Claude Code auto mode: a safer way to skip permissions
…Instead, we want it to judge what the agent did, not what the agent said. At this layer, stripping tool results is the primary prompt-injection defense, since tool outputs are where…
Search
All sources
xda-developers.com
35
anthropic.com
18
theregister.com
9
wired.com
6
developer.nvidia.com
5
pcworld.com
5
9to5mac.com
4
theverge.com
4
blog.cloudflare.com
3
engadget.com
2
tweakers.net
2
bleepingcomputer.com
2
I tested Claude Code against 3 open-source alternatives, and one came surprisingly close
…Quiz 8 Questions · Test Your Knowledge Vibe Coding From AI pair programmers to autonomous coding agents — how well do you know the tools reshaping software development? Origins Tools AI Models Culture Future…
Anthropic's design assistant now works better with its coding agent - Engadget
Anthropic's design assistant now works better with its coding agent Claude Design 🤝 Claude Code. By Igor Bonifacic June 17, 2026 3:00 pm EST Exactly two months after releasing a…
Xcode 26.3 unlocks the power of agentic coding
…With agentic coding, Xcode can work with greater autonomy toward a developer’s goals — from breaking down tasks to making decisions based on the project architecture and using built-in tools. Expanding…
Discussions and forums
Arch-Decision – A multi-agent architecture tool for Claude Code
Arch-Decision – A multi-agent architecture tool for Claude Code
3
Show HN: Agentcad – Claude Code's favorite CAD tool
Think of it as CAD software for your agent. Allows your agent to "see" what it's designing and iterate on it before it hands it back to you.
1
Show HN: Lazarus, a coding agent for long-horizon tasks
I have been interested in long-horizon coding tasks for a while, especially with benchmarks like FrontierSWE, where even the best coding agents like Codex and Claude Code struggle to complete tasks.These agents come with…
1
Show HN: I threw away my analytics dashboard and replaced it with 42 MCP tools
Back in October, I built a web analytics tool. It had two distinguishing features: it was cheap, and it had a weekly AI email summary so you wouldn't have to check your dashboards. Turned out that cheap made no differenc…
3
4
Show HN: Jsonl-tools – secure paste bin for agent run traces
Hey, I've built a small tool and OSS repo allowing users to view/transform/share JSONL traces.There's also a CLI you can use to upload traces from sandboxes and/or share them with Claude/Codex for analysis.Zero Knowledge…
3
I paired NotebookLM with Claude's browser extension, and it changed how I use both tools
…This meant my workflow was largely three tools deep: NotebookLM for synthesis, Claude for thinking through sources and finding new ones, and an agentic browser just for the automation. I was stuck…
Building Effective AI Agents
…Prompt engineering your tools No matter which agentic system you're building, tools will likely be an important part of your agent. Tools enable Claude to interact with external services and APIs…
Anthropic acquires Stainless
…Hundreds of companies rely on Stainless to generate SDKs, CLIs, and MCP servers—the libraries, command-line tools, and connectors that let developers and agents use an API. Stainless turns an API…
Measuring AI agent autonomy in practice
…Because we characterize agents as AI systems that use tools, we can analyze individual tool calls as the building blocks of agent behavior. To understand what agents are doing in the world…
These open-source tools do what Claude charges for, and some do it better
…your own machine, Claude Code isn't really the best tool for that. OpenCode is. It's an open-source coding agent that does basically everything Claude Code does (editing files, running…
How we contain Claude across products
…The agent is attacked through external vectors such as tools, files, or network access. This category includes both prompt injection and conventional attacks on the agent's runtime, orchestration layer, or proxy…