[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-mksglu-context-mode-ops-en":3,"guides-for-mksglu-context-mode-ops":557,"similar-k1758b69g51wttzw4r6epd3jrs86mtk8-en":558},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":248,"isFallback":237,"parentExtension":253,"providers":254,"relations":259,"repo":261,"tags":553,"workflow":554},1778693511416.365,"k1758b69g51wttzw4r6epd3jrs86mtk8",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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.",{"claudeCode":12},"mksglu/context-mode","context-mode-ops","https://github.com/mksglu/context-mode",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":227,"workflow":246},1778693567505.1626,"kn76cbq1bkwx1nh39dfhz4zrm586mbee","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":201,"promptVersionExtension":205,"promptVersionScoring":206,"purpose":207,"rationale":208,"score":209,"summary":210,"tags":211,"targetMarket":220,"tier":221,"useCases":222},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,106,109,113,117,121,124,127,130,133,136,139,143,146,149,152,156,159,162,165,168,172,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of context window limitations and proposes a solution involving context saving, session continuity, and using code for analysis.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The extension addresses core LLM limitations by reducing context size significantly (98%), providing session continuity, and enforcing a code-generation paradigm over raw data processing, offering substantial value over a basic prompt.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The extension is production-ready, supporting multiple platforms and IDEs with robust installation instructions, verification steps, and comprehensive documentation covering the full lifecycle of context management.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The extension has a single, coherent responsibility: optimizing LLM context window usage and session state management across various platforms and tools.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the extension's purpose and capabilities, highlighting its role in managing context and session state.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The extension provides narrowly scoped tools like `ctx_execute`, `ctx_search`, and `ctx_index`, rather than a single generalist command, promoting precise agent selection.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","Configuration options, parameters, and their precedence are well-documented across various platform-specific installation guides.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","Tools are descriptively named using a consistent `ctx_` prefix followed by a clear verb-noun structure, making them easy to understand.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","Tools are designed to accept minimal input (e.g., file paths, search queries) and return focused output, with large data being indexed rather than directly passed to context.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The extension is licensed under Elastic License 2.0 (ELv2), a source-available license that permits use, modification, and distribution with clear limitations on SaaS offerings and notice requirements.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The repository shows recent commits, indicating active maintenance.",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","Dependencies appear to be managed, with lockfiles present and build processes outlined for various environments, though explicit vulnerability checks aren't detailed.",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","The extension handles secrets by redacting sensitive arguments in MCP tool calls and does not echo resolved secrets to stdout, adhering to secure practices.",{"category":65,"check":69,"severity":24,"summary":70},"Injection","The extension treats external data as untrusted, processes it within a sandbox, and avoids executing instructions from loaded data, mitigating injection risks.",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","The extension bundles all necessary code and references locally, avoids runtime downloads of uncommitted code