Guidance for explicitly requested new tests and for updating or reviewing existing tests in the Remotion repository.

Implement or review a Remotion 5 breaking change while the v4 and v5 release lines still share code. Use when v4 behavior and public types must remain compatible on main, but flipping the central v5 flag should activate a new runtime behavior, default, or TypeScript API.

Capture and analyze Remotion Studio React render profiles through development-only WebMCP tools. Use when diagnosing unnecessary re-renders, slow commits, frame-reactive component trees, or when comparing render performance before and after a change.

Rebuild, install, and reload the private Remotion Canvas Capture unpacked Chrome extension. Use when the extension needs to be restored after a Codex worktree was deleted, rebuilt after source changes, moved to its durable install directory, or reloaded in Chrome or Chrome Canary.

Use when releasing the Cline VS Code extension — stable (standalone SDK build of main via ext-vscode-publish), nightly (ext-vscode-publish-nightly, manual dispatch), or an emergency legacy-branch hotfix (ext-vscode-publish-legacy). Guides version selection, changelog, workflow dispatch, environment approvals, tagging, post-publish verification, and the remaining retirement of the finished A/B rollout machinery.

Use for Codex models/pricing, scheduled tasks, skills, settings, setup, troubleshooting, customization, automations, and self-knowledge—including 'you,' 'your,' 'this app,' or 'this coding agent' when they refer to Codex—and for OpenAI APIs/products and ChatGPT Work. Also use for model choice/migration, prompting, SDKs, Responses, Realtime, agents, evals, and Chat/Work/Codex comparisons. Do not use for generic app/software tasks that merely mention Codex.

Retrieve the pre-aggregated digest of World Monitor's curated news feeds, bucketed by category, with per-article threat classification and alert flags. Use when the user asks what's in the news right now, wants headlines by topic, or needs a current-events sweep.

Model oil or gas supply shock exposure for a country and chokepoint. Use when the user asks how an energy disruption could affect fuel supply, strategic cover, or product deficits.

Triage WorldMonitor Sentry issues — classify unresolved events as noise, already-fixed, product bugs, or needs-human; optionally ship a tested fix. Use when the user says triage Sentry, pastes a WORLDMONITOR-* ID or sentry.io URL, or asks to investigate production errors.

Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.

Generate images, video, and audio via diffusion workflows.

Make a verified AI presenter video from script + image.

ASCII art: pyfiglet, cowsay, boxes, image-to-ascii.

Plan-in-code fan-outs, adversarial verification, waves.

Creates devcontainers with Claude Code, language-specific tooling (Python/Node/Rust/Go), and persistent volumes. Use when adding devcontainer support to a project, setting up isolated development environments, or configuring sandboxed Claude Code workspaces.

Diagnose and fix Claude in Chrome MCP extension connectivity issues. Use when mcp__claude-in-chrome__* tools fail, return "Browser extension is not connected", or behave erratically.

Searches and explores Burp Suite project files (.burp) from the command line. Use when searching response headers or bodies with regex patterns, extracting security audit findings, dumping proxy history or site map data, or analyzing HTTP traffic captured in a Burp project.

Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct expression injection, dangerous sandbox configurations, and wildcard user allowlists. Use when reviewing workflow files that invoke AI coding agents, auditing CI/CD pipeline security for prompt injection risks, or evaluating agentic action configurations.

在重要任务上运行完整世界模型闭环的执行协议——恢复持久状态→建立竞争模型→显式预测→真实观察→修订模型→主动取证→决策→持久化。由 AGENTS.md World Model Gate 判 OFF/CORE/FULL 后加载；用于多步、高风险、跨会话、存在竞争解释或需要持久世界模型的真实任务，不用于简单一次性任务。

Overview of how to analyze data in a Rill project