[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-cli-gsd-build-get-shit-done-en":3,"guides-for-gsd-build-get-shit-done":322,"similar-k177a2tx8trp59d6qddfgyqfhs86m99h-en":323},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":14,"identity":251,"isFallback":239,"parentExtension":255,"providers":256,"relations":261,"repo":263,"tags":318,"workflow":319},1778688084060.638,"k177a2tx8trp59d6qddfgyqfhs86m99h",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":12,"sourceUrl":13},"A meta-prompting, context engineering and spec-driven development system for Claude Code, OpenCode, Gemini and Codex by TÂCHES.",{"npm":12},"get-shit-done-cc","https://github.com/gsd-build/get-shit-done",{"_creationTime":15,"_id":16,"extensionId":5,"locale":17,"result":18,"trustSignals":229,"workflow":249},1778688110243.7856,"kn71n5bjrrdcghr5hk62khw1kn86m82j","en",{"checks":19,"evaluatedAt":197,"extensionSummary":198,"features":199,"nonGoals":205,"promptVersionExtension":209,"promptVersionScoring":210,"purpose":211,"rationale":212,"score":213,"summary":214,"tags":215,"targetMarket":222,"tier":223,"useCases":224},[20,25,28,31,35,38,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,106,109,112,115,119,122,125,128,131,134,137,141,145,149,152,156,159,162,165,168,171,174,177,180,183,186,190,193],{"category":21,"check":22,"severity":23,"summary":24},"Practical Utility","Problem relevance","pass","The description clearly states the problem of context rot and provides a solution for AI development workflows.",{"category":21,"check":26,"severity":23,"summary":27},"Unique selling proposition","The tool offers a sophisticated meta-prompting, context engineering, and spec-driven development system that goes beyond basic prompt engineering for AI agents.",{"category":21,"check":29,"severity":23,"summary":30},"Production readiness","The tool appears to cover the complete lifecycle of AI development, from initialization to shipping, with a focus on reliability and verification.",{"category":32,"check":33,"severity":23,"summary":34},"Scope","Single responsibility principle","The extension focuses on a coherent workflow for AI development and context management, without apparent unrelated capabilities.",{"category":32,"check":36,"severity":23,"summary":37},"Description quality","The provided description accurately and concisely reflects the tool's purpose and capabilities.",{"category":39,"check":40,"severity":41,"summary":42},"Invocation","Scoped tools","info","The tool uses a mix of command-line interface commands and slash commands, which are generally well-scoped, but a deeper inspection of all internal commands is not possible from the provided source.",{"category":44,"check":45,"severity":23,"summary":46},"Documentation","Configuration & parameter reference","The README provides comprehensive documentation for commands, settings, and installation, including configuration details.",{"category":32,"check":48,"severity":23,"summary":49},"Tool naming","Tool names are descriptive and follow a consistent pattern (e.g., `/gsd-new-project`, `/gsd-plan-phase`).",{"category":32,"check":51,"severity":23,"summary":52},"Minimal I/O surface","The tool's commands appear designed to accept specific inputs and produce structured outputs without unnecessary data.",{"category":54,"check":55,"severity":23,"summary":56},"License","License usability","The extension is licensed under the MIT license, which is permissive and clearly stated in a LICENSE file.",{"category":58,"check":59,"severity":23,"summary":60},"Maintenance","Commit recency","The repository has recent commits as of 2026-05-13, indicating active maintenance.",{"category":58,"check":62,"severity":23,"summary":63},"Dependency Management","The project uses npm with a lockfile and has dependencies like @anthropic-ai/claude-agent-sdk, suggesting managed dependencies.",{"category":65,"check":66,"severity":23,"summary":67},"Security","Secret Management","No secrets are hardcoded or exposed in the provided source files. Documentation hints at handling credentials and permissions, but the mechanism is not detailed enough to identify risks.",{"category":65,"check":69,"severity":23,"summary":70},"Injection","The tool is designed for AI agent workflows and appears to treat external data as input rather than instructions, with no evidence of remote content execution.",{"category":65,"check":72,"severity":23,"summary":73},"Transitive Supply-Chain Grenades","The tool relies on npm dependencies and a local install process, with no indication of runtime fetching