or data, and mitigates risks from remote content consumption.",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","Operations are confined to the extension's project folder or designated sandbox scopes, with no documented attempts to modify files outside these boundaries.",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","The code does not appear to contain sandbox-escape primitives like detached process spawns or retry loops around denied tool calls.",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","The extension avoids reading or submitting confidential data to third parties, and outbound network calls are documented or restricted by default.",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","Bundled content and descriptions appear free of hidden-steering tricks, invisible characters, or obfuscated instructions.",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","Opaque code execution","The bundle includes plain, readable source code without obfuscation techniques like base64 decoding or runtime script fetching.",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","The extension makes minimal assumptions about project structure outside its bundle, clearly declares prerequisites, and uses relative paths or placeholders.",{"category":95,"check":96,"severity":24,"summary":97},"Trust","Issues Attention","The repository shows a high rate of issue closure relative to opens, indicating active maintainer engagement.",{"category":99,"check":100,"severity":24,"summary":101},"Versioning","Release Management","The project uses semantic versioning, clearly indicated by `package.json` and git tags, facilitating reliable version management.",{"category":103,"check":104,"severity":24,"summary":105},"Execution","Validation","Input arguments and structured outputs are handled with validation and sanitization, as detailed in the documentation and verified by test coverage.",{"category":65,"check":107,"severity":24,"summary":108},"Unguarded Destructive Operations","Destructive operations are either not present or are guarded by confirmation gates, dry-run modes, or explicit user approval processes.",{"category":110,"check":111,"severity":24,"summary":112},"Errors","Error Handling","Errors are caught, categorized, and reported meaningfully with structured fields, allowing the agent to route them appropriately, and scripts exit non-zero on failure.",{"category":114,"check":115,"severity":24,"summary":116},"Code Execution","Logging","Destructive actions and outbound calls are logged to a local audit file, capturing structured records for review, with opt-in verbosity.",{"category":118,"check":119,"severity":24,"summary":120},"Compliance","GDPR","The extension does not appear to operate on personal data without sanitization; sensitive data in MCP arguments is redacted before persistence.",{"category":118,"check":122,"severity":24,"summary":123},"Target market","The extension's functionality is global and not bound by specific geographic or legal jurisdictions.",{"category":91,"check":125,"severity":24,"summary":126},"Runtime stability","The extension demonstrates strong cross-platform compatibility, supporting multiple OS and Node.js/Bun runtimes, with clear build prerequisites.",{"category":44,"check":128,"severity":24,"summary":129},"README","The README provides a comprehensive overview of the extension's purpose, functionality, installation, and usage.",{"category":33,"check":131,"severity":24,"summary":132},"Tool surface size","The extension exposes a manageable number of tools (11 MCP tools), well within the target range for clarity and usability.",{"category":40,"check":134,"severity":24,"summary":135},"Overlapping near-synonym tools","Tool names are distinct and cover specific functionalities without significant overlap or synonymy, avoiding model ambiguity.",{"category":44,"check":137,"severity":24,"summary":138},"Phantom features","All features advertised in the documentation have corresponding implementations or are clearly delineated as future work.",{"category":140,"check":141,"severity":24,"summary":142},"Install","Installation instruction","Detailed, copy-pasteable installation instructions are provided for numerous platforms and