[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-thedotmack-mem-search-en":3,"guides-for-thedotmack-mem-search":464,"similar-k1790kka1gerjkd8t2y1bfct6586ne6s-en":465},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":260,"isFallback":241,"parentExtension":266,"providers":267,"relations":272,"repo":274,"tags":460,"workflow":461},1778698056313.1526,"k1790kka1gerjkd8t2y1bfct6586ne6s",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Search claude-mem's persistent cross-session memory database. Use when user asks \"did we already solve this?\", \"how did we do X last time?\", or needs work from previous sessions.",{"claudeCode":12},"thedotmack/claude-mem","Claude-Mem","https://github.com/thedotmack/claude-mem",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":239,"workflow":258},1778698211608.3833,"kn79dhwkjhk2r4v7yn8b6h9rmh86mkgh","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"practices":205,"prerequisites":209,"promptVersionExtension":214,"promptVersionScoring":215,"purpose":216,"rationale":217,"score":218,"summary":219,"tags":220,"targetMarket":226,"tier":227,"useCases":228,"workflow":233},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,106,109,112,115,119,122,125,128,131,134,137,141,145,149,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of remembering past work and sessions, and provides specific example user questions.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The extension offers a persistent memory database and specific tools for searching and retrieving past work, going beyond basic LLM context.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The extension provides a complete workflow for searching, filtering, and fetching past observations, covering the full lifecycle of retrieving historical context.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The extension focuses solely on persistent memory search and retrieval, without introducing unrelated capabilities.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the extension's functionality as described in the SKILL.md and README.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The extension exposes narrow verb-noun tools (`search`, `timeline`, `get_observations`) for specific memory operations.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","All parameters for the MCP tools are clearly documented in the SKILL.md, including defaults where applicable.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","Tool names (`search`, `timeline`, `get_observations`) are descriptive and adhere to the verb-noun convention.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","Tool parameters are specific and documented, and responses are focused on the requested data without excessive diagnostic information.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The extension is licensed under Apache-2.0, as indicated by the LICENSE file and README.",{"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","The project utilizes `package.json` and `npm`, and the installation instructions suggest `npx claude-mem install`, implying standard dependency management practices. Automatic installation handles dependencies.",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","The extension does not appear to handle or expose secrets in its core functionality; it operates on user-provided data and metadata.",{"category":65,"check":69,"severity":24,"summary":70},"Injection","The extension's tools operate on structured queries and IDs, and the SKILL.md emphasizes treating search results as data, mitigating injection risks.",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","The installation process uses `npx` which is standard, and the code does not appear to fetch or execute arbitrary remote code at runtime.",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","The extension operates within the Claude Code environment and interacts with its database and tools; no evidence of writing outside designated scopes or to sensitive system paths.",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","No evidence of detached process spawns or retry loops around denied tool calls was found in the provided code snippets.",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","The extension's purpose is to store and retrieve user's past work within their own environment, with no indication of sending this data to third parties.",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","The bundled files and documentation