A developer built a proxy that filters unused tool definitions from requests sent to Claude Code, cutting their monthly API bill from $200 to $50. The proxy classifies user messages into categories an…
A developer built a token fuel gauge for Claude Code to monitor usage in real time, preventing quality degradation from hitting the 5-hour block limit. The system combines ccusage and cost logs into a…
Seedeep, a new open-source tool by developer duqaXxX, visualizes Claude Code's internal operations in real time, showing every model call, subagent, and token cost during a session. Analyzing 1,830 re…
SkillPreflight, a new open-source command-line tool, scores AI agent skills on a 100-point scale across security, permission restraint, token efficiency, lightweight footprint, maintainability, reliab…
Cameron Smith, a Brisbane-based product manager and head of ecommerce at Bloody Good Tests, released Ambient Context on August 25th, an open-source macOS app that records focused-window text into loca…
Cybercriminals are using fake OpenAI Codex download pages in sponsored Google search results to trick Mac developers into running malware disguised as installation commands, according to researchers a…
Chinese state-backed hacking groups have more than doubled their attacks since using AI models like DeepSeek to write exploit code and scan networks, according to Taiwanese security firm TeamT5. Hacke…
AI desktop pets are evolving from nostalgic digital companions into visual proxies for autonomous agents, with Tencent's Hunyuan Hy3 large model enabling generative intelligence and memory. These new …
A developer running a one-person AI company reported that a crypto trading bot logged a fresh decision every five minutes for over an hour while the price it was deciding on never moved. The bot's API…
Andreas Wolf's T3DD26 talk 'Before You Let AI Touch Your Code' argues that AI amplifies existing software development practices, so teams must build a 'harness' of QA, team culture, and specs before a…
HOL Guard, a free open-source tool, acts as an antivirus for AI agents by pausing risky actions and asking for user approval, with checks under 50 milliseconds and no internet required. It installs in…
Anthropic, the AI company behind Claude, has demonstrated a lack of understanding of software engineering, as evidenced by issues on its Claude status page and Claude Code GitHub issues page. Despite …
Anthropic's Claude Code team member Thariq Shihipar published the ELI5 skill, which generates jargon-free, diagram-heavy HTML explainers for any topic via the `/eli5` command. The skill, distributed t…
Safer-dependencies, a new security layer for Claude Code, automatically audits and blocks risky dependencies—including CVEs, typosquats, abandoned packages, and version-age issues—across npm, PyPI, Ru…
Ambient Context, a macOS menu bar app that records the text of the focused window via the accessibility API into plain Markdown files for LLM consumption, has been released as an early unsigned build …
Conductor Cloud, an orchestration layer for external coding agents, differs from Replit, a full development and deployment environment with an integrated agent layer, according to a comparison by Ryan…
A developer has built verdict, an MCP server that gives coding agents structured, sandboxed test feedback, replacing raw pytest output with concise typed verdicts. The tool runs tests in ephemeral con…
A developer highlights the use of 'Skills' as a solution to repetitive prompting in AI coding agents, describing a folder-based standard that works across tools like Claude Code, Cursor, and Copilot. …
Gitwhy, a new open-source tool in beta, automatically records AI provenance for every git commit by installing a post-commit hook that captures environment variables such as $CLAUDE_CODE_MODEL, $COPIL…
Developer imshaikot released render-visual-skill, an agent skill that lets coding agents generate diagrams, presentation slides, social cards, code snippets, and device mockups as HTML/SVG rendered to…