[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-mksglu-context-mode-en":3,"guides-for-mksglu-context-mode":576,"similar-k17dkaqde3zchmw9bsrw8h1ckn86mggx-en":577},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":240,"isFallback":229,"parentExtension":244,"providers":280,"relations":284,"repo":285,"tags":573,"workflow":574},1778693511416.3652,"k17dkaqde3zchmw9bsrw8h1ckn86mggx",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Use context-mode tools (ctx_execute, ctx_execute_file) instead of Bash/cat when processing\nlarge outputs. Triggers: \"analyze logs\", \"summarize output\", \"process data\",\n\"parse JSON\", \"filter results\", \"extract errors\", \"check build output\",\n\"analyze dependencies\", \"process API response\", \"large file analysis\",\n\"page snapshot\", \"browser snapshot\", \"DOM structure\", \"inspect page\",\n\"accessibility tree\", \"Playwright snapshot\",\n\"run tests\", \"test output\", \"coverage report\", \"git log\", \"recent commits\",\n\"diff between branches\", \"list containers\", \"pod status\", \"disk usage\",\n\"fetch docs\", \"API reference\", \"index documentation\",\n\"call API\", \"check response\", \"query results\",\n\"find TODOs\", \"count lines\", \"codebase statistics\", \"security audit\",\n\"outdated packages\", \"dependency tree\", \"cloud resources\", \"CI/CD output\".\nAlso triggers on ANY MCP tool output that may exceed 20 lines.\nSubagent routing is handled automatically via PreToolUse hook.\n",{"claudeCode":12},"mksglu/context-mode","context-mode","https://github.com/mksglu/context-mode",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":219,"workflow":238},1778693586612.444,"kn76x1ekfcgfhkfx1g4dg9bbbd86n7z3","en",{"checks":20,"evaluatedAt":186,"extensionSummary":187,"features":188,"nonGoals":194,"promptVersionExtension":199,"promptVersionScoring":200,"purpose":201,"rationale":202,"score":203,"summary":204,"tags":205,"targetMarket":212,"tier":213,"useCases":214},[21,26,29,32,36,39,43,46,50,54,58,61,64,68,72,76,78,81,84,87,91,95,99,102,106,110,113,116,119,123,126,129,132,135,138,141,145,148,152,156,159,162,165,168,172,176,179,182,184],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly identifies the problem of context window bloat and inefficient data handling, and proposes context-mode tools as the solution.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The extension offers significant value over default behavior by providing a robust sandboxing mechanism, session continuity, and a code-first paradigm for data processing, directly addressing context window limitations.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The extension is production-ready, offering comprehensive documentation, clear installation instructions for multiple platforms, and a complete lifecycle for managing large outputs and maintaining session state.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The extension focuses solely on managing context window usage and data processing efficiency within AI agent interactions, without extending into unrelated domains.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The description is accurate, concise, and clearly explains the extension's purpose, triggers, and core functionality, effectively guiding users on when and how to utilize it.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Precise Purpose","The description clearly states the artifact (large outputs, API responses, files) and the user intent (processing, analyzing, filtering) that context-mode tools address, along with explicit non-goals like avoiding Bash for large data.",{"category":40,"check":44,"severity":24,"summary":45},"Concise Frontmatter","The frontmatter is dense, self-contained, and effectively summarizes the core capability and trigger phrases within the first 160 characters.",{"category":47,"check":48,"severity":24,"summary":49},"Documentation","Concise Body","The SKILL.md body is well-structured, under 500 lines, and delegates extensive material like patterns and platform details to separate reference files.",{"category":51,"check":52,"severity":24,"summary":53},"Context","Progressive Disclosure","Detailed patterns, platform specifics, and benchmarks are organized into separate reference files and