[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-plugin-vercel-labs-agent-browser-en":3,"guides-for-vercel-labs-agent-browser":465,"similar-k175gma4kma3radvem5pa46wgn86nd1b-en":466},{"_creationTime":4,"_id":5,"children":6,"community":45,"display":46,"evaluation":49,"identity":282,"isFallback":278,"parentExtension":285,"providers":312,"relations":317,"repo":318,"tags":462,"workflow":463},1778698388090.9075,"k175gma4kma3radvem5pa46wgn86nd1b",[7],{"_creationTime":8,"_id":9,"community":10,"display":12,"identity":18,"providers":23,"relations":38,"tags":40,"workflow":41},1778698388090.9092,"k1747f35gjnz60tye52m1aa5fh86nszq",{"reviewCount":11},0,{"description":13,"installMethods":14,"name":16,"sourceUrl":17},"Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.",{"claudeCode":15},"vercel-labs/agent-browser","agent-browser","https://github.com/vercel-labs/agent-browser",{"basePath":19,"githubOwner":20,"githubRepo":16,"locale":21,"slug":16,"type":22},"skills/agent-browser","vercel-labs","en","skill",{"evaluate":24,"extract":36},{"promptVersionExtension":25,"promptVersionScoring":26,"score":27,"tags":28,"targetMarket":34,"tier":35},"3.0.0","4.4.0",98,[29,30,31,32,33],"browser-automation","cli","web-testing","automation","ai-agent","global","verified",{"commitSha":37},"HEAD",{"parentExtensionId":5,"repoId":39},"kd74a6sfc26xa0ec2tpntj8r2986mn0a",[33,32,29,30,31],{"evaluatedAt":42,"extractAt":43,"updatedAt":44},1778698546309,1778698388091,1778698677055,{"reviewCount":11},{"description":47,"installMethods":48,"name":16,"sourceUrl":17},"Automates browser interactions for web testing, form filling, screenshots, and data extraction",{"claudeCode":16},{"_creationTime":50,"_id":51,"extensionId":5,"locale":21,"result":52,"trustSignals":261,"workflow":280},1778698422910.9119,"kn72ajhv4hsqjdtfcfq2svmben86mm2d",{"checks":53,"evaluatedAt":238,"extensionSummary":239,"features":240,"nonGoals":246,"promptVersionExtension":25,"promptVersionScoring":26,"purpose":250,"rationale":251,"score":27,"summary":252,"tags":253,"targetMarket":34,"tier":35,"useCases":255},[54,59,62,65,69,72,76,80,83,86,90,94,98,102,105,108,111,114,117,120,124,128,132,136,140,143,146,149,153,156,159,162,165,168,171,175,179,183,186,190,193,196,199,202,205,208,211,214,217,220,224,227,230,234],{"category":55,"check":56,"severity":57,"summary":58},"Practical Utility","Problem relevance","pass","The description clearly states the problem of automating browser interactions for web testing, form filling, screenshots, and data extraction.",{"category":55,"check":60,"severity":57,"summary":61},"Unique selling proposition","The extension provides a native Rust CLI for browser automation, offering a fast and direct alternative to Node.js-based solutions and integrating with AI agents via snapshots and refs.",{"category":55,"check":63,"severity":57,"summary":64},"Production readiness","The plugin covers a complete lifecycle for browser automation, from installation and execution to various interaction types, state management, and debugging features.",{"category":66,"check":67,"severity":57,"summary":68},"Scope","Single responsibility principle","The plugin focuses on browser automation, with a coherent set of commands for interacting with web pages and related environments like Electron apps.",{"category":66,"check":70,"severity":57,"summary":71},"Description quality","The displayed description accurately reflects the plugin's capabilities in automating browser interactions for testing, form filling, and data extraction.",{"category":73,"check":74,"severity":57,"summary":75},"Invocation","Scoped tools","The plugin exposes numerous narrow verb-noun tools (e.g., `click`, `fill`, `snapshot`) which are specific and easy for agents to select.",{"category":77,"check":78,"severity":57,"summary":79},"Documentation","Configuration & parameter reference","The README provides comprehensive documentation for all commands, parameters, and environment variables, including defaults and precedence.",{"category":66,"check":81,"severity":57,"summary":82},"Tool naming","Tool names are descriptive