[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-Sagargupta16-cost-mode-en":3,"guides-for-Sagargupta16-cost-mode":357,"similar-k17bqyyps2cdpq2yaw8zpb9gy186nm8t-en":358},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":240,"isFallback":235,"parentExtension":245,"providers":273,"relations":277,"repo":278,"tags":354,"workflow":355},1778696773814.7834,"k17bqyyps2cdpq2yaw8zpb9gy186nm8t",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Cost-conscious Claude Code mode. Reduces output tokens 40-70% and overall costs 30-60% by enforcing concise responses, smart model routing, and efficient workflow patterns. Keeps full technical accuracy. Activate with /cost-mode or \"enable cost mode\". Auto-triggers on mentions of budget, cost, tokens, or spending.\n",{"claudeCode":12},"Sagargupta16/claude-cost-optimizer","cost-mode","https://github.com/Sagargupta16/claude-cost-optimizer",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":223,"workflow":238},1778696832772.6702,"kn77cwkzmp1xjpsr9z3mkgyhs186mpxa","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"promptVersionExtension":205,"promptVersionScoring":206,"purpose":207,"rationale":208,"score":209,"summary":210,"tags":211,"targetMarket":216,"tier":217,"useCases":218},[21,26,29,32,36,39,44,48,51,54,58,62,65,69,72,75,78,81,84,87,91,95,99,103,107,110,114,117,121,124,127,130,133,136,139,143,147,150,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly names the problem of high token usage and costs in Claude Code, and how the skill addresses it with concise responses and smart routing.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers significant value over simple prompting by enforcing specific response rules, model routing, and session management patterns to reduce costs, going beyond default LLM behavior.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill covers its stated use case of cost optimization and provides clear instructions and intensity levels, making it ready for use in a real workflow.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses exclusively on optimizing Claude Code interactions for cost and conciseness, without venturing into unrelated domains.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately and concisely reflects the skill's purpose and core functionality, including activation commands and auto-trigger conditions.",{"category":40,"check":41,"severity":42,"summary":43},"Invocation","Scoped tools","not_applicable","This skill does not expose explicit tools; its functionality is driven by prompt engineering and response manipulation within the Claude Code environment.",{"category":45,"check":46,"severity":24,"summary":47},"Documentation","Configuration & parameter reference","All parameters and intensity levels are clearly documented within the SKILL.md and README, including default behavior and activation commands.",{"category":33,"check":49,"severity":42,"summary":50},"Tool naming","The skill operates via natural language commands and prompt manipulation, not explicit tools with names.",{"category":33,"check":52,"severity":42,"summary":53},"Minimal I/O surface","The skill's interaction is through conversational prompts and commands, not discrete tools with parameter schemas.",{"category":55,"check":56,"severity":24,"summary":57},"License","License usability","The MIT license is clearly provided in a dedicated LICENSE file and is a permissive open-source license.",{"category":59,"check":60,"severity":24,"summary":61},"Maintenance","Commit recency","The repository has recent commits, indicating active maintenance.",{"category":59,"check":63,"severity":42,"summary":64},"Dependency Management","The skill does not appear to rely on external third-party dependencies managed via package managers.",{"category":66,"check":67,"severity":42,"summary":68},"Security","Secret Management","The skill does not handle or expose any secrets.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The skill operates on prompts and known commands, and does not load or execute untrusted third-party data as instructions.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill does not fetch remote content at runtime or execute arbitrary commands.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The skill operates within the Claude Code environment and does not interact with or modify files outside its designated scope.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","No detached processes or retry loops around denied tool calls were detected.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill does not read or submit confidential data to any third party.