rust-review: A Security Review Skill for Rust Codebases
rust-review is a Rust code security review Skill in the Trail of Bits skills marketplace. It uses an orchestrator with worker, dedup, and fp subagents to cover safe/unsafe boundaries, unsafe memory safety, concurrency, panic-DoS, FFI, and async runtime issues, producing REPORT.md and REPORT.sarif. It is suitable for auditing crates and services that include unsafe code, FFI, or concurrency; for scenarios such as pure C/C++, smart contracts, and key zeroing, use c-review, contract-specific Skills, or zeroize-audit instead. After adding the trailofbits/skills marketplace in Claude Code or Codex, start the review with /rust-review:rust-review.
Read Moredsh-moli: Driving the Local Moli Browser in DeepSeek Harness
`dsh-moli` is a web tooling plugin for DeepSeek Harness designed to address web pages that cannot be handled by plain HTTP requests due to JavaScript rendering, login-based access, or the need to save screenshots. By invoking the local Moli headless browser engine, it provides two core functions: `moli_fetch` (rendering and outputting Markdown/HTML/screenshots) and `moli_probe` (checking/installing the engine). Installation first requires adding the plugin via npm, followed by manually installing the approximately 101MB Moli engine. This plugin is suitable for SPAs, login-walled sites, and deep data extraction, but not for purely static pages.
Read Moredsh-web-fetch-moli: Lightweight Moli Backend
`dsh-web-fetch-moli` is a lightweight plugin for DeepSeek Harness (DSH) designed to address the high resource consumption of traditional browsers when rendering SPAs and micro-frontends. Built on the Rust-based Moli backend, it keeps memory usage around 50–60 MB, reducing consumption by over 90% compared with standard browsers. The plugin supports both local and CDP backend modes, handles Cloudflare challenges, removes content noise, and generates GitHub-Flavored Markdown, making it suitable for resource-constrained scenarios requiring high-concurrency scraping of dynamic pages.
Read MoreCreate a natively Rust desktop pet for DeepSeek Harness using dsh-plugin-pet-rs
dsh-plugin-pet-rs is a Rust-native desktop pet maintained by HuanLinOTO: it features a five-state whale design, dual-channel `events.mux`/`events.host` with 2-second polling, a transparent always-on-top window and system tray, and read-only connection to the local DeepSeek Harness. The community guide provides `dsh plugin add github:HuanLinOTO/dsh-plugin-pet-rs`, but the repository has no `package.json`, so you need to build it via Cargo manually. It fully supports Windows, macOS and Linux X11, with degraded functionality on Wayland. The license is subject to AGPL-3.0 in the root directory.
Read MorexAI Open-Sources All Terminal Programming Agents: Why Grok Build Shot to the Top of GitHub Trending Overnight
On July 15, 2026, xAI open-sourced the complete Harness and TUI of the Grok Build terminal programming Agent under the Apache 2.0 license. The main body is implemented in Rust, supporting MCP, Skills, local Ollama deployment and multi-model configuration. The repository quickly topped GitHub Trending, and is regarded as a landmark event in the migration of AI coding tools from closed-source IDE plugins to auditable and privatizable terminal Agents. This article sorts out its architecture, installation method, Ollama access and comparison with tools such as Claude Code.
Read MorexAI Open-Sources Grok Build: Fully Unveils Harness, TUI and Tooling Layer for Rust Coding Agents
On July 15, 2026, SpaceXAI open-sourced Grok Build (the coding Agent behind the grok CLI and its full-screen TUI) under the Apache 2.0 license. The repository xai-org/grok-build quickly gained over 20,000 stars. Based on official announcements and documentation, this article sorts out the Agent loop, tool layer, TUI, and Skills/MCP extension mechanism, introduces ACP integration, local compilation and custom model configuration, and conducts a horizontal comparison with Codex CLI and OpenCode, to help developers understand the architecture and usage of this heavyweight open-source coding Agent Harness.
Read More