verb-noun combinations (e.g., `click`, `fill`, `snapshot`) that clearly indicate their function within the browser automation domain.",{"category":66,"check":84,"severity":57,"summary":85},"Minimal I/O surface","Tool parameters are well-defined (e.g., selectors, text, paths), and output is structured (JSON, plain text) and focused on the requested data, not internal diagnostics.",{"category":87,"check":88,"severity":57,"summary":89},"License","License usability","The project is licensed under Apache-2.0, which is a permissive open-source license, clearly indicated by a LICENSE file and SPDX identifier.",{"category":91,"check":92,"severity":57,"summary":93},"Maintenance","Commit recency","The latest commit was on 2026-05-07, indicating active maintenance within the last 90 days.",{"category":91,"check":95,"severity":96,"summary":97},"Dependency Management","not_applicable","No third-party dependencies are explicitly mentioned or discoverable in the provided source files, suggesting direct native binary compilation.",{"category":99,"check":100,"severity":57,"summary":101},"Security","Secret Management","The extension provides various mechanisms for handling secrets (auth vaults, state encryption, profile reuse) and explicitly warns against committing sensitive data.",{"category":99,"check":103,"severity":57,"summary":104},"Injection","The README explicitly mentions content boundary markers (`--content-boundaries`) and action policies (`--action-policy`) to mitigate prompt injection and untrusted content risks.",{"category":99,"check":106,"severity":57,"summary":107},"Transitive Supply-Chain Grenades","The plugin relies on a self-contained native binary and standard installations, with no indication of runtime remote code fetching or execution of untrusted content.",{"category":99,"check":109,"severity":57,"summary":110},"Sandbox Isolation","The plugin operates within the browser context it controls, and its commands are specific to browser interactions, with no apparent ability to modify files outside the project or agent scope.",{"category":99,"check":112,"severity":57,"summary":113},"Sandbox escape primitives","The plugin executes commands directly within the browser context and does not appear to use detached processes or retry loops around denied operations.",{"category":99,"check":115,"severity":57,"summary":116},"Data Exfiltration","Security features like domain allowlisting and content boundary markers are provided to prevent data exfiltration. No outbound calls to undocumented or suspicious domains are apparent.",{"category":99,"check":118,"severity":57,"summary":119},"Hidden Text Tricks","The bundled README and source files appear to be free of hidden-steering tricks, Unicode tag characters, or ANSI escapes designed to manipulate models without curator visibility.",{"category":121,"check":122,"severity":57,"summary":123},"Hooks","Opaque code execution","The plugin is a native Rust binary, and any bundled scripts for initialization or hooks are expected to be plain and readable, not obfuscated or dynamically fetched.",{"category":125,"check":126,"severity":57,"summary":127},"Portability","Structural Assumption","The plugin operates on web pages via CDP and does not appear to make structural assumptions about the user's project layout beyond standard browser interaction requirements.",{"category":129,"check":130,"severity":57,"summary":131},"Trust","Issues Attention","With 142 issues opened and 155 closed in the last 90 days, the closure rate is approximately 52%, indicating active maintenance and responsiveness.",{"category":133,"check":134,"severity":57,"summary":135},"Versioning","Release Management","The project has a clear versioning strategy with a `CHANGELOG.md` file and a recent commit date, suggesting meaningful version updates.",{"category":137,"check":138,"severity":57,"summary":139},"Code Execution","Validation","While explicit mention of a schema library is absent, the CLI's structured argument parsing and the nature of browser commands suggest robust input validation.",{"category":99,"check":141,"severity":57,"summary":142},"Unguarded Destructive Operations","Commands are primarily focused on browser interaction and data retrieval; any state-changing operations would be within the browser context and not destructive to the host system.",{"category":137,"check":144,"severity":57,"summary":145},"Error Handling","The native Rust binary is expected to implement robust error handling, exiting with non-zero codes and descriptive messages on failure.",{"category":137,"check":147,"severity":57,"summary":148},"Logging","The plugin offers verbose logging and debug output options (`--verbose`, `--debug`) for auditing actions, and the dashboard provides a live activity feed.",{"category":150,"check":151,"severity":57,"summary":152},"Compliance","GDPR","The plugin offers features like domain allowlisting and content boundaries to help manage data submission and compliance, but user responsibility remains for sanitizing personal data.",{"category":150,"check":154,"severity":96,"summary":155},"Target market","The extension is a general-purpose browser automation tool with no inherent regional or jurisdictional logic, thus its target market is global.",{"category":125,"check":157,"severity":57,"summary":158},"Runtime stability","The native Rust binary and its use of CDP ensure cross-platform compatibility. The README details dependencies and build instructions for various OS.",{"category":77,"check":160,"severity":57,"summary":161},"README","The README is comprehensive, detailing installation, usage, commands, and advanced features, clearly stating the extension's purpose.",{"category":66,"check":163,"severity":57,"summary":164},"Tool surface size","The plugin exposes a large number of tools, but they are well-organized by functionality and maintain a clear scope, staying within acceptable limits for a comprehensive CLI.",{"category":73,"check":166,"severity":57,"summary":167},"Overlapping near-synonym tools","While many commands exist, they generally represent distinct actions (e.g., `click` vs. `fill`) and the use of refs (`@eN`) provides deterministic targeting, minimizing ambiguity.",{"category":77,"check":169,"severity":57,"summary":170},"Phantom features","Features mentioned in the README, such as AI chat integration, React DevTools support, and dashboard observability, are implemented and described in the documentation.",{"category":172,"check":173,"severity":57,"summary":174},"Install","Installation instruction","The README provides clear, multi-platform installation instructions (npm, Homebrew, Cargo) and copy-pasteable examples for global and local installs.",{"category":176,"check":177,"severity":57,"summary":178},"Errors","Actionable error messages","The native binary is expected to provide clear, actionable error messages with hints for remediation, as is standard for well-built CLIs.",{"category":180,"check":181,"severity":96,"summary":182},"Execution","Pinned dependencies","The plugin is a self-contained native Rust binary, and no third-party script dependencies requiring pinning or shebangs are apparent.",{"category":66,"check":184,"severity":57,"summary":185},"Dry-run preview","While not explicitly a 'dry-run' flag for all commands, features like `--json` output and detailed command descriptions allow for previewing intended actions.",{"category":187,"check":188,"severity":57,"summary":189},"Protocol","Idempotent retry & timeouts","The plugin defines a default timeout for operations and has a mechanism for session persistence, implying some level of state management suitable for retries.",{"category":150,"check":191,"severity":57,"summary":192},"Telemetry opt-in","The dashboard's AI chat feature requires environment variables for API keys, and other telemetry/logging features are explicitly enabled or opt-in via flags.",{"category":73,"check":194,"severity":57,"summary":195},"Name collisions","The plugin's tools are specific to browser automation and do not appear to collide with built-in Claude Code commands or common CLI utilities.",{"category":73,"check":197,"severity":96,"summary":198},"Hooks-off mechanism","The