-file loading, environment variables, workingdir, promptfoo, or coding-agent runtime execution fails.
Skill Claude CodeCodex
Use when a user wants to start using a downloaded Promptbeat full package, connect an HTTP agent, LLM, coding agent, choose an evaluation path, run a first red-team test, or asks where to begin.
Skill Claude CodeCodex
Use when a user has a Promptbeat config or generated promptfoo config and wants to validate, generate a few cases, run a first small evaluation, inspect artifacts, or create a report.
Skill Claude CodeCodex
Use when a user needs help choosing Promptbeat attack goals, risk types, scenarios, seed files, dataset subscriptions, compliance profiles, or a small smoke-test scope.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: