The mjmirza/app-store-compliance repository provides a playbook and pre-submission guard for iOS and Android apps, including checks for privacy manifests and Data safety forms. Its author says the project documents 117 rejection patterns and fixes and tracks 95 regulatory deadlines. The guard can run through AI coding tools and block submission commands when it detects critical risks. The repository uses the OpenRoots Agent License 2.3 for its current release, and earlier releases have different license terms.
Nightly build v0.71.0-nightly.20261121.geecccfcd5 includes two fixes: expanding Windows home-relative paths using tilde and backslash, and resuming the most recently active session instead of the most recently started one.
Valhalla Matrix Governance Laboratory reviewed Google Labs’ stitch-skills as a collection of standardized Agent Skill contracts for exporting designs, generating components, and validating artifacts through Stitch MCP Server. The repository separates React and React Native workflows, includes SWC-based checks for color literals, and adds timeout and input validation to static HTML extraction. The review was limited to static source analysis and did not test runtime compatibility, service connectivity, or generated-output fidelity.
Gemini CLI Releases published v0.71.0-nightly.20261120.gd4cb1713f with a new /stats heatmap for viewing daily token usage. The release also preserves literal dollar signs during template replacement, avoids a GCLI_EXPAND_TARGET environment-variable collision, serializes ACP tool-call output as text, and includes numerous CLI and core fixes.
Gemini CLI released version 0.70.0 with fixes across session previews, authentication restarts, model responses, request timeouts, MCP permissions, and workspace handling. Notable changes include preserving Unicode prompts while removing ANSI fragments from previews, retaining a selected worktree after authentication restarts, and reporting accurate output-token limits in model listings.
Gemini CLI released v0.71.0-preview.0 with a change to parse PowerShell commands asynchronously, intended to prevent the interface spinner from freezing. The release notes also list a change to push a development worker to a private artifact registry.
The Gemini CLI v0.69.0 release notes list a new /stats heatmap subcommand for viewing daily token usage. The release also includes fixes for template placeholder substitution, an environment-variable collision, ACP tool-call output, Windows PowerShell substitution, network-failure hangs, quota retries, and other CLI and VS Code issues.
Gemini CLI released version 0.70.0-preview.0 with fixes across its CLI, core, and IDE components. Notable changes preserve Unicode prompts, remove ANSI fragments from session previews, retain selected worktrees across authentication restarts, scale request timeouts, improve model output-limit reporting, and skip system MCP servers with insecure command permissions.
Google’s second edition of its SRE book updates a first edition that standardized practices such as SLOs, error budgets, toil reduction and blameless postmortems. Authors told InfoQ 中文 AI&大模型 that platform engineering and AI are changing reliability work, including managing nondeterministic model outputs and reviewing AI-generated incident responses, so the rewrite emphasizes first principles, organizational culture and practices from other companies. The book also gives greater space to social-technical systems and the business value of reliability while trimming technical details that have become commodity features or easier to generate with LLM tools.
A hands-on report tests Plannotator, an open-source local review tool that displays plans, Markdown, HTML, code changes, pull requests, and merge requests for line-level annotations. The author confirmed that a local binary serves the interface, found that uncommitted changes can be reviewed without opening a pull request, and showed that annotations can be returned as structured JSON containing file locations, comments, and a three-state decision. Plannotator does not run models or make code changes itself, while some integration features and approval-note support remain dependent on vendor documentation and host compatibility.
The google-labs-code/stitch-skills repository contains Agent Skills and plugins designed to work with the Stitch MCP server and follow the Agent Skills open standard. It lists compatibility with coding agents including Codex, Antigravity, Gemini CLI, Claude Code, Cursor, and OpenCode. The documentation provides setup instructions for Codex, Claude Code, and Cursor, plus a manual installation process for OpenCode. Its skills cover design generation and management, design-system workflows, converting Stitch screens to React components, and generating complete multi-page websites. The repository states that all skills require a configured and running Stitch MCP server with appropriate credentials and environment variables.
The huytieu/COG-second-brain repository describes COG as a self-evolving personal knowledge system combining AI agents, local Markdown files, Git, specialist workers, read-only verifiers and a people CRM. The MIT-licensed project lists support for Claude Code, Antigravity, Cursor, Kiro, Gemini CLI, OpenAI Codex and other Markdown-reading agents. Its documentation gives conflicting skill counts, stating 35 in the repository description while another section lists 43.
Anthropic Cybersecurity Skills is an independent, community-created project, not affiliated with Anthropic PBC. It is distributed under the Apache 2.0 license and provides structured cybersecurity workflows for AI agents using the agentskills.io standard. The README describes 817 or 818 skills across 29 or 34 domains and maps the collection to MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, MITRE D3FEND, NIST AI RMF and MITRE F3. It also claims compatibility with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI and other platforms.