plugin does not appear to utilize hooks in a way that would require a hooks-off mechanism separate from the main plugin uninstall.",{"category":73,"check":200,"severity":96,"summary":201},"Hook matcher tightness","The plugin does not expose hooks that require custom matching logic; its functionality is command-based.",{"category":99,"check":203,"severity":96,"summary":204},"Hook security","The plugin does not appear to implement hooks that would require specific security gating beyond standard command execution.",{"category":121,"check":206,"severity":96,"summary":207},"Silent prompt rewriting","The plugin does not appear to have UserPromptSubmit hooks that would silently rewrite prompts.",{"category":99,"check":209,"severity":96,"summary":210},"Permission Hook","The plugin does not appear to implement PermissionRequest hooks that auto-approve permissions.",{"category":150,"check":212,"severity":96,"summary":213},"Hook privacy","The plugin does not appear to use hooks for network-based logging or telemetry.",{"category":137,"check":215,"severity":96,"summary":216},"Hook dependency","The plugin is a native binary and does not appear to rely on external hook scripts.",{"category":77,"check":218,"severity":57,"summary":219},"Feature Transparency","Critical functionality, including security features and the dashboard, is clearly explained in the README.",{"category":221,"check":222,"severity":57,"summary":223},"Convention","Layout convention adherence","The plugin follows standard conventions, with a clear separation of concerns and executable binaries appropriately placed. The README documents executable commands.",{"category":221,"check":225,"severity":57,"summary":226},"Plugin state","The plugin utilizes standard environment variables (`AGENT_BROWSER_SESSION_NAME`, `AGENT_BROWSER_PROFILE`) for state management, consistent with typical plugin patterns.",{"category":99,"check":228,"severity":57,"summary":229},"Keychain-stored secrets","The plugin supports encrypted session state and an authentication vault, routing sensitive data through secure mechanisms rather than plain text settings.",{"category":231,"check":232,"severity":57,"summary":233},"Dependencies","Tagged release sourcing","The plugin is distributed as a native binary, and its dependencies are managed through package managers like npm, implying sourced from tagged releases.",{"category":235,"check":236,"severity":57,"summary":237},"Installation","Clean uninstall","The plugin is installed as a native binary and does not appear to spawn persistent background daemons or services that would survive uninstallation.",1778698422796,"agent-browser is a native Rust CLI tool that provides comprehensive browser automation capabilities, including navigation, form filling, element interaction, screenshots, data extraction, and session management. It integrates with AI agents by providing accessibility tree snapshots with element references and supports various environments like Electron apps and cloud browsers.",[241,242,243,244,245],"Automate browser interactions via CLI commands","Generate accessibility tree snapshots with element refs","Support for various interaction types (click, fill, type, etc.)","Manage browser sessions, profiles, and authentication state","Integrate with AI agents and observability dashboards",[247,248,249],"Acting as a full-fledged browser engine itself","Replacing direct user browser interaction for general browsing","Providing advanced AI reasoning capabilities (relies on external agents)","To provide AI agents with a powerful, efficient, and secure tool for automating browser interactions, enabling tasks such as web testing, data extraction, and complex web-based workflows.","The plugin is well-documented, production-ready, and actively maintained with a comprehensive set of browser automation tools. No critical or warning findings were identified.","A robust and feature-rich browser automation CLI for AI agents, offering extensive capabilities and strong security practices.",[29,31,30,32,254],"web-scraping",[256,257,258,259,260],"Automating web