of external code or data that could be a supply chain risk.",{"category":65,"check":75,"severity":23,"summary":76},"Sandbox Isolation","The tool appears to operate within its defined project scope and does not show evidence of modifying files outside its designated directories.",{"category":65,"check":78,"severity":23,"summary":79},"Sandbox escape primitives","No detached process spawns or deny-retry loops were found in the provided source code snippets.",{"category":65,"check":81,"severity":23,"summary":82},"Data Exfiltration","The tool's focus on code generation and workflow management does not appear to involve exfiltrating confidential user data.",{"category":65,"check":84,"severity":23,"summary":85},"Hidden Text Tricks","The provided source code and README content do not contain any hidden text tricks or obfuscated instructions.",{"category":87,"check":88,"severity":23,"summary":89},"Hooks","Opaque code execution","The code and scripts appear to be standard JavaScript and Node.js, with no evidence of obfuscation, base64 payloads, or runtime fetched code.",{"category":91,"check":92,"severity":23,"summary":93},"Portability","Structural Assumption","The tool's installation instructions and documentation suggest it is designed for cross-platform compatibility (Mac, Windows, Linux) and handles runtime differences.",{"category":95,"check":96,"severity":23,"summary":97},"Trust","Issues Attention","With 43 open and 1272 closed issues in 90 days, the closure rate is high (approx. 96.7%), indicating active maintainer engagement.",{"category":99,"check":100,"severity":23,"summary":101},"Versioning","Release Management","The tool declares a version (1.50.0-canary.0) in its package.json, and installation instructions reference specific versions or latest, indicating versioned releases.",{"category":103,"check":104,"severity":23,"summary":105},"Code Execution","Validation","The tool uses an SDK (@anthropic-ai/claude-agent-sdk) which implies robust input validation and handling. The README also mentions rigorous planning and verification steps.",{"category":65,"check":107,"severity":23,"summary":108},"Unguarded Destructive Operations","The workflow emphasizes verification and approval steps before actions are taken, suggesting destructive operations are guarded.",{"category":103,"check":110,"severity":23,"summary":111},"Error Handling","The tool's design, particularly the emphasis on verification and debug agents, suggests robust error handling is a core component.",{"category":103,"check":113,"severity":23,"summary":114},"Logging","The tool's workflow includes phases and verification, implying logging of actions and outcomes for auditability.",{"category":116,"check":117,"severity":23,"summary":118},"Compliance","GDPR","The tool's purpose is code generation and workflow management, not direct handling of personal data without appropriate sanitization.",{"category":116,"check":120,"severity":23,"summary":121},"Target market","The tool is described as working on Mac, Windows, and Linux and supports multiple AI runtimes globally.",{"category":91,"check":123,"severity":23,"summary":124},"Runtime stability","The tool explicitly supports multiple operating systems (Mac, Windows, Linux) and multiple AI runtimes, indicating strong portability.",{"category":44,"check":126,"severity":23,"summary":127},"README","The README file is extensive, well-structured, and clearly states the tool's purpose and how it works.",{"category":32,"check":129,"severity":23,"summary":130},"Tool surface size","The tool exposes a focused set of commands (around 10 main loop commands listed) related to its AI development workflow.",{"category":39,"check":132,"severity":23,"summary":133},"Overlapping near-synonym tools","The commands presented in the README follow a clear, distinct naming convention and do not appear to have overlapping synonyms.",{"category":44,"check":135,"severity":23,"summary":136},"Phantom features","All advertised features, such as context engineering and spec-driven development, are directly supported by the described workflow and commands.",{"category":138,"check":139,"severity":23,"summary":140},"Install","Installation instruction","The README provides clear installation instructions using npx and mentions runtime setup, with documentation for user guides and configuration.",{"category":142,"check":143,"severity":23,"summary":144},"Errors","Actionable error messages","The tool's emphasis on verification, debug agents, and clear workflow steps suggests that errors are likely