appear to be free of hidden text tricks or malicious steering instructions.",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","Opaque code execution","The code appears to be standard TypeScript/JavaScript, with no evidence of obfuscation, base64 payloads, or runtime script fetching.",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","The extension assumes a standard Claude Code environment and tool availability but does not make assumptions about user project file structure outside its own scope.",{"category":95,"check":96,"severity":24,"summary":97},"Trust","Issues Attention","The repository has a high rate of issue closure relative to open issues, indicating good maintainer responsiveness.",{"category":99,"check":100,"severity":24,"summary":101},"Versioning","Release Management","The extension has a clear version number (6.5.0) in the README and `package.json`, and installation methods allow for version pinning.",{"category":103,"check":104,"severity":24,"summary":105},"Code Execution","Validation","Tool parameters are documented and specific, implying validation within the MCP framework. The workflow emphasizes filtering before fetching, suggesting a degree of data validation.",{"category":65,"check":107,"severity":24,"summary":108},"Unguarded Destructive Operations","The extension is primarily read-only concerning user data; its operations involve searching and retrieving, not destructive actions.",{"category":103,"check":110,"severity":24,"summary":111},"Error Handling","The SKILL.md describes a structured workflow and emphasizes filtering before fetching details, implying robust error handling to prevent excessive API calls.",{"category":103,"check":113,"severity":24,"summary":114},"Logging","The documentation mentions logging settings and an audit log feature for reviewing actions, indicating proper logging practices.",{"category":116,"check":117,"severity":24,"summary":118},"Compliance","GDPR","The extension operates on user's past work and session data, not personal data from external sources. Sensitive content can be excluded via private tags.",{"category":116,"check":120,"severity":24,"summary":121},"Target market","The extension is designed for use with Claude Code and its tools, making it globally applicable without specific regional restrictions.",{"category":91,"check":123,"severity":24,"summary":124},"Runtime stability","The extension targets the Claude Code environment and standard Node.js/Bun runtimes, with clear setup notes for Windows, indicating multi-platform compatibility.",{"category":44,"check":126,"severity":24,"summary":127},"README","The README is comprehensive, well-structured, and clearly states the extension's purpose, features, and usage.",{"category":33,"check":129,"severity":24,"summary":130},"Tool surface size","The extension exposes three core MCP tools, which is a manageable and focused surface area.",{"category":40,"check":132,"severity":24,"summary":133},"Overlapping near-synonym tools","The tools (`search`, `timeline`, `get_observations`) have distinct purposes and do not appear to overlap as near-synonyms.",{"category":44,"check":135,"severity":24,"summary":136},"Phantom features","All advertised features, including persistent memory, search tools, and workflow, are implemented and documented.",{"category":138,"check":139,"severity":24,"summary":140},"Install","Installation instruction","Clear, copy-pasteable installation instructions are provided for various environments (npx, Gemini CLI, OpenCode, plugin marketplace) along with verification steps.",{"category":142,"check":143,"severity":24,"summary":144},"Errors","Actionable error messages","While specific error message formats aren't detailed, the structured workflow and documentation imply clear error reporting and recovery guidance.",{"category":146,"check":147,"severity":24,"summary":148},"Execution","Pinned dependencies","The use of `package.json` and `npx` for installation implies pinned dependencies managed by npm/Bun.",{"category":33,"check":150,"severity":151,"summary":152},"Dry-run preview","not_applicable","The extension is primarily for retrieving information and does not perform destructive operations that would require a dry-run mode.",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","The workflow emphasizes filtering before fetching and batching requests, suggesting a design that supports idempotency and efficient retries. Specific timeouts are not detailed but are typically managed by the underlying MCP framework.",{"category":116,"check":158,"severity":24,"summary":159},"Telemetry opt-in","The documentation mentions configuration for logging and data handling, implying control over telemetry, and no opt-out telemetry is evident.