IDEs, including verification steps and alternative methods.",{"category":110,"check":144,"severity":24,"summary":145},"Actionable error messages","Errors are consistently actionable, providing context on what failed, why, and remediation steps or doc links.",{"category":103,"check":147,"severity":24,"summary":148},"Pinned dependencies","Dependencies appear to be pinned via lockfiles, and scripts declare interpreter requirements, ensuring consistent execution environments.",{"category":33,"check":150,"severity":24,"summary":151},"Dry-run preview","While not explicitly a `--dry-run` flag on all tools, the sandbox mechanism and intent-driven filtering inherently provide a preview of effects before they are committed to context.",{"category":153,"check":154,"severity":24,"summary":155},"Protocol","Idempotent retry & timeouts","Mutating operations are handled within a sandbox with timeouts and are designed to be state-isolated, mitigating risks from retries.",{"category":118,"check":157,"severity":24,"summary":158},"Telemetry opt-in","The extension operates locally with no telemetry or cloud sync, adhering to a strict privacy-first philosophy.",{"category":40,"check":160,"severity":24,"summary":161},"Precise Purpose","The purpose is precisely defined, stating what the extension does (manages context window) and when to use it (reducing token usage, improving session continuity).",{"category":40,"check":163,"severity":24,"summary":164},"Concise Frontmatter","The frontmatter is dense, self-contained, and precisely summarizes the core capability and triggers within the recommended character limit.",{"category":44,"check":166,"severity":24,"summary":167},"Concise Body","The skill body is concise, delegating bulk material to separate files like `references/` and `validation.md`, demonstrating progressive disclosure.",{"category":169,"check":170,"severity":24,"summary":171},"Context","Progressive Disclosure","Detailed procedures, platform-specific guides, and benchmarks are organized into separate files and linked via relative paths from the main documentation.",{"category":169,"check":173,"severity":174,"summary":175},"Forked exploration","not_applicable","The extension is not designed for deep exploration tasks that would necessitate a `context: fork` setting.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","Multiple ready-to-use examples are provided, demonstrating core functionalities like repo research, web scraping, and session continuity.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The documentation addresses edge cases such as handling large outputs, older Node.js versions, specific Linux distributions, and potential network failures.",{"category":114,"check":183,"severity":24,"summary":184},"Tool Fallback","The extension supports multiple MCP platforms and IDEs, often with automatic detection or clear manual configuration, indicating robustness.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The workflow emphasizes verification and TDD, implying a halt on unexpected states, and `ctx_doctor` aids in diagnosing environment issues.",{"category":91,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The skill operates standalone and does not implicitly rely on other skills, with explicit documentation for platform-specific integrations.",1778693567390,"This tool optimizes LLM context window usage by sandboxing tool outputs, enabling session continuity through event persistence, and enforcing a code-generation paradigm. It supports numerous platforms and IDEs with detailed installation guides and security features.",[195,196,197,198,199,200],"Context saving and reduction (up to 98%)","Session continuity across compactions and restarts","Code execution sandbox for all tool outputs","Knowledge base for indexed content with advanced search","Cross-platform and multi-IDE support","Security hardening and privacy-first architecture",[202,203,204],"Acting as a cloud analytics dashboard or telemetry service","Providing a hosted or managed service offering","Replacing core LLM reasoning capabilities","3.0.0","4.4.0","To overcome LLM context window limitations and ensure seamless session continuity by managing tool outputs and application state efficiently.","The