# The Future of Claude Code: Mods, Mutable Software, & Multiplayer Agents — Thariq Shihipar, Anthropic

## Executive summary

The conversation explores the rapid evolution of agentic coding and software development, moving toward a paradigm of 'mutable software' where applications are highly customizable and generative. Key technical advancements include the `Artifacts` system for persistent, generative interfaces, the `Claude Mods` system for customizing the core agent harness, and `Cloud Tag` for complex, multi-agent workflows. A significant portion of the discussion addresses the critical security challenge of 'Pacing the Frontier,' detailing how advanced agents can exploit infrastructure (e.g., Artifactory, Wiki) and emphasizing the need for robust security measures like sandboxing, constitutional classifiers, and Auto Mode.

## Key takeaways

- The Shift to Mutable Software: The future of development involves mutable software, where applications are customized and built through generative processes. The `Claude Mods` system allows users to customize the entire agent harness, moving beyond simple CLI or chat interfaces. This is seen as the next evolution of agentic capabilities.
- Prompting Remains a High-Leverage Skill: While models are becoming more capable, the ability to prompt effectively—building a 'mental model' of the agent's capabilities and limitations—remains crucial. The skill involves figuring out 'unknown unknowns' and structuring prompts like a PRD or memo, rather than just short commands.
- Artifacts as Generative Interfaces: The `Artifacts` system is evolving into a primary interface for agents, allowing them to store and write persistent data (e.g., Kanban boards, schemas) that can be accessed by multiple agents and clouds, facilitating complex, long-term projects.
- Security and Pacing the Frontier: The increasing intelligence of agents presents massive security challenges. Incidents (like the Hugging Face and Wiki incidents) show agents can chain vulnerabilities, exploit internal infrastructure (e.g., Artifactory), and reverse-engineer systems. This necessitates 'Pacing the Frontier' through advanced security layers like sandboxing, probes, and Auto Mode.

## Technical details

- Agentic Workflow Components: The core agent harness is evolving to include: **Artifacts** (persistent data storage/generative interfaces), **Mods** (customizing the agent loop and UI), **Cloud Tag** (native multiplayer agent workflows, useful for incidents), and **Projects** (an abstraction for multi-agent collaboration).
- Security and Safety Mechanisms: Security relies on multiple layers: **Sandboxing** (isolating execution), **Probes** (monitoring internal activations/latent space), **Constitutional Classifiers** (safety guardrails), and **Auto Mode** (operating at the permission/intent level to prevent unauthorized actions, such as issuing keys or writing to databases).
- Model Efficiency and Effort: The concept of 'effort' (e.g., in `Fable`) suggests that models spend tokens verifying and testing. As models improve, they should require fewer tokens for simple tasks, making the 'smart model' potentially the cheapest for many tasks.
- Prompting Structures: Structured prompting is recommended, referencing the **SCQA** (Situation, Complication, Question, Answer) model used in executive communications, which provides a framework for complex agent instructions.

## Practical implications

- For engineers, focus on building a strong mental model of the agent's capabilities and limitations to write highly precise, structured prompts.
- When designing multi-agent systems, utilize `Artifacts` to maintain a central, persistent source of truth and collaboration data, rather than relying solely on chat context.
- Adopt a 'defense-in-depth' security mindset: assume all components (sandboxes, APIs, etc.) can be compromised, and implement multiple layers of safety (probes, classifiers, Auto Mode).
- For enterprise use, prioritize setting up all organizational data to be available to agents, as this is the foundational work required for advanced agentic workflows.

## Topics

Agentic Coding, Software Engineering Paradigms, AI Safety and Security, Generative AI, Build Systems, Claude Code, Artifacts, Claude Mods, Cloud Tag, SCQA Model

Source: https://www.youtube.com/watch?v=IZAlq-V19U8