Skillsaw: Lints the files that steer your AI coding agents
Skillsaw is a new linting tool designed for AI coding agents. It checks configuration files like rules, custom instructions, and agent specs for errors such as misspellings, truncation warnings, and dead references, helping developers avoid subtle misconfigurations that can cause unexpected agent behavior.
Background
- Skillsaw is a new open-source linting tool designed specifically for AI coding agent configuration files (e.g., Cursor rules, Copilot instructions, custom agent prompts). "Linting" means automatically checking files for errors, inconsistencies, or violations of best practices — like a spellchecker for code style.
- AI coding agents are tools (Cursor, GitHub Copilot, etc.) that can generate or edit code based on natural-language instructions. These agents rely on plain-text configuration/rules files (often Markdown) that tell them how to behave, which libraries to use, what coding style to follow, etc.
- The problem Skillsaw addresses: these configuration files have no standard syntax checker. Mistakes in them (typos, contradictory rules, broken references) silently cause AI agents to produce worse code, but there was no easy way to catch such errors before running the agent.
- Skillsaw fills the same role for AI agent configs that tools like ESLint (for JavaScript) or Ruff (for Python) fill for source code: catch problems early, enforce consistency, and save debugging time.
Max Weinbach says he had early access to OpenAI's new model GPT-5.6 Sol, calling it his favorite model by far. He highlights that it never gives up and will keep reasoning until it's done. OpenAI announced that GPT-5.6 Sol, along with Terra and Luna, will launch publicly on Thursday, with preview access expanding globally now.
The US government ordered Anthropic to suspend access to its Fable 5 and Mythos 5 models for all customers, citing a potential jailbreak technique that involved asking the model to review a codebase for vulnerabilities—a capability Anthropic says is available in other public models. Access was abruptly cut off on June 12.
Andrej Karpathy announces the release of Claude Fable 5, the same underlying model as Mythos but with added safeguards. He calls it a major step forward, particularly for long problem-solving sessions on difficult tasks, and describes it as state-of-the-art on nearly all benchmarks with exceptional performance in software engineering, research, and vision.
Roman Storm warns that the legal theory in his case could set a precedent making open-source developers liable for how others use their code, potentially criminalizing the mere publication of privacy, messaging, or crypto tools. He notes that developer Michael Lewellen cannot publish lawful code due to prosecution fears, and argues this chilling effect extends beyond any single case.
Meta's engineering culture is deteriorating under Mark Zuckerberg and Scale AI CEO Alexandr Wang, who have introduced keyboard tracking, reassignments to data labeling, and AI-centric performance metrics. Critics argue this incentivizes performative AI use, drives away experienced engineers, and contributed to a major Instagram hijacking incident caused by AI-written and AI-reviewed code.