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The description clearly states the purpose (search memory database) and usage scenarios (asking about past work, previous sessions) with explicit triggers.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The frontmatter in SKILL.md is concise and effectively summarizes the extension's core capability and purpose.",{"category":44,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md is well-structured and delegates detailed information to external documentation links, keeping the main file concise.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","The SKILL.md outlines the main workflow and links to the full documentation for deeper dives, demonstrating progressive disclosure.",{"category":170,"check":174,"severity":151,"summary":175},"Forked exploration","This skill is focused on querying existing data and does not involve deep exploration that would require forked context.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","Multiple clear, end-to-end examples are provided in the SKILL.md and README, demonstrating invocation and expected outcomes.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The SKILL.md outlines a clear workflow with parameters and potential filters, implying handling of various search scenarios, and the documentation covers troubleshooting.",{"category":103,"check":183,"severity":151,"summary":184},"Tool Fallback","The extension relies on Claude Code's internal MCP tools and does not depend on external MCP servers that would require a fallback.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The structured workflow and emphasis on filtering before fetching suggest that unexpected states would halt the process gracefully with clear reporting.",{"category":91,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The skill operates independently on its memory database and does not appear to rely on other specific skills being loaded concurrently.",1778698211503,"This extension provides a persistent cross-session memory database for Claude Code, enabling users to search and retrieve past work, observations, and prompts. It uses a three-layer MCP tool workflow (search, timeline, get_observations) to efficiently query historical data and includes features like project filtering and chronological context retrieval.",[195,196,197,198,199],"Persistent cross-session memory storage","Advanced search and filtering capabilities","Chronological timeline retrieval around observations","Efficient token usage via progressive disclosure workflow","Integration with Claude Code and MCP tools",[201,202,203,204],"Acting as a general-purpose task manager","Storing real-time conversation context","Replacing the primary Claude Code conversation history","Providing project management or bug tracking features",[206,207,208],"Memory management","Search indexing","Context retrieval",[210,211,212,213],"Node.js 18.0.0 or higher","Claude Code with plugin support","Bun (auto-installed if missing)","uv (auto-installed if missing)","3.0.0","4.4.0","To allow Claude Code users to easily recall and leverage past work and knowledge across different sessions, improving continuity and reducing redundant effort.","The extension is exceptionally well-documented and practical, with a clear purpose, well-defined tools, and robust examples. It adheres to best practices for security, maintainability, and user experience, leading to a very high trust score.",99,"A high-quality extension for persistent memory search, offering clear utility and robust implementation.",[221,222,223,224,225],"memory","search","context","persistence","claude-code","global","verified",[229,230,231,232],"Recalling solutions to previously encountered problems","Reviewing past project decisions and discoveries","Finding specific information from previous work sessions","Maintaining context across long-term projects",[234,235,236,237,238],"Search memory index for relevant observations using `search` tool.","Filter results by query, type, date, project, etc.","Use `timeline` tool to get chronological context around interesting results.","Select relevant observation IDs based on search and timeline context.","Fetch full details of selected observations using `get_observations` tool.",{"codeQuality":240,"collectedAt":242,"documentation":243,"maintenance":246,"popularity":252,"security":254,"testCoverage":257},{"hasLockfile":241},false,1778698195953,{"descriptionLength":244,"readmeSize":245},178,17010,{"closedIssues90d":247,"forks":248,"hasChangelog":241,"openIssues90d":249,"pushedAt":250,"stars":251},781,6488,53,1778643518000,75457,{"npmDownloads":253},124555,{"hasNpmPackage":255,"license":256,"smitheryVerified":241},true,"Apache-2.0",{"hasCi":255,"hasTests":255},{"updatedAt":259},1778698211608,{"basePath":261,"githubOwner":262,"githubRepo":263,"locale":18,"slug":264,"type":265},"plugin/skills/mem-search","thedotmack","claude-mem","mem-search","skill",null,{"evaluate":268,"extract":270},{"promptVersionExtension":214,"promptVersionScoring":215,"score":218,"tags":269,"targetMarket":226,"tier":227},[221,222,223,224,225],{"commitSha":271,"license":256},"HEAD",{"repoId":273},"kd70jnxgm695az2wtf37zbqdj986mp7k",{"_creationTime":275,"_id":273,"identity":276,"providers":277,"workflow":455},1778698049260.0457,{"githubOwner":262,"githubRepo":263,"sourceUrl":14},{"classify":278,"discover":427,"extract":430,"github":431,"npm":454},{"commitSha":271,"extensions":279},[280,291,304,318,327,335,346,354,362,370,375,383,391,399,410,418],{"basePath":281,"displayName":282,"installMethods":283,"rationale":284,"selectedPaths":285,"source":289,"sourceLanguage":18,"type":290},".agents/plugins","claude-mem-local",{"claudeCode":12},"marketplace.json at .agents/plugins/marketplace.json",[286],{"path":287,"priority":288},"marketplace.json","mandatory","rule","marketplace",{"basePath":292,"description":293,"displayName":262,"installMethods":294,"rationale":295,"selectedPaths":296,"source":289,"sourceLanguage":18,"type":290},"","Plugins by Alex Newman (thedotmack)",{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[297,299,301],{"path":298,"priority":288},".claude-plugin/marketplace.json",{"path":300,"priority":288},"README.md",{"path":302,"priority":303},"LICENSE","high",{"basePath":292,"description":305,"displayName":263,"installMethods":306,"license":256,"rationale":307,"selectedPaths":308,"source":289,"sourceLanguage":18,"type":317},"Memory compression system for Claude Code - persist context across sessions",{"claudeCode":263},"plugin manifest at .claude-plugin/plugin.json (coalesced with duplicate plugin at plugin)",[309,311,312,313,315],{"path":310,"priority":288},".claude-plugin/plugin.json",{"path":300,"priority":288},{"path":302,"priority":303},{"path":314,"priority":288},".mcp.json",{"path":316,"priority":303},".codex-plugin/plugin.json","plugin",{"basePath":319,"description":320,"displayName":321,"installMethods":322,"rationale":323,"selectedPaths":324,"source":289,"sourceLanguage":18,"type":265},"plugin/skills/babysit","Watch a pull request or review cycle until it is ready to merge. Use when asked to babysit, monitor, or keep checking PR comments, reviews, and CI until all actionable issues are resolved.","babysit",{"claudeCode":12},"SKILL.md frontmatter at plugin/skills/babysit/SKILL.md",[325],{"path":326,"priority":288},"SKILL.md",{"basePath":328,"description":329,"displayName":330,"installMethods":331,"rationale":332,"selectedPaths":333,"source":289,"sourceLanguage":18,"type":265},"plugin/skills/do","Execute a phased implementation plan using subagents. Use when asked to execute, run, or carry out a plan — especially one created by make-plan.","do",{"claudeCode":12},"SKILL.md frontmatter at plugin/skills/do/SKILL.md",[334],{"path":326,"priority":288},{"basePath":336,"description":337,"displayName":338,"installMethods":339,"rationale":340,"selectedPaths":341,"source":289,"sourceLanguage":18,"type":265},"plugin/skills/how-it-works","Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks \"how does claude-mem work?\" or \"what is this thing doing?