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled content and descriptions are free of hidden steering tricks or malicious Unicode characters.",{"category":88,"check":89,"severity":24,"summary":90},"Hooks","Opaque code execution","The skill's logic is contained within readable markdown and does not use obfuscated code or runtime fetches.",{"category":92,"check":93,"severity":24,"summary":94},"Portability","Structural Assumption","The skill makes no assumptions about user project file layouts, operating entirely within the conversational context.",{"category":96,"check":97,"severity":24,"summary":98},"Trust","Issues Attention","1 open and 1 closed issue in the last 90 days suggests good maintainer engagement.",{"category":100,"check":101,"severity":24,"summary":102},"Versioning","Release Management","The skill has a meaningful versioning indicated by the commit history and a `CHANGELOG.md`.",{"category":104,"check":105,"severity":42,"summary":106},"Execution","Validation","The skill does not expose tools with complex parameter schemas that would require schema validation libraries.",{"category":66,"check":108,"severity":24,"summary":109},"Unguarded Destructive Operations","The skill does not perform any destructive operations.",{"category":111,"check":112,"severity":24,"summary":113},"Code Execution","Error Handling","The skill provides clear instructions on how it operates and what to expect, implicitly handling potential errors through its structured prompt-based interaction.",{"category":111,"check":115,"severity":42,"summary":116},"Logging","The skill is conversational and does not perform actions that require local audit logging.",{"category":118,"check":119,"severity":24,"summary":120},"Compliance","GDPR","The skill does not operate on personal data; it influences LLM output style and model selection.",{"category":118,"check":122,"severity":24,"summary":123},"Target market","The skill's functionality is universal and not tied to any specific geographic or legal jurisdiction; targetMarket is global.",{"category":92,"check":125,"severity":24,"summary":126},"Runtime stability","The skill operates within the Claude Code environment and has no external runtime dependencies or OS-specific assumptions.",{"category":45,"check":128,"severity":24,"summary":129},"README","The README file clearly states the extension's purpose, installation, and usage instructions.",{"category":33,"check":131,"severity":42,"summary":132},"Tool surface size","The extension does not expose multiple distinct tools; it functions as a single conversational mode.",{"category":40,"check":134,"severity":42,"summary":135},"Overlapping near-synonym tools","The skill does not use distinct tools with overlapping functionality; it relies on conversational commands.",{"category":45,"check":137,"severity":24,"summary":138},"Phantom features","All advertised features in the README and SKILL.md are implemented and verifiable through the provided commands and descriptions.",{"category":140,"check":141,"severity":24,"summary":142},"Install","Installation instruction","Clear installation instructions for both Claude Code and other multi-agent environments are provided in the README, along with copy-pasteable invocation examples.",{"category":144,"check":145,"severity":24,"summary":146},"Errors","Actionable error messages","The skill provides clear instructions and context, implicitly handling errors through its structured interaction model.",{"category":104,"check":148,"severity":42,"summary":149},"Pinned dependencies","The skill does not use third-party dependencies that require pinning.",{"category":33,"check":151,"severity":42,"summary":152},"Dry-run preview","The skill does not perform state-changing operations that would require a dry-run preview.",{"category":154,"check":155,"severity":42,"summary":156},"Protocol","Idempotent retry & timeouts","The skill operates within the Claude Code conversational context and does not involve remote calls or state-changing operations requiring idempotency or timeouts.",{"category":118,"check":158,"severity":24,"summary":159},"Telemetry opt-in","The skill does not emit telemetry; its operation is limited to influencing LLM output within the user's session.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The description clearly defines the purpose (reduce tokens/costs) and when to use it (mentions of budget, cost, tokens, spending) and what it operates on (Claude Code mode, LLM responses).",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The frontmatter in SKILL.md is concise, self-contained, and accurately summarizes the core capability and trigger phrases.",{"category":45,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md body is well under 500 lines and effectively delegates detailed procedures to the README and internal structure.