Guidelines to create/update a new mode for PostHog AI agent. Modes are a way to limit what tools, prompts, and prompt injections are applied and under what conditions. Achieve better results using your plan mode.

Fix speech-to-text errors and improve text clarity in dictated content related to GitHub Agentic Workflows

For fetching Rust/crate information, use this priority order:

Claude Code Bash tool patterns with hooks, automation, git workflows. Use for PreToolUse hooks, command chaining, CLI orchestration, custom commands, or encountering bash permissions, command failures, security guards, hook configurations.

Create a new underwriting agent (assets, credit, collateral) following established patterns. Use when implementing new agents, extending the system with new document analysis capabilities, or understanding how agents work.

Testing toolkit with assertions, mocks, and suites.

Standards for creating redteam plugins and graders. Use when creating new plugins, writing graders, or modifying attack templates.

Execute implementation tasks from design documents using markdown checkboxes. Use when (1) implementing features from feature-design-assistant output, (2) resuming interrupted work, (3) batch executing tasks. Triggers on 'start implementation', 'run tasks', 'resume'.

Automated privacy review for git repositories. Scans for sensitive data exposure including API keys, passwords, database credentials, and tokens. Use before pushing to public repositories or sharing code. Trigger by running 'python privacy_scan.py' on a git repository.

DDD設計原則チェッカー（AIDLC ドキュメントと実装コードの一貫性を検証）

Create GitHub issues with TDD principles and proper labels

Run goal-based evaluation tests for agents. Use when you need to verify an agent meets its goals, debug failing tests, or iterate on agent improvements based on test results.

Expert prompt engineering for creating effective prompts for Claude, GPT, and other LLMs. Use when writing system prompts, user prompts, few-shot examples, or optimizing existing prompts for better performance.

Expert guidance for proactive threat hunting. Use this when the user asks to "hunt" for threads, IOCs, or specific TTPs.

Create and maintain Claude Code agents/subagents (.claude/agents/*.md) with YAML frontmatter (name/description/tools/model/permissionMode/skills/hooks), least-privilege tool selection, delegation patterns (Task), context budgeting, and safety best practices.

Implement OAuth 2.0 authentication with GitHub and Microsoft Entra (Azure AD) in Cloudflare Workers and other edge environments. Covers provider-specific quirks, required headers, scope requirements, and token handling without MSAL. Use when: implementing GitHub OAuth, Microsoft/Azure AD authentication, handling OAuth callbacks, or troubleshooting 403 errors in OAuth flows.

Redis-backed SSE stream management with stream registry, heartbeat monitoring, completion store for terminal events, and automatic orphan cleanup via background guardian process.

Guide for using pagent - a PRD-to-code orchestration tool. Use when users ask how to use pagent, run agents, create PRDs, or transform requirements into code.

name: [invalid yaml with unclosed bracket