linked from the main SKILL.md, adhering to progressive disclosure.",{"category":51,"check":55,"severity":56,"summary":57},"Forked exploration","not_applicable","The extension itself is a utility for managing context, rather than performing deep exploration tasks that would necessitate a forked context.",{"category":22,"check":59,"severity":24,"summary":60},"Usage examples","Multiple end-to-end, ready-to-use examples are provided for various scenarios, demonstrating inputs, invocations, and expected outcomes.",{"category":22,"check":62,"severity":24,"summary":63},"Edge cases","The documentation addresses various edge cases and limitations, including timeout recommendations, Bash vs. execute distinctions, and effective `summary_prompt` usage, with clear recovery steps.",{"category":65,"check":66,"severity":56,"summary":67},"Code Execution","Tool Fallback","The extension primarily relies on Claude Code's internal tools and Node.js runtimes; it does not reference external MCP servers that would require fallbacks.",{"category":69,"check":70,"severity":24,"summary":71},"Safety","Halt on unexpected state","The documentation emphasizes using the correct tools for the job (e.g., Bash for mutations, execute for analysis) and promotes explicit output, implicitly halting workflows that don't produce expected results.",{"category":73,"check":74,"severity":24,"summary":75},"Portability","Cross-skill coupling","The skill is self-contained and does not rely on other specific skills being loaded; it provides utility directly through its own tools.",{"category":40,"check":44,"severity":24,"summary":77},"The frontmatter is dense and immediately conveys the core capability and trigger phrases.",{"category":33,"check":79,"severity":24,"summary":80},"Tool surface size","The extension exposes a focused set of 11 well-defined MCP tools.",{"category":40,"check":82,"severity":24,"summary":83},"Overlapping near-synonym tools","The tools provided have distinct functionalities (e.g., execute vs. execute_file, index vs. search) with no significant overlap or redundancy.",{"category":47,"check":85,"severity":24,"summary":86},"Phantom features","All advertised features, including the various tools, hooks, and session continuity capabilities, have corresponding implementations detailed in the documentation.",{"category":88,"check":89,"severity":24,"summary":90},"Install","Installation instruction","Comprehensive installation instructions are provided for numerous platforms, including automatic and manual methods, with verification steps and optional configurations.",{"category":92,"check":93,"severity":24,"summary":94},"Errors","Actionable error messages","The documentation provides clear guidance on error handling, emphasizing specific output requirements and suggesting remediation steps for common issues.",{"category":96,"check":97,"severity":24,"summary":98},"Execution","Pinned dependencies","The installation instructions and build prerequisites indicate careful dependency management, including notes on Node.js versions and native compilation requirements.",{"category":33,"check":100,"severity":56,"summary":101},"Dry-run preview","The extension's core tools are analytical and do not perform state-changing operations or send data outward in a way that would require a dry-run mode.",{"category":103,"check":104,"severity":24,"summary":105},"Protocol","Idempotent retry & timeouts","The documentation explicitly recommends and demonstrates appropriate timeouts for various operations, and the sandbox nature of `execute` implies a level of statelessness between calls.",{"category":107,"check":108,"severity":24,"summary":109},"Compliance","GDPR","The extension operates locally and does not process personal data; privacy is a core architectural choice, with no telemetry or cloud sync.",{"category":107,"check":111,"severity":24,"summary":112},"Target market","The extension is designed for local execution and has no regional or jurisdictional logic, making it globally applicable.",{"category":73,"check":114,"severity":24,"summary":115},"Runtime stability","The documentation provides detailed build prerequisites and notes on Node.js versions, Bun, and native compilation, ensuring cross-platform