testing and QA workflows","Filling forms and submitting data programmatically","Extracting structured data from web pages","Automating tasks in Electron desktop applications","Integrating with AI agents for complex web-based decision making",{"codeQuality":262,"collectedAt":264,"documentation":265,"maintenance":268,"popularity":274,"security":276,"testCoverage":279},{"hasLockfile":263},true,1778698406640,{"descriptionLength":266,"readmeSize":267},94,61552,{"closedIssues90d":269,"forks":270,"hasChangelog":263,"openIssues90d":271,"pushedAt":272,"stars":273},155,2035,142,1778168700000,32896,{"npmDownloads":275},2851726,{"hasNpmPackage":263,"license":277,"smitheryVerified":278},"Apache-2.0",false,{"hasCi":263,"hasTests":263},{"updatedAt":281},1778698422911,{"basePath":283,"githubOwner":20,"githubRepo":16,"locale":21,"slug":16,"type":284},"","plugin",{"_creationTime":286,"_id":287,"community":288,"display":289,"identity":292,"parentExtension":294,"providers":295,"relations":307,"tags":308,"workflow":309},1778698388090.9072,"k171hvn0e2t3jzczxm3vzspj3186mgj7",{"reviewCount":11},{"description":290,"installMethods":291,"name":16,"sourceUrl":17},"Browser automation for AI agents",{"claudeCode":15},{"basePath":283,"githubOwner":20,"githubRepo":16,"locale":21,"slug":16,"type":293},"marketplace",null,{"evaluate":296,"extract":302},{"promptVersionExtension":297,"promptVersionScoring":26,"score":298,"tags":299,"targetMarket":34,"tier":35},"3.1.0",99,[29,30,300,301,33],"webdriver","testing",{"commitSha":37,"marketplace":303,"plugin":305},{"name":16,"pluginCount":304},1,{"mcpCount":11,"provider":306,"skillCount":11},"classify",{"repoId":39},[33,29,30,301,300],{"evaluatedAt":310,"extractAt":43,"updatedAt":311},1778698406247,1778698675865,{"evaluate":313,"extract":315},{"promptVersionExtension":25,"promptVersionScoring":26,"score":27,"tags":314,"targetMarket":34,"tier":35},[29,31,30,32,254],{"commitSha":37,"plugin":316},{"mcpCount":11,"provider":306,"skillCount":304},{"parentExtensionId":287,"repoId":39},{"_creationTime":319,"_id":39,"identity":320,"providers":321,"workflow":457},1778698380039.9202,{"githubOwner":20,"githubRepo":16,"sourceUrl":17},{"classify":322,"discover":449,"extract":452,"github":453,"npm":456},{"commitSha":37,"extensions":323},[324,337,346,355,386,398,406,418,426,431,441],{"basePath":283,"description":290,"displayName":16,"installMethods":325,"rationale":326,"selectedPaths":327,"source":336,"sourceLanguage":21,"type":293},{"claudeCode":15},"marketplace.json at .claude-plugin/marketplace.json",[328,331,333],{"path":329,"priority":330},".claude-plugin/marketplace.json","mandatory",{"path":332,"priority":330},"README.md",{"path":334,"priority":335},"LICENSE","high","rule",{"basePath":283,"description":47,"displayName":16,"installMethods":338,"rationale":339,"selectedPaths":340,"source":336,"sourceLanguage":21,"type":284},{"claudeCode":16},"inline plugin source from marketplace.json at /",[341,342,343],{"path":332,"priority":330},{"path":334,"priority":335},{"path":344,"priority":345},"bin/agent-browser.js","low",{"basePath":347,"description":348,"displayName":349,"installMethods":350,"rationale":351,"selectedPaths":352,"source":336,"sourceLanguage":21,"type":22},"skill-data/agentcore","Run agent-browser on AWS Bedrock AgentCore cloud browsers. Use when the user wants to use AgentCore, run browser automation on AWS, use a cloud browser with AWS credentials, or needs a managed browser session backed by AWS infrastructure. Triggers include \"use agentcore\", \"run on AWS\", \"cloud browser with AWS\", \"bedrock browser\", \"agentcore session\", or any task requiring AWS-hosted browser automation.","agentcore",{"claudeCode":15},"SKILL.md frontmatter at skill-data/agentcore/SKILL.md",[353],{"path":354,"priority":330},"SKILL.md",{"basePath":356,"description":357,"displayName":358,"installMethods":359,"rationale":360,"selectedPaths":361,"source":336,"sourceLanguage":21,"type":22},"skill-data/core","Core agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple browser sessions in parallel, and troubleshooting common failures. Use