Chrome DevTools documentation says chrome-devtools-mcp lets coding agents such as Antigravity, Claude, Cursor and Copilot control and inspect a live Chrome browser through an MCP server or CLI. The tool provides browser automation, network and console debugging, screenshots, performance traces and source-mapped stack traces, along with skills for accessibility, cookie and session debugging, Largest Contentful Paint optimization and memory-leak debugging. The documentation says Google Chrome and Chrome for Testing are officially supported; other Chromium-based browsers may work but are not guaranteed.
A Chinese-language report describes open-source Magpie as a local, cross-platform gateway for AI coding agents such as Claude Code and Codex CLI. According to the report, it translates Anthropic Messages requests into an OpenAI-compatible format and can connect clients to models including DeepSeek-V3/R1, Kimi, Qwen, and Ollama-hosted models. The report also says Magpie supports account failover when a primary provider encounters errors such as rate limits or unpaid balances. It offers a macOS menu utility, terminal TUI, web interface, and a Go-based build that can run on Linux or in Docker. These capabilities were not independently verified in the supplied material.
A source-referenced analysis compares how Codex, Gemini CLI, OpenCode, and ZCode assemble model context from system prompts, instruction files, environment details, conversation history, tool output, and new messages. It also examines curated history, prompt caching, context compaction, and OpenCode's image budget. The findings are based on four repository snapshots dated November 9, 2026, with specific files and line numbers cited; the source code and line references may since have changed.
Gemini CLI v0.68.0 adds an extension-validation command and evaluation tests, along with support for recognizing dotted Gemini 3 model names in multimodal function responses. The release also fixes terminal-width history rendering, surrogate-pair display truncation, case-insensitive root checks on Windows, rate-limit cooldown messages, extension installation races, and selected-model persistence during fallback or rewind operations.
Gemini CLI Releases published v0.69.0-preview.0 with a new /stats heatmap subcommand for viewing daily token usage. The release also preserves literal dollar signs during template replacement and serializes AnsiOutput as text in ACP tool-call updates, alongside numerous fixes for hangs, retries, sandboxing, memory retention, and process handling.
掘金 describes GitHub Spec Kit as a specification-driven development toolkit that moves AI coding through constitution, specification, plan, tasks, implementation, and convergence stages. Its clarify stage asks about ambiguous requirements, while converge compares generated code with the specification and appends tasks for uncovered gaps; in one reported CLI todo test, this process found an unhandled corrupted-file case despite 14 passing tests. The toolkit supports more than 20 coding agents, including Claude Code, GitHub Copilot, Codex, Gemini CLI, Cursor, Cline, opencode, Qwen Code, Kiro CLI, and Zed.
The author released honestly, an MIT-licensed, local rule-based tool that checks AI coding assistant replies before they are sent. In a recorded Claude Code session with Sonnet 5.5, the tool blocked a claim that four tests had passed after only a small Python check, and the assistant then ran pytest and reported four passing tests. The author also says honestly supports Codex, has experimental Cursor and Gemini CLI support, and flagged 12 replies across 219 personal sessions.
CyberArena evaluated 12 model-and-harness combinations through 22 batches and 466 valid cybersecurity games, with agents attacking opponents while protecting their own services. The research team reported GPT-5.6 Sol running on Codex first with a 78.6 relative score, followed by Claude Opus 5 running on Claude Code at 73.8. Its contrast with static tasks showed capture rates falling to 52%, 37%, and 35% by the third adversarial round for the three models that solved all 30 selected tasks in solo mode.
According to the Gemini CLI v0.67.0 release notes, the release adds a bridge that connects the IDE companion to container sandboxes over exec stdio. It also fixes duplicate agent loading when the workspace is the home directory, adds a models command and --list-models flag for model discovery, and addresses cancellation, token-usage metadata, and permission-request handling. The notes also reference nightly and preview changelogs, so the packaging status of every listed change is not fully specified.
Gemini CLI Releases reported the release of v0.68.0-preview.0. The changelog lists an extension validation command and evaluation tests, recognition of dotted Gemini 3 models in multimodal function responses, documentation clarifying the project's scope and limitations, and fixes for Windows root checks, terminal width changes, concurrent extension installs, and rate-limit cooldown feedback.
A Juejin author reports that Codex repeatedly modified code and reran failing tests, consuming substantial token usage without completing the task. The article recommends pausing after two unsuccessful attempts on the same issue, preserving evidence, avoiding redundant checks and scope expansion, and recording goals, test results, and remaining work for longer sessions.