stability.",{"category":47,"check":117,"severity":24,"summary":118},"README","A comprehensive README exists and clearly states the extension's purpose, value proposition, installation, and usage details.",{"category":120,"check":121,"severity":24,"summary":122},"Security","Secret Management","The extension emphasizes local execution and does not handle or expose secrets; it integrates with existing platform credential passthrough securely.",{"category":120,"check":124,"severity":24,"summary":125},"Injection","The sandbox environment for `ctx_execute` and file processing isolates execution, preventing loaded data from acting as instructions.",{"category":120,"check":127,"severity":24,"summary":128},"Transitive Supply-Chain Grenades","The extension operates within a controlled environment and does not fetch remote code or markdown to be executed as instructions.",{"category":120,"check":130,"severity":24,"summary":131},"Sandbox Isolation","The extension explicitly runs commands in an isolated sandbox, processing stdout only and never modifying files outside its designated scope.",{"category":120,"check":133,"severity":24,"summary":134},"Sandbox escape primitives","The extension's design and documentation do not indicate any use of detached processes or retry loops around denied tool calls.",{"category":120,"check":136,"severity":24,"summary":137},"Data Exfiltration","The extension operates locally with no outbound calls for telemetry or data submission, and security configurations prevent sensitive data exposure.",{"category":120,"check":139,"severity":24,"summary":140},"Hidden Text Tricks","The bundled content is free of hidden steering tricks, control characters, or obfuscated instructions.",{"category":142,"check":143,"severity":24,"summary":144},"Hooks","Opaque code execution","The bundled scripts are plain, readable source code, with no obfuscation, base64 payloads, or runtime fetched code.",{"category":73,"check":146,"severity":24,"summary":147},"Structural Assumption","The extension makes no assumptions about user-specific project organization outside its defined operational scope and tools.",{"category":149,"check":150,"severity":24,"summary":151},"Trust","Issues Attention","The project shows high maintainer engagement with a strong ratio of closed to open issues, indicating active development and responsiveness.",{"category":153,"check":154,"severity":24,"summary":155},"Versioning","Release Management","The project clearly indicates meaningful versions via package.json and GitHub tags, ensuring clear detectability of new releases.",{"category":65,"check":157,"severity":24,"summary":158},"Validation","The extension's tools operate within sandboxed environments, implicitly handling input validation and sanitization through language-specific best practices and the overall MCP framework.",{"category":120,"check":160,"severity":24,"summary":161},"Unguarded Destructive Operations","The extension's tools are primarily analytical and do not perform destructive operations; any file mutations are handled by Bash commands subject to user's system permissions.",{"category":65,"check":163,"severity":24,"summary":164},"Error Handling","The design emphasizes capturing stdout and processing it intelligently, implying robust error handling within the execution environments and clear reporting.",{"category":65,"check":166,"severity":24,"summary":167},"Logging","The extension operates locally with no external telemetry; audit logs are handled by the host platform's session continuity features.",{"category":169,"check":170,"severity":24,"summary":171},"License","License usability","The extension is licensed under Elastic License 2.0, a source-available license that permits use, modification, and distribution with reasonable restrictions.",{"category":173,"check":174,"severity":24,"summary":175},"Maintenance","Commit recency","The project has recent commits within the last 12 months, indicating active maintenance and ongoing development.",{"category":173,"check":177,"severity":24,"summary":178},"Dependency Management","The project clearly documents build prerequisites and dependencies, with instructions for various platforms, suggesting robust management.",{"category":180,"check":52,"severity":24,"summary":181},"Type: skill","Long