Version updated for https://github.com/rw-core/rw-ai-reviewer to version v1. This action is used across all versions by ? repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary The AI code review action automates the process of performing AI-based reviews on pull requests by gathering PR context, diff, and customizable instructions. It sends the combined data to a GitHub Models inference API and posts the result as a sticky comment on the PR, along with job summaries and outputs. The action supports extending or replacing built-in review instructions with custom markdown files.

Version updated for https://github.com/sipyourdrink-ltd/bernstein to version v3.5.0. This action is used across all versions by 5 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary Bernstein automates multi-agent deterministic scheduling of CLIs such as Claude Code, Codex, and Gemini CLI in parallel Git worktrees. It uses an HMAC-signed audit chain to track each step of the process and provides signed agent cards for secure delegation. The lineage feature records every adapter file write, ensuring artifact provenance.

Version updated for https://github.com/spekhq/spek to version v1.8.1. This action is used across all versions by 0 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary Spek is a lightweight read-only viewer that transforms local OpenSpec directories into an interactive, structured interface. It provides features like dashboard overview, spec browsing, change management, Git worktree aggregation, timeline visualization, BDD syntax highlighting, task progress tracking, and full-text search. The tool is available in various forms including web apps, VS Code extensions, and IntelliJ plugins, all designed for read-only access to OpenSpec content without server deployment or authentication.

Version updated for https://github.com/stranxik/runward to version v0.18.1. This action is used across all versions by 0 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary Runward is a delivery framework designed to structure agentic systems from idea to production. It automates the gating process, ensuring that agents are built and run correctly before deployment, covering six key phases of development: frame, spec kit or open spec, brownfield characterization, floor first (testing), evolution on evidence, governance from day zero, and handover. Runward helps prevent architecture failures by addressing core assumptions of classical distributed engineering and providing a structured approach to the delivery of agentic systems.

Version updated for https://github.com/sun-praise/pi-review-agent to version v1.5.0. This action is used across all versions by ? repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary Multi-persona PR review agent using Pi and Litellm AI to automate inline reviews, cache management, and team collaboration on GitHub or Gitea platforms. What’s Changed Highlights Two-layer verifier suppresses hallucinated findings — rule-based line/file checks plus LLM re-confirmation. Demoted items appear in a collapsible section. Regex grep tool — the walkGrep matcher now accepts regex patterns by default. Cross-model fallback — configure a comma-separated fallback model list (PI_REVIEW_FALLBACK_MODELS) so the agent retries on another model when the primary fails. What’s Changed Added Two-layer verifier to suppress hallucinated findings (#21) Regex support in grep tool Cross-model fallback support (#29) Fixed parseDiffPath handles file paths containing spaces (#25) filterDiff truncates at section boundaries and excludes build artifacts by default (#28) walkGrep glob matching normalizes path separators for Windows compatibility Full Changelog: https://github.com/sun-praise/pi-review-agent/compare/v1.4.0...v1.5.0

Version updated for https://github.com/vbem/setup-hcloud to version v1.0.6. This action is used across all versions by 1 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary This GitHub Action sets up Huawei Cloud KooCLI (Huawei CLI) on your runner, supporting Linux, macOS, and Windows. It supports downloading the tool from internal mirrors if needed, and can automatically check its version and accept the privacy statement during installation. The action provides outputs for the download URL, binary path, and version detected after setup.

Version updated for https://github.com/warmup-rocks/warm-action to version v1.0.1. This action is used across all versions by ? repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary The warmup.rocks CDN Cache Warmer Action automatically triggers a cache warm run on the warmup.rocks service right after a deployment in your GitHub repository. It helps ensure that your CDN cache is hot and ready to serve content to visitors before they arrive, improving performance and user experience. The action uses an encrypted secret for the deploy hook URL and can skip runs if it detects a warm pass in progress or within the cooldown period.

Version updated for https://github.com/yaniv-golan/cowork-harness to version v1.1.0. This action is used across all versions by 0 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary This GitHub Action, cowork-harness, provides a scriptable, CI-friendly test harness to reproduce the observable runtime contract of Claude Cowork. It allows users to test their skills across many scenarios headless and in CI environments without relying on the locked Desktop app. The action supports different fidelity tiers, including replay mode for free demos, linting functionality with Python3, and live testing modes that require a running agent, token, and runtime environment. The summary highlights its main purpose, how it solves the need to test skills in various contexts, and the key capabilities it offers for developers.

Version updated for https://github.com/yshrsmz/kover-report-action to version v3.0.0. This action is used across all versions by ? repositories. Action Type This is a Node action using Node version 24. Go to the GitHub Marketplace to find the latest changes. Action Summary This GitHub Action automates the process of generating and reporting code coverage from Kover XML reports in Kotlin/Android projects. It supports multi-module support with flexible discovery methods (command-based or glob pattern) and configurable thresholds for different module types and names. The action also provides options to include coverage history and trends in PR comments, making it useful for tracking code coverage improvements over time.

Version updated for https://github.com/NieZhuZhu/ai-harness-doctor to version v1.9.0. This action is used across all versions by 0 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary AI Harness Doctor is a GitHub Action that automates the consolidation of scattered agent configurations into a single canonical file (AGENTS.md) to prevent drift in repository settings such as tools, paths, and package managers. It helps manage agent configurations by providing a full checkup including inventory, conflict evidence, security audit, missing infrastructure gaps, and tech-stack snapshot. The action avoids mutating files or directories that are linked through symlinks.