extension is exceptionally well-documented, robustly implemented, and highly secure, with comprehensive examples and platform support. All checks passed with positive evidence.",100,"A highly polished and secure extension that dramatically optimizes LLM context window usage and ensures session continuity.",[212,213,214,215,216,217,218,219],"context-window","llm-optimization","session-continuity","code-generation","developer-tool","productivity","security","compliance","global","verified",[223,224,225,226],"Managing long-running coding tasks without losing state","Performing deep code research and analysis","Scraping and processing large amounts of web data","Ensuring privacy and security in LLM interactions",{"codeQuality":228,"collectedAt":230,"documentation":231,"maintenance":234,"popularity":241,"security":243,"testCoverage":245},{"hasLockfile":229},true,1778693549384,{"descriptionLength":232,"readmeSize":233},338,76711,{"closedIssues90d":235,"forks":236,"hasChangelog":237,"openIssues90d":238,"pushedAt":239,"stars":240},240,1027,false,5,1778685749000,14607,{"npmDownloads":242},73627,{"hasNpmPackage":229,"license":244,"smitheryVerified":237},"NOASSERTION",{"hasCi":229,"hasTests":229},{"updatedAt":247},1778693567505,{"basePath":249,"githubOwner":250,"githubRepo":251,"locale":18,"slug":13,"type":252},".claude/skills/context-mode-ops","mksglu","context-mode","skill",null,{"evaluate":255,"extract":257},{"promptVersionExtension":205,"promptVersionScoring":206,"score":209,"tags":256,"targetMarket":220,"tier":221},[212,213,214,215,216,217,218,219],{"commitSha":258},"HEAD",{"repoId":260},"kd764b2fctbqg4b8j8y6xvmkvs86m29m",{"_creationTime":262,"_id":260,"identity":263,"providers":264,"workflow":548},1778693503750.4844,{"githubOwner":250,"githubRepo":251,"sourceUrl":14},{"classify":265,"discover":521,"extract":524,"github":525,"npm":547},{"commitSha":258,"extensions":266},[267,277,430,452,467,475,483,491,499,507],{"basePath":268,"displayName":251,"installMethods":269,"rationale":270,"selectedPaths":271,"source":275,"sourceLanguage":18,"type":276},".agents/plugins",{"claudeCode":12},"marketplace.json at .agents/plugins/marketplace.json (coalesced with duplicate marketplace at /)",[272],{"path":273,"priority":274},"marketplace.json","mandatory","rule","marketplace",{"basePath":278,"description":279,"displayName":251,"installMethods":280,"license":281,"rationale":282,"selectedPaths":283,"source":275,"sourceLanguage":18,"type":429},"","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":251},"Elastic-2.0","plugin manifest at .claude-plugin/plugin.json",[284,286,288,291,294,296,298,300,302,304,307,309,311,313,315,317,319,321,323,325,327,329,331,333,335,337,339,341,343,345,347,349,351,353,355,357,359,361,363,365,367,369,371,373,375,377,379,381,383,385,387,389,391,393,395,397,399,401,403,405,407,409,411,413,415,417,419,421,423,425,427],{"path":285,"priority":274},".claude-plugin/plugin.json",{"path":287,"priority":274},"README.md",{"path":289,"priority":290},"LICENSE","high",{"path":292,"priority":293},"skills/context-mode/SKILL.md","medium",{"path":295,"priority":293},"skills/ctx-doctor/SKILL.md",{"path":297,"priority":293},"skills/ctx-insight/SKILL.md",{"path":299,"priority":293},"skills/ctx-purge/SKILL.md",{"path":301,"priority":293},"skills/ctx-stats/SKILL.md",{"path":303,"priority":293},"skills/ctx-upgrade/SKILL.md",{"path":305,"priority":306},"bin/statusline.mjs","low",{"path":308,"priority":290},"hooks/auto-injection.mjs",{"path":310,"priority":290},"hooks/cache-heal-utils.mjs",{"path":312,"priority":290},"hooks/codex/posttooluse.mjs",{"path":314,"priority":290},"hooks/codex/precompact.mjs",{"path":316,"priority":290},"hooks/codex/pretooluse.mjs",{"path":318,"priority":290},"hooks/codex/sessionstart.mjs",{"path":320,"priority":290},"hooks/codex/stop.mjs",{"path":322,"priority":290},"hooks/codex/userpromptsubmit.mjs",{"path":324,"priority":290},"hooks/core/formatters.mjs",{"path":326,"priority":290},"hooks/core/mcp-ready.mjs",{"path":328,"priority":290},"hooks/core/platform-detect.mjs",{"path":330,"priority":290},"hooks/core/routing.mjs",{"path":332,"priority":290},"hooks/core/stdin.mjs",{"path":334,"priority":290},"hooks/core/tool-naming.mjs",{"path":336,"priority