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","The SKILL.md outlines the core flow and intensity levels, with the README providing detailed usage and installation instructions, effectively using progressive disclosure.",{"category":170,"check":174,"severity":42,"summary":175},"Forked exploration","The skill does not perform deep exploration or code review; its function is to modify conversational output style.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The README provides clear, copy-pasteable examples for activating and using the cost mode at different intensity levels.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The SKILL.md and README document limitations such as auto-deactivation conditions and what the mode does not change, providing a clear understanding of edge cases.",{"category":111,"check":183,"severity":42,"summary":184},"Tool Fallback","The skill does not rely on external tools beyond the Claude Code environment itself and therefore has no fallback requirement.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The skill operates via conversational commands and explicit mode switching, implicitly halting unintended behavior by reverting to normal mode when conditions are met.",{"category":92,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The skill is self-contained and does not implicitly rely on other skills; its function is to modify the current session's interaction style.",1778696832447,"This skill optimizes Claude Code interactions by enforcing stricter response rules and suggesting more cost-effective models and CLI tools to reduce token consumption and overall costs.",[195,196,197,198,199],"Enforces concise responses and cuts filler content","Suggests cheaper, viable LLM models for tasks","Recommends CLI tools for deterministic tasks","Manages session awareness to prevent token bloat","Offers adjustable intensity levels (lite, standard, strict)",[201,202,203,204],"Sacrificing technical accuracy for brevity","Reducing clarity on security warnings or destructive operation confirmations","Writing code in commits, PRs, or generated files differently","Implementing cost-saving measures that confuse the user or hinder complex concept explanation","3.0.0","4.4.0","To significantly reduce Claude Code operational costs by minimizing token usage and intelligently routing tasks to the most cost-effective models, while maintaining technical accuracy.","The skill is well-documented, focused, and provides clear value. It has no significant security or maintenance concerns.",99,"A highly effective skill for reducing LLM token usage and costs through concise responses and smart model routing.",[212,213,214,215],"cost-optimization","llm-efficiency","prompt-engineering","claude-code","global","verified",[219,220,221,222],"Reducing budget for frequent Claude Code usage","Maintaining technical accuracy while minimizing output verbosity","Guiding LLM interactions for cost-effectiveness in daily development","Ensuring efficiency for repetitive or deterministic coding tasks",{"codeQuality":224,"collectedAt":226,"documentation":227,"maintenance":230,"security":234,"testCoverage":237},{"hasLockfile":225},true,1778696819148,{"descriptionLength":228,"readmeSize":229},316,14383,{"closedIssues90d":231,"forks":231,"hasChangelog":225,"openIssues90d":231,"pushedAt":232,"stars":233},1,1778458960000,20,{"hasNpmPackage":235,"license":236,"smitheryVerified":235},false,"MIT",{"hasCi":225,"hasTests":235},{"updatedAt":239},1778696832772,{"basePath":241,"githubOwner":242,"githubRepo":243,"locale":18,"slug":13,"type":244},"skills/cost-mode","Sagargupta16","claude-cost-optimizer","skill",{"_creationTime":246,"_id":247,"community":248,"display":249,"identity":253,"parentExtension":256,"providers":257,"relations":266,"tags":268,"workflow":269},1778696773814.783,"k1752jjawz8vy49fxchx4f3fyx86nfkd",{"reviewCount":8},{"description":250,"installMethods":251,"name":252,"sourceUrl":14},"Cost-conscious mode for Claude Code. Saves 30-60% on costs through concise responses, model routing, and efficient workflow patterns.",{"claudeCode":243},"Claude Cost