actionable and well-diagnosed.",{"category":146,"check":147,"severity":23,"summary":148},"Execution","Pinned dependencies","The project uses npm and includes a lockfile, indicating that dependencies are pinned.",{"category":32,"check":150,"severity":23,"summary":151},"Dry-run preview","The workflow includes explicit verification and approval steps before execution, implying a form of dry-run or preview for state-changing operations.",{"category":153,"check":154,"severity":23,"summary":155},"Protocol","Idempotent retry & timeouts","The tool's design for reliable AI workflows, including subagent orchestration and verification, suggests an underlying architecture that handles retries and timeouts appropriately.",{"category":116,"check":157,"severity":23,"summary":158},"Telemetry opt-in","There is no mention of telemetry collection in the README or package.json, and the focus is on user control and local workflow, implying no unsolicited telemetry.",{"category":39,"check":160,"severity":23,"summary":161},"Hierarchical discoverable arguments","The CLI commands are presented in a hierarchical structure (e.g., `/gsd-new-project`, `/gsd-plan-phase [N]`) and the documentation suggests detailed help is available.",{"category":39,"check":163,"severity":23,"summary":164},"Unknown-flag handling","Given the use of a modern SDK and Node.js conventions, it is highly probable that unknown flags would result in explicit errors.",{"category":65,"check":166,"severity":23,"summary":167},"Secrets not in argv","The tool's installation and usage documentation does not indicate that secrets are passed directly via command-line arguments.",{"category":39,"check":169,"severity":23,"summary":170},"Parseable --version","The package.json declares a version (`1.50.0-canary.0`), and it's common for npm packages to have a parseable `--version` flag.",{"category":39,"check":172,"severity":23,"summary":173},"Flag precedence","The documentation mentions configuration files and settings, implying a documented precedence order for flags, environment variables, and config files.",{"category":39,"check":175,"severity":23,"summary":176},"Schema introspection","The use of `@anthropic-ai/claude-agent-sdk` and the emphasis on structured workflows suggest that machine-readable schemas for inputs/outputs are likely implemented.",{"category":39,"check":178,"severity":23,"summary":179},"Prompt bypass","The workflow is designed for automation and includes modes like 'yolo' and auto-approval flags, indicating interactive prompts are bypassable.",{"category":138,"check":181,"severity":23,"summary":182},"No unnecessary global install","The primary install method uses npx, which typically runs packages in a sandboxed environment without a global install.",{"category":138,"check":184,"severity":23,"summary":185},"Pipe-to-shell installer","The installation instructions use `npx`, which is a safe package runner and does not involve pipe-to-shell commands.",{"category":187,"check":188,"severity":23,"summary":189},"Output","Stream separation","The tool's focus on structured workflows and agent interaction implies clear separation of stdout for data and stderr for diagnostics.",{"category":187,"check":191,"severity":23,"summary":192},"Structured output mode","The tool's reliance on AI agents and structured workflows strongly suggests that a structured output mode (like JSON) is available for machine readability.",{"category":194,"check":195,"severity":23,"summary":196},"Subprocess behavior","Signal handling","As a modern Node.js application, it is expected to handle signals gracefully for clean shutdowns.",1778688109744,"This CLI tool provides a structured system for AI-driven development, managing context engineering, and enabling spec-driven workflows for various AI models. It aims to solve context rot by orchestrating subagents and maintaining structured artifacts.",[200,201,202,203,204],"Meta-prompting and context engineering","Spec-driven development workflows","Multi-AI model support","Context rot mitigation","Structured artifact management",[206,207,208],"Replacing direct AI model interaction for simple queries","Serving as a general-purpose CI/CD tool","Providing a GUI interface for AI development","3.0.0","4.4.0","To provide a reliable and efficient system for developers to leverage AI models for code generation and project development, ensuring context quality and verifiable outcomes.","The tool is highly polished with excellent documentation, a clear focus on AI development workflows, and strong adherence to best