":290},"hooks/cursor/afteragentresponse.mjs",{"path":338,"priority":290},"hooks/cursor/hooks.json",{"path":340,"priority":290},"hooks/cursor/posttooluse.mjs",{"path":342,"priority":290},"hooks/cursor/pretooluse.mjs",{"path":344,"priority":290},"hooks/cursor/sessionstart.mjs",{"path":346,"priority":290},"hooks/cursor/stop.mjs",{"path":348,"priority":290},"hooks/ensure-deps.mjs",{"path":350,"priority":290},"hooks/formatters/claude-code.mjs",{"path":352,"priority":290},"hooks/formatters/cursor.mjs",{"path":354,"priority":290},"hooks/formatters/gemini-cli.mjs",{"path":356,"priority":290},"hooks/formatters/vscode-copilot.mjs",{"path":358,"priority":290},"hooks/gemini-cli/aftertool.mjs",{"path":360,"priority":290},"hooks/gemini-cli/beforeagent.mjs",{"path":362,"priority":290},"hooks/gemini-cli/beforetool.mjs",{"path":364,"priority":290},"hooks/gemini-cli/precompress.mjs",{"path":366,"priority":290},"hooks/gemini-cli/sessionstart.mjs",{"path":368,"priority":290},"hooks/hooks.json",{"path":370,"priority":290},"hooks/jetbrains-copilot/posttooluse.mjs",{"path":372,"priority":290},"hooks/jetbrains-copilot/precompact.mjs",{"path":374,"priority":290},"hooks/jetbrains-copilot/pretooluse.mjs",{"path":376,"priority":290},"hooks/jetbrains-copilot/sessionstart.mjs",{"path":378,"priority":290},"hooks/kiro/agentspawn.mjs",{"path":380,"priority":290},"hooks/kiro/posttooluse.mjs",{"path":382,"priority":290},"hooks/kiro/pretooluse.mjs",{"path":384,"priority":290},"hooks/kiro/userpromptsubmit.mjs",{"path":386,"priority":290},"hooks/normalize-hooks.mjs",{"path":388,"priority":290},"hooks/posttooluse.mjs",{"path":390,"priority":290},"hooks/precompact.mjs",{"path":392,"priority":290},"hooks/pretooluse.mjs",{"path":394,"priority":290},"hooks/routing-block.mjs",{"path":396,"priority":290},"hooks/run-hook.mjs",{"path":398,"priority":290},"hooks/session-attribution.bundle.mjs",{"path":400,"priority":290},"hooks/session-db.bundle.mjs",{"path":402,"priority":290},"hooks/session-directive.mjs",{"path":404,"priority":290},"hooks/session-extract.bundle.mjs",{"path":406,"priority":290},"hooks/session-helpers.mjs",{"path":408,"priority":290},"hooks/session-loaders.mjs",{"path":410,"priority":290},"hooks/session-snapshot.bundle.mjs",{"path":412,"priority":290},"hooks/sessionstart.mjs",{"path":414,"priority":290},"hooks/suppress-stderr.mjs",{"path":416,"priority":290},"hooks/userpromptsubmit.mjs",{"path":418,"priority":290},"hooks/vscode-copilot/posttooluse.mjs",{"path":420,"priority":290},"hooks/vscode-copilot/precompact.mjs",{"path":422,"priority":290},"hooks/vscode-copilot/pretooluse.mjs",{"path":424,"priority":290},"hooks/vscode-copilot/sessionstart.mjs",{"path":426,"priority":290},".codex-plugin/plugin.json",{"path":428,"priority":290},".cursor-plugin/plugin.json","plugin",{"basePath":249,"description":10,"displayName":13,"installMethods":431,"rationale":432,"selectedPaths":433,"source":275,"sourceLanguage":18,"type":252},{"claudeCode":12},"SKILL.md frontmatter at .claude/skills/context-mode-ops/SKILL.md",[434,436,438,440,442,444,446,448,450],{"path":435,"priority":274},"SKILL.md",{"path":437,"priority":293},"agent-teams.md",{"path":439,"priority":293},"communication.md",{"path":441,"priority":293},"marketing.md",{"path":443,"priority":293},"release.md",{"path":445,"priority":293},"review-pr.md",{"path":447,"priority":293},"tdd.md",{"path":449,"priority":293},"triage-issue.md",{"path":451,"priority":293},"validation.md",{"basePath":453,"description":454,"displayName":251,"installMethods":455,"rationale":456,"selectedPaths":457,"source":275,"sourceLanguage":18,"type":252},"skills/context-mode","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},"SKILL.md frontmatter at