Optimizer",{"basePath":254,"githubOwner":242,"githubRepo":243,"locale":18,"slug":243,"type":255},"","plugin",null,{"evaluate":258,"extract":262},{"promptVersionExtension":205,"promptVersionScoring":206,"score":209,"tags":259,"targetMarket":216,"tier":217},[212,215,214,260,261],"workflow","developer-tools",{"commitSha":263,"license":236,"plugin":264},"HEAD",{"mcpCount":8,"provider":265,"skillCount":231},"classify",{"repoId":267},"kd7001v1z5cqn8kbm748zh0x4n86nrmc",[215,212,261,214,260],{"evaluatedAt":270,"extractAt":271,"updatedAt":272},1778696801957,1778696773814,1778696888236,{"evaluate":274,"extract":276},{"promptVersionExtension":205,"promptVersionScoring":206,"score":209,"tags":275,"targetMarket":216,"tier":217},[212,213,214,215],{"commitSha":263},{"parentExtensionId":247,"repoId":267},{"_creationTime":279,"_id":267,"identity":280,"providers":281,"workflow":350},1778696768665.4775,{"githubOwner":242,"githubRepo":243,"sourceUrl":14},{"classify":282,"discover":334,"github":337},{"commitSha":263,"extensions":283},[284,294,318,327],{"basePath":285,"displayName":243,"installMethods":286,"rationale":287,"selectedPaths":288,"source":292,"sourceLanguage":18,"type":293},".agents/plugins",{"claudeCode":12},"marketplace.json at .agents/plugins/marketplace.json (coalesced with duplicate marketplace at /)",[289],{"path":290,"priority":291},"marketplace.json","mandatory","rule","marketplace",{"basePath":254,"description":250,"displayName":243,"installMethods":295,"rationale":296,"selectedPaths":297,"source":292,"sourceLanguage":18,"type":255},{"claudeCode":243},"plugin manifest at .claude-plugin/plugin.json",[298,300,302,305,308,310,312,314,316],{"path":299,"priority":291},".claude-plugin/plugin.json",{"path":301,"priority":291},"README.md",{"path":303,"priority":304},"LICENSE","high",{"path":306,"priority":307},"skills/cost-mode/SKILL.md","medium",{"path":309,"priority":304},"hooks/README.md",{"path":311,"priority":304},"hooks/budget-tracker.sh",{"path":313,"priority":304},"hooks/cost-logger.sh",{"path":315,"priority":304},"hooks/session-summary.sh",{"path":317,"priority":304},"hooks/settings-example.json",{"basePath":319,"description":320,"displayName":13,"installMethods":321,"license":236,"rationale":322,"selectedPaths":323,"source":292,"sourceLanguage":18,"type":255},"plugins/cost-mode","Cost-conscious mode for Claude Code. Cuts filler, suggests cheaper models, encourages efficient patterns.",{"claudeCode":13},"plugin manifest at plugins/cost-mode/.codex-plugin/plugin.json",[324,326],{"path":325,"priority":291},".codex-plugin/plugin.json",{"path":306,"priority":307},{"basePath":241,"description":10,"displayName":13,"installMethods":328,"rationale":329,"selectedPaths":330,"source":292,"sourceLanguage":18,"type":244},{"claudeCode":12},"SKILL.md frontmatter at skills/cost-mode/SKILL.md (coalesced with duplicate skill at plugins/cost-mode/skills/cost-mode)",[331,333],{"path":332,"priority":291},"SKILL.md",{"path":301,"priority":304},{"sources":335},[336],"manual",{"closedIssues90d":231,"description":338,"forks":231,"homepage":339,"license":236,"openIssues90d":231,"pushedAt":232,"readmeSize":229,"stars":233,"topics":340},"Save 30-60% on Claude Code costs -- proven strategies, real benchmarks, copy-paste configs, and interactive tools","http://sagargupta.online/claude-cost-optimizer/",[341,342,343,344,215,212,261,345,346,347,348,349,214],"ai-coding","anthropic","best-practices","claude","llm","token-optimization","ai-development","ai-tools","cost-reduction",{"classifiedAt":351,"discoverAt":352,"extractAt":353,"githubAt":353,"updatedAt":351},1778696773647,1778696768665,1778696771564,[215,212,213,214],{"evaluatedAt":239,"extractAt":271,"updatedAt":356},1778696888713,[],[359,388,415,445,475,504],{"_creationTime":360,"_id":361,"community":362,"display":363,"identity":369,"providers":373,"relations":381,"tags":384,"workflow":385},1778694480889.9487,"k17eg219cke0p45yfhh8n2t37986mgm4",{"reviewCount":8},{"description":364,"installMethods":365,"name":367,"sourceUrl":368},"Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration",{"claudeCode":366},"NeoLabHQ/context-engineering-kit","create-command","https://github.com/NeoLabHQ/context-engineering-kit",{"basePath":370,"githubOwner":371,"githubRepo":372,"locale":18,"slug":367,"type":244},"plugins/customaize-agent/skills/create-command","NeoLabHQ","context-engineering-kit",{"evaluate":374,"extract":380},{"promptVersionExtension":205,"promptVersionScoring":206,"score":375,"tags":376,"targetMarket":216,"tier":217},100,[377,378,214,379,215],"command-creation","agent-development","mcp",{"commitSha":263},{"parentExtensionId":382,"repoId":383},"k173g0c46wghgz5j9gn02wfydn86mkh8","kd7a3rj13ezgx1wgm0jfh08hsx86n0sz",[378,215,377,379,214],{"evaluatedAt":386,"extractAt":387,"updatedAt":386},1778694773368,1778694480890,{"_creationTime":389,"_id":390,"community":391,"display":392,"identity":398,"providers":403,"relations":408,"tags":411,"workflow":412},1778696691708.329,"k170yjw596k3cg892bq130jyd186mhyz",{"reviewCount":8},{"description":393,"installMethods":394,"name":396,"sourceUrl":397},"Validate a Claude Code plugin structure, frontmatter, and MCP tool