procedures are split into reference files, adhering to progressive disclosure principles.",{"category":180,"check":55,"severity":56,"summary":183},"The skill is a utility for context management, not an exploration tool requiring a forked context.",{"category":180,"check":66,"severity":56,"summary":185},"The skill does not rely on external MCP tools that would require fallbacks.",1778693586492,"This skill provides context-mode tools that replace standard Bash/cat commands for handling large outputs, ensuring that raw data stays within a sandboxed environment and never floods the LLM's context window. It offers session continuity, code-first data processing, and integrates with numerous AI platforms.",[189,190,191,192,193],"Sandbox tools for large output processing","Session continuity across context compaction","Code-first data processing paradigm","Support for multiple platforms and AI agents","Detailed documentation and usage examples",[195,196,197,198],"Acting as a cloud analytics dashboard","Collecting or syncing user data","Replacing Bash for simple, small-output commands","Providing AI-generated prose summaries directly (focuses on data processing)","3.0.0","4.4.0","To significantly enhance LLM performance and user productivity by optimizing context window usage and enabling efficient, sandboxed processing of large data volumes.","The extension is exceptionally well-documented, feature-rich, and prioritizes user privacy and security. Comprehensive installation instructions, clear examples, and extensive documentation on best practices contribute to a high-quality user experience. All checks passed with high severity.",99,"An essential utility for managing LLM context windows and processing large data efficiently.",[206,207,208,209,210,211],"context-management","llm-ops","productivity","developer-tools","sandboxing","code-analysis","global","verified",[215,216,217,218],"Analyzing large log files or API responses without token loss","Processing codebases or configuration files efficiently","Maintaining conversation state across context window shifts","Ensuring privacy by keeping data processing local",{"codeQuality":220,"collectedAt":222,"documentation":223,"maintenance":226,"popularity":233,"security":235,"testCoverage":237},{"hasLockfile":221},true,1778693567799,{"descriptionLength":224,"readmeSize":225},946,76711,{"closedIssues90d":227,"forks":228,"hasChangelog":229,"openIssues90d":230,"pushedAt":231,"stars":232},240,1027,false,5,1778685749000,14607,{"npmDownloads":234},73627,{"hasNpmPackage":221,"license":236,"smitheryVerified":229},"NOASSERTION",{"hasCi":221,"hasTests":221},{"updatedAt":239},1778693586612,{"basePath":241,"githubOwner":242,"githubRepo":13,"locale":18,"slug":13,"type":243},"skills/context-mode","mksglu","skill",{"_creationTime":245,"_id":246,"community":247,"display":248,"identity":251,"parentExtension":254,"providers":255,"relations":273,"tags":275,"workflow":276},1778693511416.3647,"k17ezy748es7sfnbnp9phht43h86m53y",{"reviewCount":8},{"description":249,"installMethods":250,"name":13,"sourceUrl":14},"MCP server that saves 98% of your context window with session continuity. Sandboxed code execution in 11 languages, FTS5 knowledge base with BM25 ranking, and automatic state restore across compactions.",{"claudeCode":13},{"basePath":252,"githubOwner":242,"githubRepo":13,"locale":18,"slug":13,"type":253},"","plugin",null,{"evaluate":256,"extract":267},{"promptVersionExtension":199,"promptVersionScoring":200,"score":257,"tags":258,"targetMarket":212,"tier":213},98,[259,260,261,262,263,264,265,266],"mcp","context-window","sandbox","code-execution","fts5","bm25","session-continuity","typescript",{"commitSha":268,"license":269,"plugin":270},"HEAD","Elastic-2.0",{"mcpCount":8,"provider":271,"skillCount":272},"classify",6,{"repoId":274},"kd764b2fctbqg4b8j8y6xvmkvs86m29m",[264,262,260,263,259,261,265,266],{"evaluatedAt":277,"extractAt":278,"updatedAt":279},1778693549024,1778693511416,1778693816974,{"evaluate":281,"extract":283},{"promptVersionExtension":199,"promptVersionScoring":200,"score":203,"tags":282,"targetMarket":212,"tier":213},[206,207,208,209,210,211],{"commitSha":268},{"parentExtensionId":246,"repoId":274},{"_creationTime":286,"_id":274,"identity":287,"providers":288,"workflow":568},1778693503750.4844,{"githubOwner":242,"githubRepo":13,"sourceUrl":14},{"classify":289,"discover":541,"extract":544,"github":545,"npm":567},{"commitSha":268,"extensions":290},[291,301,450,475,488,496,504,512,520,528],{"basePath":292,"displayName":13,"installMethods":293,"rationale":294,"selectedPaths":295,"source":299,"sourceLanguage":18,"type":300},".agents/plugins",{"claudeCode":12},"marketplace.json