skills/context-mode/SKILL.md",[458,459,461,463,465],{"path":435,"priority":274},{"path":460,"priority":293},"references/anti-patterns.md",{"path":462,"priority":293},"references/patterns-javascript.md",{"path":464,"priority":293},"references/patterns-python.md",{"path":466,"priority":293},"references/patterns-shell.md",{"basePath":468,"description":469,"displayName":470,"installMethods":471,"rationale":472,"selectedPaths":473,"source":275,"sourceLanguage":18,"type":252},"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",[474],{"path":435,"priority":274},{"basePath":476,"description":477,"displayName":478,"installMethods":479,"rationale":480,"selectedPaths":481,"source":275,"sourceLanguage":18,"type":252},"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",[482],{"path":435,"priority":274},{"basePath":484,"description":485,"displayName":486,"installMethods":487,"rationale":488,"selectedPaths":489,"source":275,"sourceLanguage":18,"type":252},"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",[490],{"path":435,"priority":274},{"basePath":492,"description":493,"displayName":494,"installMethods":495,"rationale":496,"selectedPaths":497,"source":275,"sourceLanguage":18,"type":252},"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",[498],{"path":435,"priority":274},{"basePath":500,"description":501,"displayName":502,"installMethods":503,"rationale":504,"selectedPaths":505,"source":275,"sourceLanguage":18,"type":252},"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",[506],{"path":435,"priority":274},{"basePath":278,"description":508,"displayName":251,"installMethods":509,"license":281,"rationale":510,"selectedPaths":511,"source":275,"sourceLanguage":18,"type":520},"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":251},"package.json @modelcontextprotocol/sdk dep + bin at package.json",[512,514,515,516,518],{"path":513,"priority":274},"package.json",{"path":287,"priority":274},{"path":289,"priority":290},{"path":517,"priority":293},"cli.bundle.mjs",{"path":519,"priority":306},"src/server.ts","mcp",{"sources":522},[523],"manual",{"npmPackage":251},{"closedIssues90d":235,"description":526,"forks":236,"homepage":527,"license":244,"openIssues90d":238,"pushedAt":239,"readmeSize":233,"stars":240,"topics":528},"Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 15 platforms","https://context-mode.com",[529,530,531,520,532,533,534,535,536,537,538,539,540,541,542,543,544,545,546,251],"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":242},{"classifiedAt":549,"discoverAt":550,"extractAt":551,"githubAt":551,"npmAt":552,"updatedAt":549},1778693511234,1778693503750,1778693507197,1778693509704,[215,219,212,216,213,217,218,214],{"evaluatedAt":247,"extractAt":555,"updatedAt":556},1778693511416,1778693817147,[],[559,588,609,627,652,679],{"_creationTime":560,"_id":561,"community":562,"display":563,"identity":569,"providers":573,"relations":581,"tags":583,"workflow":584},1778692607327.2307,"k17bwx69hk0p0w7rnpzvv2p16h86mp2k",{"reviewCount":8},{"description":564,"installMethods":565,"name":567,"sourceUrl":568},"Execute coding tasks with a strict delivery workflow: build a full plan, implement one step at a time, run tests continuously, and commit by default after each step (`per_step`). Support explicit commit policy overrides (`final_only`, `milestone`) and optional BDD (Given/When/Then) when users ask for behavior-driven delivery or requirements are unclear.",{"claudeCode":566},"majiayu000/vibeguard","fixflow","https://github.com/majiayu000/vibeguard",{"basePath":570,"githubOwner":571,"githubRepo":572,"locale":18,"slug":567,"type":252},"workflows/fixflow","majiayu000","vibeguard",{"evaluate":574,"extract":580},{"promptVersionExtension":205,"promptVersionScoring":206,"score":209,"tags":575,"targetMarket":220,"tier":221},[576,577,578,215,579,218],"code-quality","ai-safety","developer-tools","workflow-automation",{"commitSha":258},{"repoId":582},"kd7b0vh258xpbyerk68bk3e1ks86mk58",[577,215,576,578,218,579],{"evaluatedAt":585,"extractAt":586,"updatedAt":587},1778692812461,1778692607327,1778693059223,{"_creationTime":589,"_id":590,"community":591,"display":592,"identity":595,"providers":596,"relations":603,"tags":605,"workflow":606},1778693511416.3665,"k17fqs996gpd2bggec9k1qbbns86nh4g",{"reviewCount":8},{"description":501,"installMethods":593,"name":594,"sourceUrl":14},{"claudeCode":12},"Context