SimpleEnglish is an MIT-licensed Agent Skill that asks LLMs to write plain English by default and can apply stricter ASD-STE100 rules on request. Its documentation lists compatibility with Claude Code, Cursor, VS Code Copilot, OpenAI Codex, Gemini CLI, Goose, OpenCode, and other Agent Skills-compatible tools. The project reports that version 2.0.1 reduced visible formatting defects by 95% across 16 Claude replies and lowered STE linter violations by 81.3% across nine Claude models, but no evaluation run is available for version 2.1.0 or later.
The blader Humanizer repository describes an installable agent skill that rewrites AI-generated text to sound more human without changing what it says. It is built on Wikipedia’s “Signs of AI writing” guide, checks for 26 writing patterns and supports voice matching. The project says it works with Claude Code, Codex and other agents that support skills, including Gemini CLI, GitHub Copilot and Windsurf; these compatibility claims have not been independently verified. The project also reports that judges preferred its rewrites in all 16 blind-test comparisons, a result that has not been independently validated. It says the tool is intended for human readers rather than AI-detector evasion, and that detectors still flag most output.
掘金 · 人工智能 presents Magpie v0.1.2906 as an open-source local gateway and configuration manager for AI coding agents. It converts among OpenAI Chat Completions, OpenAI Responses, Anthropic Messages and Gemini APIs, allowing Claude Code to use DeepSeek and Codex to use Kimi while managing provider keys, model settings and reusable profiles. The report also describes routing groups, intent-based model selection and local key redaction, but its functionality claims come from one unofficial tutorial citing project documentation.
Gemini CLI released the nightly build v0.67.0-nightly.20261104.g89e9d25d6. The changelog lists fixes for handling stream failures during extension release downloads, preserving an explicitly selected Gemini 2.5 Flash model during dynamic resolution, supporting SubagentStop event mapping and merging hook definitions, awaiting history replay before responding to ACP session/load requests, and supplying the --userns=keep-id option for rootless Podman.
According to its README, Paperclip is an open-source Node.js server and React interface for coordinating teams of AI agents around business goals. It allows users to bring their own agents, assign goals, select models and harnesses per agent, and track tasks, permissions, history, budgets, and costs from one dashboard. These features are described by the project and were not independently verified in the supplied report. The project is licensed under MIT and includes a waitlist for Paperclip Cloud; the report does not establish the cloud service's release date or general availability.
Gemini CLI Releases published the v0.67.0-nightly.20261103.g0ac57c029 build with a core fix for interrupted Whisper model downloads. The change prevents a download that did not finish from being treated as successfully installed.
What problem it solves
Personal and team knowledge is distributed across notes, conversations, trackers, and research, making it difficult to capture, organize, verify, and synthesize useful information. COG provides a markdown-based workflow in which agents can maintain a shared knowledge base, support recurring research and operational tasks, and verify selected work through independent checks.
…
What problem it solves
Managing multiple AI coding assistants often requires switching API providers and editing JSON, TOML, or YAML configuration files by hand. This project centralizes those provider and extension-management tasks in one desktop interface.
Key features
One-click provider switching — Switch between API providers without manually editing each application's configuration files.
Sou…
What problem it solves
AI agents need relevant design context from Figma files to generate code that follows a design system and reflects design intent. This project documents how to connect the Figma MCP server to supported clients, use its tools and skills, and apply practices for more consistent results.
Key features
Connect supported MCP clients — Setup instructions cover the Figma MCP server …
What problem it solves
Coding agents need a structured way to create, manage, and build from Google Stitch designs while integrating with the Stitch MCP server. The project organizes design, code generation, and supporting workflows into skills that can be installed with supported coding agents.
Key features
Design workflows — The design plugin covers converting frontend code into Stitch designs, …
What problem it solves
Developers and enterprise teams need a terminal-based agent that can understand and modify code, automate operational tasks, and integrate additional capabilities into development workflows. Gemini CLI also needs clear access requirements and authentication options for organizations using Gemini Code Assist or supported Google Cloud services.
Key features
Code understanding …
What problem it solves
Teams that rely on AI agents need a way to give each agent a role, workspace, and instructions, keep context across conversations, and control what agents are allowed to do. Without that, agents run blind: actions happen without review, memory does not persist, and repeating scheduled work means redoing setup by hand.
Key features
Create agents and teams — Give an agent a na…
What problem it solves
Accessing Google Workspace APIs from the command line can require repetitive request construction, manual pagination, and custom tooling for agents. The project addresses this by generating its command surface from Google Discovery Service and producing structured JSON output across Workspace services.
Key features
Dynamic Workspace command surface — The CLI reads Google's D…