at .agents/plugins/marketplace.json (coalesced with duplicate marketplace at /)",[296],{"path":297,"priority":298},"marketplace.json","mandatory","rule","marketplace",{"basePath":252,"description":249,"displayName":13,"installMethods":302,"license":269,"rationale":303,"selectedPaths":304,"source":299,"sourceLanguage":18,"type":253},{"claudeCode":13},"plugin manifest at .claude-plugin/plugin.json",[305,307,309,312,315,317,319,321,323,325,328,330,332,334,336,338,340,342,344,346,348,350,352,354,356,358,360,362,364,366,368,370,372,374,376,378,380,382,384,386,388,390,392,394,396,398,400,402,404,406,408,410,412,414,416,418,420,422,424,426,428,430,432,434,436,438,440,442,444,446,448],{"path":306,"priority":298},".claude-plugin/plugin.json",{"path":308,"priority":298},"README.md",{"path":310,"priority":311},"LICENSE","high",{"path":313,"priority":314},"skills/context-mode/SKILL.md","medium",{"path":316,"priority":314},"skills/ctx-doctor/SKILL.md",{"path":318,"priority":314},"skills/ctx-insight/SKILL.md",{"path":320,"priority":314},"skills/ctx-purge/SKILL.md",{"path":322,"priority":314},"skills/ctx-stats/SKILL.md",{"path":324,"priority":314},"skills/ctx-upgrade/SKILL.md",{"path":326,"priority":327},"bin/statusline.mjs","low",{"path":329,"priority":311},"hooks/auto-injection.mjs",{"path":331,"priority":311},"hooks/cache-heal-utils.mjs",{"path":333,"priority":311},"hooks/codex/posttooluse.mjs",{"path":335,"priority":311},"hooks/codex/precompact.mjs",{"path":337,"priority":311},"hooks/codex/pretooluse.mjs",{"path":339,"priority":311},"hooks/codex/sessionstart.mjs",{"path":341,"priority":311},"hooks/codex/stop.mjs",{"path":343,"priority":311},"hooks/codex/userpromptsubmit.mjs",{"path":345,"priority":311},"hooks/core/formatters.mjs",{"path":347,"priority":311},"hooks/core/mcp-ready.mjs",{"path":349,"priority":311},"hooks/core/platform-detect.mjs",{"path":351,"priority":311},"hooks/core/routing.mjs",{"path":353,"priority":311},"hooks/core/stdin.mjs",{"path":355,"priority":311},"hooks/core/tool-naming.mjs",{"path":357,"priority":311},"hooks/cursor/afteragentresponse.mjs",{"path":359,"priority":311},"hooks/cursor/hooks.json",{"path":361,"priority":311},"hooks/cursor/posttooluse.mjs",{"path":363,"priority":311},"hooks/cursor/pretooluse.mjs",{"path":365,"priority":311},"hooks/cursor/sessionstart.mjs",{"path":367,"priority":311},"hooks/cursor/stop.mjs",{"path":369,"priority":311},"hooks/ensure-deps.mjs",{"path":371,"priority":311},"hooks/formatters/claude-code.mjs",{"path":373,"priority":311},"hooks/formatters/cursor.mjs",{"path":375,"priority":311},"hooks/formatters/gemini-cli.mjs",{"path":377,"priority":311},"hooks/formatters/vscode-copilot.mjs",{"path":379,"priority":311},"hooks/gemini-cli/aftertool.mjs",{"path":381,"priority":311},"hooks/gemini-cli/beforeagent.mjs",{"path":383,"priority":311},"hooks/gemini-cli/beforetool.mjs",{"path":385,"priority":311},"hooks/gemini-cli/precompress.mjs",{"path":387,"priority":311},"hooks/gemini-cli/sessionstart.mjs",{"path":389,"priority":311},"hooks/hooks.json",{"path":391,"priority":311},"hooks/jetbrains-copilot/posttooluse.mjs",{"path":393,"priority":311},"hooks/jetbrains-copilot/precompact.mjs",{"path":395,"priority":311},"hooks/jetbrains-copilot/pretooluse.mjs",{"path":397,"priority":311},"hooks/jetbrains-copilot/sessionstart.mjs",{"path":399,"priority":311},"hooks/kiro/agentspawn.mjs",{"path":401,"priority":311},"hooks/kiro/posttooluse.mjs",{"path":403,"priority":311},"hooks/kiro/pretooluse.mjs",{"path":405,"priority":311},"hooks/kiro/userpromptsubmit.mjs",{"path":407,"priority":311},"hooks/normalize-hooks.mjs",{"path":409,"priority":311},"hooks/posttooluse.mjs",{"path":411,"priority":311},"hooks/precompact.mjs",{"path":413,"priority":311},"hooks/pretooluse.mjs",{"path":415,"priority":311},"hooks/routing-block.mjs",{"path":417,"priority":311},