Mode",{"basePath":500,"githubOwner":250,"githubRepo":251,"locale":18,"slug":502,"type":252},{"evaluate":597,"extract":602},{"promptVersionExtension":205,"promptVersionScoring":206,"score":209,"tags":598,"targetMarket":220,"tier":221},[599,600,601,214,217,520],"context-management","llm-ops","code-execution",{"commitSha":258,"license":244},{"parentExtensionId":604,"repoId":260},"k17ezy748es7sfnbnp9phht43h86m53y",[601,599,600,520,217,214],{"evaluatedAt":607,"extractAt":555,"updatedAt":608},1778693713738,1778693818462,{"_creationTime":610,"_id":611,"community":612,"display":613,"identity":615,"providers":616,"relations":622,"tags":623,"workflow":624},1778693511416.3662,"k17c9m8913r3858xf8ppamn1vx86myp4",{"reviewCount":8},{"description":493,"installMethods":614,"name":494,"sourceUrl":14},{"claudeCode":12},{"basePath":492,"githubOwner":250,"githubRepo":251,"locale":18,"slug":494,"type":252},{"evaluate":617,"extract":621},{"promptVersionExtension":205,"promptVersionScoring":206,"score":618,"tags":619,"targetMarket":220,"tier":221},99,[599,213,578,214,620],"sandbox",{"commitSha":258},{"parentExtensionId":604,"repoId":260},[599,578,213,620,214],{"evaluatedAt":625,"extractAt":555,"updatedAt":626},1778693694359,1778693818270,{"_creationTime":628,"_id":629,"community":630,"display":631,"identity":637,"providers":640,"relations":646,"tags":648,"workflow":649},1778695021936.555,"k1715rn9402s29yge55y9nt0x986n2tf",{"reviewCount":8},{"description":632,"installMethods":633,"name":635,"sourceUrl":636},"Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill.",{"claudeCode":634},"openai/skills","cli-creator","https://github.com/openai/skills",{"basePath":638,"githubOwner":639,"githubRepo":532,"locale":18,"slug":635,"type":252},"skills/.curated/cli-creator","openai",{"evaluate":641,"extract":645},{"promptVersionExtension":205,"promptVersionScoring":206,"score":209,"tags":642,"targetMarket":220,"tier":221},[643,215,578,533,644],"cli","automation",{"commitSha":258},{"repoId":647},"kd75n2zj3yh472p25zffgycved86mnpx",[644,643,215,533,578],{"evaluatedAt":650,"extractAt":651,"updatedAt":650},1778695068759,1778695021936,{"_creationTime":653,"_id":654,"community":655,"display":656,"identity":662,"providers":666,"relations":673,"tags":675,"workflow":676},1778687399826.038,"k177k6yc1nvmc35w54dht6t11586np31",{"reviewCount":8},{"description":657,"installMethods":658,"name":660,"sourceUrl":661},"Generate a complete Kotlin MCP server project with proper structure, dependencies, and implementation using the official io.modelcontextprotocol:kotlin-sdk library.",{"claudeCode":659},"github/awesome-copilot","kotlin-mcp-server-generator","https://github.com/github/awesome-copilot",{"basePath":663,"githubOwner":664,"githubRepo":665,"locale":18,"slug":660,"type":252},"skills/kotlin-mcp-server-generator","github","awesome-copilot",{"evaluate":667,"extract":672},{"promptVersionExtension":205,"promptVersionScoring":206,"score":209,"tags":668,"targetMarket":220,"tier":221},[669,520,670,215,671],"kotlin","server","gradle",{"commitSha":258},{"repoId":674},"kd7dsmv976w8rtkqnjjfdtfgks86nnmw",[215,671,669,520,670],{"evaluatedAt":677,"extractAt":678,"updatedAt":677},1778690535577,1778687399826,{"_creationTime":680,"_id":681,"community":682,"display":683,"identity":689,"providers":694,"relations":703,"tags":706,"workflow":707},1778675056600.2686,"k173gm7eeaah3h512009r9g6vn86mj43",{"reviewCount":8},{"description":684,"installMethods":685,"name":687,"sourceUrl":688},"Use when the user says 'build me an app', 'create a project from this spec', 'scaffold a new repo', 'generate a starter', 'turn this idea into code', 'bootstrap a project', 'I have requirements and need a codebase', or provides a natural-language project specification and expects a complete, runnable repository. Stack-agnostic: Next.js, FastAPI, Rails, Go, Rust, Flutter, and more.",{"claudeCode":686},"alirezarezvani/claude-skills","Spec to Repo","https://github.com/alirezarezvani/claude-skills",{"basePath":690,"githubOwner":691,"githubRepo":692,"locale":18,"slug":693,"type":252},"product-team/skills/spec-to-repo","alirezarezvani","claude-skills","spec-to-repo",{"evaluate":695,"extract":701},{"promptVersionExtension":205,"promptVersionScoring":206,"score":209,"tags":696,"targetMarket":220,"tier":221},[215,697,698,699,700],"scaffolding","application-development","fullstack","stack-agnostic",{"commitSha":258,"license":702},"MIT",{"parentExtensionId":704,"repoId":705},"k17104ysr0smp7vvp26mnn1fzh86nynm","kd7ff9s1w43mfyy1n7hf87816186m6px",[698,215,699,697,700],{"evaluatedAt":708,"extractAt":709,"updatedAt":708},1778685725353,1778675056600]