when the user asks to interact with a website, fill a form, click something, extract data, take a screenshot, log into a site, test a web app, or automate any browser task.","core",{"claudeCode":15},"SKILL.md frontmatter at skill-data/core/SKILL.md",[362,363,366,368,370,372,374,376,378,380,382,384],{"path":354,"priority":330},{"path":364,"priority":365},"references/authentication.md","medium",{"path":367,"priority":365},"references/commands.md",{"path":369,"priority":365},"references/profiling.md",{"path":371,"priority":365},"references/proxy-support.md",{"path":373,"priority":365},"references/session-management.md",{"path":375,"priority":365},"references/snapshot-refs.md",{"path":377,"priority":365},"references/trust-boundaries.md",{"path":379,"priority":365},"references/video-recording.md",{"path":381,"priority":345},"templates/authenticated-session.sh",{"path":383,"priority":345},"templates/capture-workflow.sh",{"path":385,"priority":345},"templates/form-automation.sh",{"basePath":387,"description":388,"displayName":389,"installMethods":390,"rationale":391,"selectedPaths":392,"source":336,"sourceLanguage":21,"type":22},"skill-data/dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app/site/platform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","dogfood",{"claudeCode":15},"SKILL.md frontmatter at skill-data/dogfood/SKILL.md",[393,394,396],{"path":354,"priority":330},{"path":395,"priority":365},"references/issue-taxonomy.md",{"path":397,"priority":345},"templates/dogfood-report-template.md",{"basePath":399,"description":400,"displayName":401,"installMethods":402,"rationale":403,"selectedPaths":404,"source":336,"sourceLanguage":21,"type":22},"skill-data/electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","electron",{"claudeCode":15},"SKILL.md frontmatter at skill-data/electron/SKILL.md",[405],{"path":354,"priority":330},{"basePath":407,"description":408,"displayName":409,"installMethods":410,"rationale":411,"selectedPaths":412,"source":336,"sourceLanguage":21,"type":22},"skill-data/slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","slack",{"claudeCode":15},"SKILL.md frontmatter at skill-data/slack/SKILL.md",[413,414,416],{"path":354,"priority":330},{"path":415,"priority":365},"references/slack-tasks.md",{"path":417,"priority":345},"templates/slack-report-template.md",{"basePath":419,"description":420,"displayName":421,"installMethods":422,"rationale":423,"selectedPaths":424,"source":336,"sourceLanguage":21,"type":22},"skill-data/vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","vercel-sandbox",{"claudeCode":15},"SKILL.md frontmatter at skill-data/vercel-sandbox/SKILL.md",[425],{"path":354,"priority":330},{"basePath":19,"description":13,"displayName":16,"installMethods":427,"rationale":428,"selectedPaths":429,"source":336,"sourceLanguage":21,"type":22},{"claudeCode":15},"SKILL.md frontmatter at skills/agent-browser/SKILL.md",[430],{"path":354,"priority":330},{"basePath":283,"description":432,"displayName":16,"installMethods":433,"license":277,"rationale":434,"selectedPaths":435,"source":336,"sourceLanguage":21,"type":30},"Browser automation CLI for AI agents",{"npm":16},"cli ecosystem detected at /",[436,438,439,440],{"path":437,"priority":330},"package.json",{"path":332,"priority":330},{"path":334,"priority":335},{"path":344,"priority":365},{"basePath":30,"installMethods":442,"rationale":443,"selectedPaths":444,"source":336,"sourceLanguage":21,"type":30},{"cargo":16},"cli ecosystem detected at cli",[445,447],{"path":446,"priority":330},"Cargo.toml",{"path":448,"priority":365},"src/main.rs",{"sources":450},[451],"manual",{"npmPackage":16},{"closedIssues90d":269,"description":432,"forks":270,"homepage":454,"license":277,"openIssues90d":271,"pushedAt":272,"readmeSize":267,"stars":273,"topics":455},"https://agent-browser.dev",[],{"downloads":275},{"classifiedAt":458,"discoverAt":459,"extractAt":460,"githubAt":460,"npmAt":461,"updatedAt":458},1778698387373,1778698380040,1778698383100,1778698385198,[32,29,30,254,31],{"evaluatedAt":281,"extractAt":43,"updatedAt":464},1778698675646,[],[]]