"hooks/run-hook.mjs",{"path":419,"priority":311},"hooks/session-attribution.bundle.mjs",{"path":421,"priority":311},"hooks/session-db.bundle.mjs",{"path":423,"priority":311},"hooks/session-directive.mjs",{"path":425,"priority":311},"hooks/session-extract.bundle.mjs",{"path":427,"priority":311},"hooks/session-helpers.mjs",{"path":429,"priority":311},"hooks/session-loaders.mjs",{"path":431,"priority":311},"hooks/session-snapshot.bundle.mjs",{"path":433,"priority":311},"hooks/sessionstart.mjs",{"path":435,"priority":311},"hooks/suppress-stderr.mjs",{"path":437,"priority":311},"hooks/userpromptsubmit.mjs",{"path":439,"priority":311},"hooks/vscode-copilot/posttooluse.mjs",{"path":441,"priority":311},"hooks/vscode-copilot/precompact.mjs",{"path":443,"priority":311},"hooks/vscode-copilot/pretooluse.mjs",{"path":445,"priority":311},"hooks/vscode-copilot/sessionstart.mjs",{"path":447,"priority":311},".codex-plugin/plugin.json",{"path":449,"priority":311},".cursor-plugin/plugin.json",{"basePath":451,"description":452,"displayName":453,"installMethods":454,"rationale":455,"selectedPaths":456,"source":299,"sourceLanguage":18,"type":243},".claude/skills/context-mode-ops","Manage context-mode GitHub issues, PRs, releases, and marketing with parallel subagent army. Orchestrates 10-20 dynamic agents per task. Use when triaging issues, reviewing PRs, releasing versions, writing LinkedIn posts, announcing releases, fixing bugs, merging contributions, validating ENV vars, testing adapters, or syncing branches.","context-mode-ops",{"claudeCode":12},"SKILL.md frontmatter at .claude/skills/context-mode-ops/SKILL.md",[457,459,461,463,465,467,469,471,473],{"path":458,"priority":298},"SKILL.md",{"path":460,"priority":314},"agent-teams.md",{"path":462,"priority":314},"communication.md",{"path":464,"priority":314},"marketing.md",{"path":466,"priority":314},"release.md",{"path":468,"priority":314},"review-pr.md",{"path":470,"priority":314},"tdd.md",{"path":472,"priority":314},"triage-issue.md",{"path":474,"priority":314},"validation.md",{"basePath":241,"description":10,"displayName":13,"installMethods":476,"rationale":477,"selectedPaths":478,"source":299,"sourceLanguage":18,"type":243},{"claudeCode":12},"SKILL.md frontmatter at skills/context-mode/SKILL.md",[479,480,482,484,486],{"path":458,"priority":298},{"path":481,"priority":314},"references/anti-patterns.md",{"path":483,"priority":314},"references/patterns-javascript.md",{"path":485,"priority":314},"references/patterns-python.md",{"path":487,"priority":314},"references/patterns-shell.md",{"basePath":489,"description":490,"displayName":491,"installMethods":492,"rationale":493,"selectedPaths":494,"source":299,"sourceLanguage":18,"type":243},"skills/ctx-doctor","Run context-mode diagnostics. Checks runtimes, hooks, FTS5,\nplugin registration, npm and marketplace versions.\nTrigger: /context-mode:ctx-doctor\n","ctx-doctor",{"claudeCode":12},"SKILL.md frontmatter at skills/ctx-doctor/SKILL.md",[495],{"path":458,"priority":298},{"basePath":497,"description":498,"displayName":499,"installMethods":500,"rationale":501,"selectedPaths":502,"source":299,"sourceLanguage":18,"type":243},"skills/ctx-insight","Open the context-mode Insight analytics dashboard in the browser.\nShows personal metrics: session activity, tool usage, error rate,\nparallel work patterns, project focus, and actionable insights.\nFirst run installs dependencies (~30s). Subsequent runs open instantly.\nTrigger: /context-mode:ctx-insight\n","ctx-insight",{"claudeCode":12},"SKILL.md frontmatter at skills/ctx-insight/SKILL.md",[503],{"path":458,"priority":298},{"basePath":505,"description":506,"displayName":507,"installMethods":508,"rationale":509,"selectedPaths":510,"source":299,"sourceLanguage":18,"type":243},"skills/ctx-purge","Purge the context-mode knowledge base. Permanently deletes all indexed content\nand resets session stats. This is destructive and cannot be undone.\nTrigger: /context-mode:ctx-purge\n","ctx-purge",{"claudeCode":12},"SKILL.md frontmatter at skills/ctx-purge/SKILL.md",[511],{"path":458,"priority":298},{"basePath":513,"description":514,"displayName":515,"installMethods":516,"rationale":517,"selectedPaths":518,"source":299,"sourceLanguage":18,"type":243},"skills/ctx-stats","Show how much context window context-mode saved this session.