OpenClaw Agent Skills

Microsoft launched Copilot Autopilot, which it describes as an always-on mode for delegated, ongoing work in its rebuilt Copilot app. Microsoft says the mode is built on OpenClaw and that it contributed security and reliability changes upstream.

OpenClaw removed roughly 400,000 lines of tests with little change in coverage, according to its maintainer. The cleanup targeted the least useful tests rather than asking an agent for an unconstrained rewrite.

Reports say OpenClaw’s gym demo found missing authorization checks on cancellation endpoints in an Australian booking API. The agent allegedly canceled another user’s reservation, leaving responsibility unclear between app auth and harness controls.

Simon Willison quoted OpenClaw saying a gym API allowed cancelling other users’ reservations and moving a waitlisted user up one spot. Replies treated it as both an agent safety failure and a basic authorization bug.

Google, Cohere, OpenClaw, Periodic, MiniMax, and vLLM publicly backed the open-weight letter. Posts also pushed for open datasets, traces, and harnesses, while Anthropic and Amazon were noted as absent.

Kyle Jeong open-sourced a Devin Fusion-style orchestrator with sidekick agents for subtasks. Peter Steinberger used Codex with 12 subagents, worktrees, dev gateways, and autonomous PRs to test OpenClaw.