\".","how-it-works",{"claudeCode":12},"SKILL.md frontmatter at plugin/skills/how-it-works/SKILL.md",[342,343],{"path":326,"priority":288},{"path":344,"priority":345},"onboarding-explainer.md","medium",{"basePath":347,"description":348,"displayName":349,"installMethods":350,"rationale":351,"selectedPaths":352,"source":289,"sourceLanguage":18,"type":265},"plugin/skills/knowledge-agent","Build and query AI-powered knowledge bases from claude-mem observations. Use when users want to create focused \"brains\" from their observation history, ask questions about past work patterns, or compile expertise on specific topics.","knowledge-agent",{"claudeCode":12},"SKILL.md frontmatter at plugin/skills/knowledge-agent/SKILL.md",[353],{"path":326,"priority":288},{"basePath":355,"description":356,"displayName":357,"installMethods":358,"rationale":359,"selectedPaths":360,"source":289,"sourceLanguage":18,"type":265},"plugin/skills/learn-codebase","Prime a codebase by reading every source file in full. Use when starting work on a new or unfamiliar project, or when the user asks to \"learn the codebase\", \"read the codebase\", \"prime\", or \"get up to speed\".","learn-codebase",{"claudeCode":12},"SKILL.md frontmatter at plugin/skills/learn-codebase/SKILL.md",[361],{"path":326,"priority":288},{"basePath":363,"description":364,"displayName":365,"installMethods":366,"rationale":367,"selectedPaths":368,"source":289,"sourceLanguage":18,"type":265},"plugin/skills/make-plan","Create a detailed, phased implementation plan with documentation discovery. Use when asked to plan a feature, task, or multi-step implementation — especially before executing with do.","make-plan",{"claudeCode":12},"SKILL.md frontmatter at plugin/skills/make-plan/SKILL.md",[369],{"path":326,"priority":288},{"basePath":261,"description":10,"displayName":264,"installMethods":371,"rationale":372,"selectedPaths":373,"source":289,"sourceLanguage":18,"type":265},{"claudeCode":12},"SKILL.md frontmatter at plugin/skills/mem-search/SKILL.md",[374],{"path":326,"priority":288},{"basePath":376,"description":377,"displayName":378,"installMethods":379,"rationale":380,"selectedPaths":381,"source":289,"sourceLanguage":18,"type":265},"plugin/skills/pathfinder","Map a codebase into feature-grouped flowcharts, identify duplicated concerns across features, and propose a unified architecture. Use when asked to \"find the ideal path,\" unify duplicated systems, or audit architecture before a refactor. Emits a proposed unified flowchart plus per-system /make-plan prompts.","pathfinder",{"claudeCode":12},"SKILL.md frontmatter at plugin/skills/pathfinder/SKILL.md",[382],{"path":326,"priority":288},{"basePath":384,"description":385,"displayName":386,"installMethods":387,"rationale":388,"selectedPaths":389,"source":289,"sourceLanguage":18,"type":265},"plugin/skills/smart-explore","Token-optimized structural code search using tree-sitter AST parsing. Use instead of reading full files when you need to understand code structure, find functions, or explore a codebase efficiently.","smart-explore",{"claudeCode":12},"SKILL.md frontmatter at plugin/skills/smart-explore/SKILL.md",[390],{"path":326,"priority":288},{"basePath":392,"description":393,"displayName":394,"installMethods":395,"rationale":396,"selectedPaths":397,"source":289,"sourceLanguage":18,"type":265},"plugin/skills/timeline-report","Generate a \"Journey Into [Project]\" narrative report analyzing a project's entire development history from claude-mem's timeline. Use when asked for a timeline report, project history analysis, development journey, or full project report.","timeline-report",{"claudeCode":12},"SKILL.md frontmatter at plugin/skills/timeline-report/SKILL.md",[398],{"path":326,"priority":288},{"basePath":400,"description":401,"displayName":402,"installMethods":403,"rationale":404,"selectedPaths":405,"source":289,"sourceLanguage":18,"type":265},"plugin/skills/version-bump","Automated semantic versioning and release workflow for Claude Code plugins. Handles version increments across package.json, marketplace.json, plugin.json manifests, npm publishing (so `npx claude-mem@X.Y.Z` resolves), build verification, git tagging, GitHub releases, and changelog generation.","claude-code-plugin-release",{"claudeCode":12},"SKILL.md frontmatter at plugin/skills/version-bump/SKILL.md",[406,407],{"path":326,"priority":288},{"path":408,"priority":409},"scripts/generate_changelog.js","low",{"basePath":411,"description":412,"displayName":413,"installMethods":414,"rationale":415,"selectedPaths":416,"source":289,"sourceLanguage":18,"type":265},"plugin/skills/wowerpoint","Turn one document into a kawaii NotebookLM slide-deck PDF. Use for \"wowerpoint this\", \"make a deck about \u003Cfile>\", \"turn this report into slides\", or any request to render a single document as shareable narrative slides.","wowerpoint",{"claudeCode":12},"SKILL.md frontmatter at plugin/skills/wowerpoint/SKILL.md",[417],{"path":326,"priority":288},{"basePath":292,"description":305,"displayName":263,"installMethods":419,"license":256,"rationale":420,"selectedPaths":421,"source":289,"sourceLanguage":18,"type":426},{"npm":263},"package.json @modelcontextprotocol/sdk dep + bin at package.json",[422,424,425],{"path":423,"priority":288},"package.json",{"path":300,"priority":288},{"path":302,"priority":303},"mcp",{"sources":428},[429],"manual",{"npmPackage":263},{"closedIssues90d":247,"description":432,"forks":248,"homepage":433,"license":256,"openIssues90d":249,"pushedAt":250,"readmeSize":245,"stars":251,"topics":434},"Persistent Context Across Sessions for Every Agent –  Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More","https://claude-mem.ai",[435,436,437,438,439,440,441,442,225,443,444,445,446,447,448,449,450,451,452,453],"ai","ai-agents","ai-memory","anthropic","artificial-intelligence","claude","claude-agent-sdk","claude-agents","claude-code-plugin","claude-skills","long-term-memory","mem0","openmemory","supermemory","chromadb","sqlite","embeddings","memory-engine","rag",{"downloads":253},{"classifiedAt":456,"discoverAt":457,"extractAt":458,"githubAt":458,"npmAt":459,"updatedAt":456},1778698055851,1778698049260,1778698052709,1778698054459,[225,223,221,224,222],{"evaluatedAt":259,"extractAt":462,"updatedAt":463},1778698056313,1778698443619,[],[466,496,526,556,586,614],{"_creationTime":467,"_id":468,"community":469,"display":470,"identity":476,"providers":479,"relations":488,"tags":491,"workflow":492},1778694389360.6567,"k1723rcremvxvx59dy10cjc0f186n67k",{"reviewCount":8},{"description":471,"installMethods":472,"name":474,"sourceUrl":475},"Token-efficient persistent memory system for Claude Code that saves ~67% tokens on session warm-up (verified with tiktoken). Layered architecture with progressive loading, compact encoding, branch-aware context, smart compression, session diffing, conflict detection, session continuation protocol, and recovery mode. Activates at session start (if MEMORY.md exists), on \"remember this\", \"pick up where we left off\", \"what were we doing\", \"wrap up\", \"save progress\", \"don't forget\", \"switch context\", \"hand off\", \"memory health\", \"save state\", \"continue where I left off\", \"context budget\", \"how much context left\", or any session start on a project with existing memory files. This skill solves two problems at once: Claude forgetting everything between sessions, AND sessions hitting context limits too fast. It replaces thousands of wasted re-explanation tokens with a compact, structured memory load that gives Claude full project context in under 2,000 tokens.\n",{"claudeCode":473},"Nagendhra-web/memory-bank","memory-bank","https://github.com/Nagendhra-web/memory-bank",{"basePath":477,"githubOwner":478,"githubRepo":474,"locale":18,"slug":474,"type":265},"skills/memory-bank","Nagendhra-web",{"evaluate":480,"extract":487},{"promptVersionExtension":214,"promptVersionScoring":215,"score":218,"tags":481,"targetMarket":226,"tier":227},[221,223,224,482,483,484,485,486],"sessions","token-efficiency","branch-aware","compression","ai-assistant",{"commitSha":271,"license":256},{"parentExtensionId":489,"repoId":490},"k17dbjbnpmrxhbszzw5sx6tsgs86n09d","kd740s537z66ds6qge39y9dk3186nbp9",[486,484,485,223,221,224,482,483],{"evaluatedAt":493,"extractAt":494,"updatedAt":495},1778694438899,1778694389360,1778694474039,{"_creationTime":497,"_id":498,"community":499,"display":500,"identity":506,"providers":511,"relations":519,"tags":522,"workflow":523},1778696691708.329,"k170yjw596k3cg892bq130jyd186mhyz",{"reviewCount":8},{"description":501,"installMethods":502,"name":504,"sourceUrl":505},"Validate a Claude Code plugin structure, frontmatter, and MCP tool references",{"claudeCode":503},"ruvnet/ruflo","Validate Plugin","https://github.com/ruvnet/ruflo",{"basePath":507,"githubOwner":508,"githubRepo":509,"locale":18,"slug":510,"type":265},"plugins/ruflo-plugin-creator/skills/validate-plugin","ruvnet","ruflo","validate-plugin",{"evaluate":512,"extract":517},{"promptVersionExtension":214,"promptVersionScoring":215,"score":513,"tags":514,"targetMarket":226,"tier":227},100,[515,317,516,225,426],"validation","developer-tools",{"commitSha":271,"license":518},"MIT",{"parentExtensionId":520,"repoId":521},"k17f4y1y2y777p7zrxxhbnf03n86mr5j","kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[225,516,426,317,515],{"evaluatedAt":524,"extractAt":525,"updatedAt":524},1778701241052,1778696691708,{"_creationTime":527,"_id":528,"community":529,"display":530,"identity":536,"providers":540,"relations":549,"tags":551,"workflow":552},1778699106670.4258,"k17c1n6dbde7qh2wemx78d13t986n7x2",{"reviewCount":8},{"description":531,"installMethods":532,"name":534,"sourceUrl":535},"Use