\nDisplays token consumption, context savings ratio, and per-tool breakdown.\nRead-only — shows stats only, no reset capability.\nTo wipe the knowledge base entirely, use ctx_purge instead.\nTrigger: /context-mode:ctx-stats\n","ctx-stats",{"claudeCode":12},"SKILL.md frontmatter at skills/ctx-stats/SKILL.md",[519],{"path":458,"priority":298},{"basePath":521,"description":522,"displayName":523,"installMethods":524,"rationale":525,"selectedPaths":526,"source":299,"sourceLanguage":18,"type":243},"skills/ctx-upgrade","Update context-mode from GitHub and fix hooks/settings.\nPulls latest, builds, installs, updates npm global, configures hooks.\nTrigger: /context-mode:ctx-upgrade\n","ctx-upgrade",{"claudeCode":12},"SKILL.md frontmatter at skills/ctx-upgrade/SKILL.md",[527],{"path":458,"priority":298},{"basePath":252,"description":529,"displayName":13,"installMethods":530,"license":269,"rationale":531,"selectedPaths":532,"source":299,"sourceLanguage":18,"type":259},"MCP plugin that saves 98% of your context window. Works with Claude Code, Gemini CLI, VS Code Copilot, OpenCode, and Codex CLI. Sandboxed code execution, FTS5 knowledge base, and intent-driven search.",{"npm":13},"package.json @modelcontextprotocol/sdk dep + bin at package.json",[533,535,536,537,539],{"path":534,"priority":298},"package.json",{"path":308,"priority":298},{"path":310,"priority":311},{"path":538,"priority":314},"cli.bundle.mjs",{"path":540,"priority":327},"src/server.ts",{"sources":542},[543],"manual",{"npmPackage":13},{"closedIssues90d":227,"description":546,"forks":228,"homepage":547,"license":236,"openIssues90d":230,"pushedAt":231,"readmeSize":225,"stars":232,"topics":548},"Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 15 platforms","https://context-mode.com",[549,550,551,259,552,553,554,555,556,557,558,559,560,561,562,563,564,565,566,13],"claude","claude-code","claude-code-plugins","skills","codex","copilot","opencode","antigravity","kiro","openclaw","claude-code-hooks","claude-code-skill","codex-cli","cursor-plugin","mcp-server","mcp-tools","pi-agent","zed-extension",{"downloads":234},{"classifiedAt":569,"discoverAt":570,"extractAt":571,"githubAt":571,"npmAt":572,"updatedAt":569},1778693511234,1778693503750,1778693507197,1778693509704,[211,206,209,207,208,210],{"evaluatedAt":239,"extractAt":278,"updatedAt":575},1778693817516,[],[578,596,614,642,671,687],{"_creationTime":579,"_id":580,"community":581,"display":582,"identity":585,"providers":586,"relations":591,"tags":592,"workflow":593},1778693511416.3665,"k17fqs996gpd2bggec9k1qbbns86nh4g",{"reviewCount":8},{"description":522,"installMethods":583,"name":584,"sourceUrl":14},{"claudeCode":12},"Context Mode",{"basePath":521,"githubOwner":242,"githubRepo":13,"locale":18,"slug":523,"type":243},{"evaluate":587,"extract":590},{"promptVersionExtension":199,"promptVersionScoring":200,"score":588,"tags":589,"targetMarket":212,"tier":213},100,[206,207,262,265,208,259],{"commitSha":268,"license":236},{"parentExtensionId":246,"repoId":274},[262,206,207,259,208,265],{"evaluatedAt":594,"extractAt":278,"updatedAt":595},1778693713738,1778693818462,{"_creationTime":597,"_id":598,"community":599,"display":600,"identity":602,"providers":603,"relations":609,"tags":610,"workflow":611},1778693511416.3655,"k17dre81ghdhwnja4h61m340qd86m942",{"reviewCount":8},{"description":490,"installMethods":601,"name":491,"sourceUrl":14},{"claudeCode":12},{"basePath":489,"githubOwner":242,"githubRepo":13,"locale":18,"slug":491,"type":243},{"evaluate":604,"extract":608},{"promptVersionExtension":199,"promptVersionScoring":200,"score":588,"tags":605,"targetMarket":212,"tier":213},[206,209,208,606,607],"debugging","diagnostics",{"commitSha":268},{"parentExtensionId":246,"repoId":274},[206,606,209,607,208],{"evaluatedAt":612,"extractAt":278,"updatedAt":613},1778693603549,1778693817685,{"_creationTime":615,"_id":616,"community":617,"display":618,"identity":624,"providers":627,"relations":635,"tags":637,"workflow":638},1778699438912.8826,"k170fxxh22hdspg4vr94whgj1986mpr9",{"reviewCount":8},{"description":619,"installMethods":620,"name":622,"sourceUrl":623},"Context Runtime for AI Agents — 59 MCP tools, 10 read modes, 95+ shell patterns, tree-sitter