Skill Claude CodeCodex
Standards for creating redteam plugins and graders. Use when creating new plugins, writing graders, or modifying attack templates.
Skill Claude CodeCodex
Standards for creating redteam plugins and graders. Use when creating new plugins, writing graders, or modifying attack templates.
Skill Claude CodeCodex
URL search param and hash state management. Use when adding or modifying URL search params, working with useSearchParams, setSearchParams, useSearchParamState, or navigate() with query strings or hash fragments, or fixing browser back/forward button issues.
Plugin Claude Code
Plugin marketplace listing 1 plugin: promptfoo.
Hook Claude Code
Runs before the agent uses a tool for Bash tool calls, running an inline shell check. From promptfoo/promptfoo.
Hook Claude Code
Runs after a tool call finishes for Edit and Write tool calls, running an inline shell check. From promptfoo/promptfoo.
Settings file Claude Code
Agent settings declaring 2 hook events (PreToolUse, PostToolUse).
Skill Claude CodeCodex
Write, refine, run, and QA promptfoo evaluation suites: promptfooconfig.yaml, prompts, providers, vars, tests, assertions, model-graded rubrics, transforms, datasets, exports, and CI gates. Use for non-redteam eval coverage, regression tests, or new eval matrices. Do not use for adversarial redteam plugin or strategy…
Instructions file CodexOpenCode
Instructions for promptfoo/promptfoo, covering agents.md, project overview, project structure, build commands and core commands.
Instructions file
Instructions for promptfoo/promptfoo, a project described as: Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.
Agent
Guidance for AI agents editing the reusable docs in docs/agents/.
Agent
These notes track the planned Promptfoo integration for the Codex app-server protocol. They are intentionally implementation-facing: keep them current as the provider, docs, examples, and verification expand.
Agent
This document summarizes how promptfoo should think about coding-agent providers, what has been implemented so far, and what should come next. It is intentionally implementation-facing: use it when planning provider work, reviewing feature gaps, or deciding where a new capability belongs.
Agent
This codebase uses Drizzle ORM with SQLite. All database queries must use parameterized SQL so user-controlled input never changes query structure.
Agent
Use --target minor for safe minor/patch updates only.
Agent
Agent "git-workflow" from promptfoo/promptfoo, covering git workflow, critical rules, commit policy, standard workflow and 1. create feature branch.
Agent
Always use the logger with an object as the second parameter.
Agent
PR titles follow Conventional Commits format. They become squash-merge commit messages and changelog entries.
Agent
For Python providers, prompts, assertions, and scripts.
Plugin Claude Code
Checks that projects follow standard conventions.
Skill Claude CodeCodex
Checks that a project follows standard conventions.
Skill Claude CodeCodex
Use this skill when asked to review authentication code for security issues.
Skill Claude CodeCodex
Reviews code for bugs, security issues, and best practices.
Skill Claude CodeCodex
Inspect the discount policy fixture with a repeatable review checklist and helper script.
Skill Claude CodeCodex
Use this skill when the user explicitly asks to use token-skill and wants the special token.