when routing Claude Code through a local LiteLLM proxy to GitHub Copilot, reducing direct Anthropic spend, configuring ANTHROPIC_BASE_URL or ANTHROPIC_MODEL overrides, or troubleshooting Copilot proxy setup failures such as model-not-found, no localhost traffic, or GitHub 401/403 auth errors.",{"claudeCode":533},"xixu-me/skills","running-claude-code-via-litellm-copilot","https://github.com/xixu-me/skills",{"basePath":537,"githubOwner":538,"githubRepo":539,"locale":18,"slug":534,"type":265},"skills/running-claude-code-via-litellm-copilot","xixu-me","skills",{"evaluate":541,"extract":548},{"promptVersionExtension":214,"promptVersionScoring":215,"score":513,"tags":542,"targetMarket":226,"tier":227},[543,544,545,225,546,547],"copilot","litellm","proxy","configuration","troubleshooting",{"commitSha":271},{"repoId":550},"kd77r2vb42jmgam0qbr9f2c6kn86mebv",[225,546,543,544,545,547],{"evaluatedAt":553,"extractAt":554,"updatedAt":555},1778699196029,1778699106670,1778699384216,{"_creationTime":557,"_id":558,"community":559,"display":560,"identity":566,"providers":570,"relations":578,"tags":581,"workflow":582},1778696712851.9746,"k17ef0e0f693nd248cs3f63rys86ndy8",{"reviewCount":8},{"description":561,"installMethods":562,"name":564,"sourceUrl":565},"Protect Claude Code sessions from context overflow by running a background daemon that monitors session size and auto-prunes before compaction hits. Use when the user says \"guard\", \"protect session\", \"context getting long\", \"prevent compaction\", \"session management\", or is running agent teams that need continuous context protection.\n",{"claudeCode":563},"Ruya-AI/cozempic","guard","https://github.com/Ruya-AI/cozempic",{"basePath":567,"githubOwner":568,"githubRepo":569,"locale":18,"slug":564,"type":265},"plugin/skills/guard","Ruya-AI","cozempic",{"evaluate":571,"extract":577},{"promptVersionExtension":214,"promptVersionScoring":215,"score":513,"tags":572,"targetMarket":226,"tier":227},[573,574,225,575,576],"session-management","context-pruning","python","utility",{"commitSha":271},{"parentExtensionId":579,"repoId":580},"k176hd1j2vn0hpak7ds6v3eand86mfqh","kd79d77qmyh3826dwhk7ynx9xd86nmqm",[225,574,575,573,576],{"evaluatedAt":583,"extractAt":584,"updatedAt":585},1778696790816,1778696712852,1778696924761,{"_creationTime":587,"_id":588,"community":589,"display":590,"identity":596,"providers":600,"relations":607,"tags":610,"workflow":611},1778694480889.9487,"k17eg219cke0p45yfhh8n2t37986mgm4",{"reviewCount":8},{"description":591,"installMethods":592,"name":594,"sourceUrl":595},"Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration",{"claudeCode":593},"NeoLabHQ/context-engineering-kit","create-command","https://github.com/NeoLabHQ/context-engineering-kit",{"basePath":597,"githubOwner":598,"githubRepo":599,"locale":18,"slug":594,"type":265},"plugins/customaize-agent/skills/create-command","NeoLabHQ","context-engineering-kit",{"evaluate":601,"extract":606},{"promptVersionExtension":214,"promptVersionScoring":215,"score":513,"tags":602,"targetMarket":226,"tier":227},[603,604,605,426,225],"command-creation","agent-development","prompt-engineering",{"commitSha":271},{"parentExtensionId":608,"repoId":609},"k173g0c46wghgz5j9gn02wfydn86mkh8","kd7a3rj13ezgx1wgm0jfh08hsx86n0sz",[604,225,603,426,605],{"evaluatedAt":612,"extractAt":613,"updatedAt":612},1778694773368,1778694480890,{"_creationTime":615,"_id":616,"community":617,"display":618,"identity":624,"providers":629,"relations":636,"tags":639,"workflow":640},1778692488329.0164,"k17d7dgccv6vnj9tcw0cehwnph86nryb",{"reviewCount":8},{"description":619,"installMethods":620,"name":622,"sourceUrl":623},"Analyze which rules are actively used vs inert. Detect coverage gaps. Recommend pruning to reduce token consumption.",{"claudeCode":621},"luiseiman/claude-kit","Rule Effectiveness Analysis","https://github.com/luiseiman/claude-kit",{"basePath":625,"githubOwner":626,"githubRepo":627,"locale":18,"slug":628,"type":265},"skills/rule-effectiveness","luiseiman","claude-kit","rule-effectiveness",{"evaluate":630,"extract":635},{"promptVersionExtension":214,"promptVersionScoring":215,"score":513,"tags":631,"targetMarket":226,"tier":227},[225,546,632,633,634],"analysis","optimization","git",{"commitSha":271,"license":518},{"parentExtensionId":637,"repoId":638},"k17650xadq8363kzchr4w0gmf186nq24","kd79wqc8an5wh20cc2znr8tyb586mxwx",[632,225,546,634,633],{"evaluatedAt":641,"extractAt":642,"updatedAt":641},1778693275143,1778692488329]