references",{"claudeCode":395},"ruvnet/ruflo","Validate Plugin","https://github.com/ruvnet/ruflo",{"basePath":399,"githubOwner":400,"githubRepo":401,"locale":18,"slug":402,"type":244},"plugins/ruflo-plugin-creator/skills/validate-plugin","ruvnet","ruflo","validate-plugin",{"evaluate":404,"extract":407},{"promptVersionExtension":205,"promptVersionScoring":206,"score":375,"tags":405,"targetMarket":216,"tier":217},[406,255,261,215,379],"validation",{"commitSha":263,"license":236},{"parentExtensionId":409,"repoId":410},"k17f4y1y2y777p7zrxxhbnf03n86mr5j","kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[215,261,379,255,406],{"evaluatedAt":413,"extractAt":414,"updatedAt":413},1778701241052,1778696691708,{"_creationTime":416,"_id":417,"community":418,"display":419,"identity":425,"providers":429,"relations":438,"tags":440,"workflow":441},1778699106670.4258,"k17c1n6dbde7qh2wemx78d13t986n7x2",{"reviewCount":8},{"description":420,"installMethods":421,"name":423,"sourceUrl":424},"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":422},"xixu-me/skills","running-claude-code-via-litellm-copilot","https://github.com/xixu-me/skills",{"basePath":426,"githubOwner":427,"githubRepo":428,"locale":18,"slug":423,"type":244},"skills/running-claude-code-via-litellm-copilot","xixu-me","skills",{"evaluate":430,"extract":437},{"promptVersionExtension":205,"promptVersionScoring":206,"score":375,"tags":431,"targetMarket":216,"tier":217},[432,433,434,215,435,436],"copilot","litellm","proxy","configuration","troubleshooting",{"commitSha":263},{"repoId":439},"kd77r2vb42jmgam0qbr9f2c6kn86mebv",[215,435,432,433,434,436],{"evaluatedAt":442,"extractAt":443,"updatedAt":444},1778699196029,1778699106670,1778699384216,{"_creationTime":446,"_id":447,"community":448,"display":449,"identity":455,"providers":459,"relations":467,"tags":470,"workflow":471},1778696712851.9746,"k17ef0e0f693nd248cs3f63rys86ndy8",{"reviewCount":8},{"description":450,"installMethods":451,"name":453,"sourceUrl":454},"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":452},"Ruya-AI/cozempic","guard","https://github.com/Ruya-AI/cozempic",{"basePath":456,"githubOwner":457,"githubRepo":458,"locale":18,"slug":453,"type":244},"plugin/skills/guard","Ruya-AI","cozempic",{"evaluate":460,"extract":466},{"promptVersionExtension":205,"promptVersionScoring":206,"score":375,"tags":461,"targetMarket":216,"tier":217},[462,463,215,464,465],"session-management","context-pruning","python","utility",{"commitSha":263},{"parentExtensionId":468,"repoId":469},"k176hd1j2vn0hpak7ds6v3eand86mfqh","kd79d77qmyh3826dwhk7ynx9xd86nmqm",[215,463,464,462,465],{"evaluatedAt":472,"extractAt":473,"updatedAt":474},1778696790816,1778696712852,1778696924761,{"_creationTime":476,"_id":477,"community":478,"display":479,"identity":485,"providers":490,"relations":497,"tags":500,"workflow":501},1778692488329.0164,"k17d7dgccv6vnj9tcw0cehwnph86nryb",{"reviewCount":8},{"description":480,"installMethods":481,"name":483,"sourceUrl":484},"Analyze which rules are actively used vs inert. Detect coverage gaps. Recommend pruning to reduce token consumption.",{"claudeCode":482},"luiseiman/claude-kit","Rule Effectiveness Analysis","https://github.com/luiseiman/claude-kit",{"basePath":486,"githubOwner":487,"githubRepo":488,"locale":18,"slug":489,"type":244},"skills/rule-effectiveness","luiseiman","claude-kit","rule-effectiveness",{"evaluate":491,"extract":496},{"promptVersionExtension":205,"promptVersionScoring":206,"score":375,"tags":492,"targetMarket":216,"tier":217},[215,435,493,494,495],"analysis","optimization","git",{"commitSha":263,"license":236},{"parentExtensionId":498,"repoId":499},"k17650xadq8363kzchr4w0gmf186nq24","kd79wqc8an5wh20cc2znr8tyb586mxwx",[493,215,435,495,494],{"evaluatedAt":502,"extractAt":503,"updatedAt":502},1778693275143,1778692488329,{"_creationTime":505,"_id":506,"community":507,"display":508,"identity":512,"providers":514,"relations":521,"tags":522,"workflow":523},1778692488329.0137,"k172mwc9y507ztvq3eqqkqnhvh86n16s",{"reviewCount":8},{"description":509,"installMethods":510,"name":511,"sourceUrl":484},"Initializes the Claude Code configuration in a new or existing project using the dotforge template.",{"claudeCode":482},"bootstrap-project",{"basePath":513,"githubOwner":487,"githubRepo":488,"locale":18,"slug":511,"type":244},"skills/bootstrap-project",{"evaluate":515,"extract":520},{"promptVersionExtension":205,"promptVersionScoring":206,"score":375,"tags":516,"targetMarket":216,"tier":217},[435,517,518,519,215],"project-setup","automation","dotforge",{"commitSha":263},{"parentExtensionId":498,"repoId":499},[518,215,435,519,517],{"evaluatedAt":524,"extractAt":503,"updatedAt":524},1778692993130]