AST for 18 languages. Compresses LLM context by up to 99%. Use when reading files, running shell commands, searching code, or exploring directories. Auto-installs if not present.",{"claudeCode":621},"yvgude/lean-ctx","lean-ctx","https://github.com/yvgude/lean-ctx",{"basePath":625,"githubOwner":626,"githubRepo":622,"locale":18,"slug":622,"type":243},"skills/lean-ctx","yvgude",{"evaluate":628,"extract":634},{"promptVersionExtension":199,"promptVersionScoring":200,"score":588,"tags":629,"targetMarket":212,"tier":213},[630,631,632,209,633,211],"context-compression","ai-agent","cli-tools","rust",{"commitSha":268},{"repoId":636},"kd7dxtfr9j3z54hs3bz0218e1n86may0",[631,632,211,630,209,633],{"evaluatedAt":639,"extractAt":640,"updatedAt":641},1778699456179,1778699438912,1778699517795,{"_creationTime":643,"_id":644,"community":645,"display":646,"identity":652,"providers":656,"relations":664,"tags":667,"workflow":668},1778696595410.5618,"k174h4yhwrcpcmdx62n2g2b88986mx17",{"reviewCount":8},{"description":647,"installMethods":648,"name":650,"sourceUrl":651},"Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team sizing, task decomposition, and when to use teams vs sub-agents vs worktrees.",{"claudeCode":649},"rohitg00/pro-workflow","agent-teams","https://github.com/rohitg00/pro-workflow",{"basePath":653,"githubOwner":654,"githubRepo":655,"locale":18,"slug":650,"type":243},"skills/agent-teams","rohitg00","pro-workflow",{"evaluate":657,"extract":663},{"promptVersionExtension":199,"promptVersionScoring":200,"score":588,"tags":658,"targetMarket":212,"tier":213},[659,660,661,207,208,662],"ai-workflow","collaboration","knowledge-management","self-correction",{"commitSha":268},{"parentExtensionId":665,"repoId":666},"k17fxtjcfh5gvxdrhv2dmgn1t986mdhv","kd7am4e918eq98hrd9s31jm4vs86nn0b",[659,660,661,207,208,662],{"evaluatedAt":669,"extractAt":670,"updatedAt":669},1778696637446,1778696595410,{"_creationTime":672,"_id":673,"community":674,"display":675,"identity":677,"providers":678,"relations":682,"tags":683,"workflow":684},1778693511416.3657,"k17bf3sgbyem7jcdeq0fg6mted86nzsk",{"reviewCount":8},{"description":498,"installMethods":676,"name":499,"sourceUrl":14},{"claudeCode":12},{"basePath":497,"githubOwner":242,"githubRepo":13,"locale":18,"slug":499,"type":243},{"evaluate":679,"extract":681},{"promptVersionExtension":199,"promptVersionScoring":200,"score":203,"tags":680,"targetMarket":212,"tier":213},[206,207,209,208,265],{"commitSha":268},{"parentExtensionId":246,"repoId":274},[206,209,207,208,265],{"evaluatedAt":685,"extractAt":278,"updatedAt":686},1778693624233,1778693817861,{"_creationTime":688,"_id":689,"community":690,"display":691,"identity":697,"providers":702,"relations":711,"tags":714,"workflow":715},1778695548458.377,"k17esa27yncbsd0bz8hcg2crg986mjqk",{"reviewCount":8},{"description":692,"installMethods":693,"name":695,"sourceUrl":696},"Extract the conceptual essence of a repository as skills, agents, and teams — the project's roles, procedures, and coordination patterns expressed as agentskills.io-standard definitions. Reads an arbitrary codebase and produces generalized definitions that capture WHAT the project does and WHO operates it, without replicating HOW it does it. Use when onboarding to a new codebase and wanting to understand its conceptual architecture, when bootstrapping an agentic system from an existing project, when studying a project's organizational DNA for cross-pollination, or when creating a skill/agent/team library inspired by a reference implementation.\n",{"claudeCode":694},"pjt222/agent-almanac","Metal","https://github.com/pjt222/agent-almanac",{"basePath":698,"githubOwner":699,"githubRepo":700,"locale":18,"slug":701,"type":243},"skills/metal","pjt222","agent-almanac","metal",{"evaluate":703,"extract":709},{"promptVersionExtension":199,"promptVersionScoring":200,"score":588,"tags":704,"targetMarket":212,"tier":213},[211,705,706,707,708],"conceptualization","agent-definition","repository-structure","software-architecture",{"commitSha":268,"license":710},"MIT",{"parentExtensionId":712,"repoId":713},"k170h0janaa9kwn7cfgfz2ykss86mmh9","kd7aryv63z61j39n2td1aeqkvh86mh12",[706,211,705,707,708],{"evaluatedAt":716,"extractAt":717,"updatedAt":716},1778699463464,1778695548458]