practices, particularly concerning security and usability.",97,"A robust and well-documented CLI tool for AI-driven development, focusing on context engineering and spec-driven workflows.",[216,217,218,219,220,221],"ai","claude","workflow","development","cli","code-generation","global","verified",[225,226,227,228],"Developing AI-powered applications with structured workflows","Maintaining code quality and context in long-running AI projects","Automating AI development tasks from planning to execution and verification","Utilizing AI for code generation and project scaffolding",{"codeQuality":230,"collectedAt":232,"documentation":233,"maintenance":236,"popularity":244,"security":246,"testCoverage":248},{"hasLockfile":231},true,1778688085798,{"descriptionLength":234,"readmeSize":235},127,10490,{"closedIssues90d":237,"forks":238,"hasChangelog":239,"manifestVersion":240,"openIssues90d":241,"pushedAt":242,"stars":243},1272,5257,false,"1.50.0-canary.0",43,1778662100000,61925,{"npmDownloads":245},201756,{"hasNpmPackage":231,"license":247,"smitheryVerified":239},"MIT",{"hasCi":231,"hasTests":231},{"updatedAt":250},1778688110243,{"basePath":252,"githubOwner":253,"githubRepo":254,"locale":17,"slug":254,"type":220},"","gsd-build","get-shit-done",null,{"evaluate":257,"extract":259},{"promptVersionExtension":209,"promptVersionScoring":210,"score":213,"tags":258,"targetMarket":222,"tier":223},[216,217,218,219,220,221],{"commitSha":260,"license":247},"HEAD",{"repoId":262},"kd742g8972gs9150hkbr4r696986nzza",{"_creationTime":264,"_id":262,"identity":265,"providers":266,"workflow":313},1778688076507.493,{"githubOwner":253,"githubRepo":254,"sourceUrl":13},{"classify":267,"discover":301,"extract":304,"github":305,"npm":312},{"commitSha":260,"extensions":268},[269,287],{"basePath":252,"description":10,"displayName":12,"installMethods":270,"license":247,"rationale":271,"selectedPaths":272,"source":286,"sourceLanguage":17,"type":220},{"npm":12},"cli ecosystem detected at /",[273,276,278,281,284],{"path":274,"priority":275},"package.json","mandatory",{"path":277,"priority":275},"README.md",{"path":279,"priority":280},"LICENSE","high",{"path":282,"priority":283},"bin/install.js","medium",{"path":285,"priority":283},"bin/gsd-sdk.js","rule",{"basePath":288,"description":289,"displayName":290,"installMethods":291,"license":247,"rationale":292,"selectedPaths":293,"source":286,"sourceLanguage":17,"type":220},"sdk","GSD SDK — programmatic interface for running GSD plans via the Agent SDK","@gsd-build/sdk",{"npm":290},"cli ecosystem detected at sdk",[294,295,296,299],{"path":274,"priority":275},{"path":277,"priority":275},{"path":297,"priority":298},"src/index.ts","low",{"path":300,"priority":298},"src/cli.ts",{"sources":302},[303],"manual",{"npmPackage":12},{"closedIssues90d":237,"description":306,"forks":238,"license":247,"openIssues90d":241,"pushedAt":242,"readmeSize":235,"stars":243,"topics":307},"A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.",[308,309,310,311],"claude-code","context-engineering","meta-prompting","spec-driven-development",{"downloads":245},{"classifiedAt":314,"discoverAt":315,"extractAt":316,"githubAt":316,"npmAt":317,"updatedAt":314},1778688083890,1778688076507,1778688079935,1778688081879,[216,217,220,221,219,218],{"evaluatedAt":250,"extractAt":320,"updatedAt":321},1778688084060,1778688164454,[],[324,355,383,413,440],{"_creationTime":325,"_id":326,"community":327,"display":328,"identity":334,"providers":337,"relations":348,"tags":350,"workflow":351},1778697107735.8984,"k177h2k24qprbp2pjjs5tsb9r586nywg",{"reviewCount":8},{"description":329,"installMethods":330,"name":332,"sourceUrl":333},"AI Constraint Engine — enforces CLAUDE.md, .cursorrules, AGENTS.md rules as laws. 51 MCP tools, 991 tests. Official MCP Registry. npx speclock protect",{"pypi":331},"speclock_ros2","speclock-ros2","https://github.com/sgroy10/speclock",{"basePath":332,"githubOwner":335,"githubRepo":336,"locale":17,"slug":332,"type":220},"sgroy10","speclock",{"evaluate":338,"extract":347},{"promptVersionExtension":209,"promptVersionScoring":210,"score":339,"tags":340,"targetMarket":222,"tier":223},100,[341,342,343,220,344,345,346],"ai-constraints","code-enforcement","developer-tool","security","mcp","robotics",{"commitSha":260},{"repoId":349},"kd73m85wtkj05xmfff4vq695hn86mgg4",[341,220,342,343,345,346,344],{"evaluatedAt":352,"extractAt":353,"updatedAt":354},1778697123911,1778697107735,1778697174406,{"_creationTime":356,"_id":357,"community":358,"display":359,"identity":364,"providers":366,"relations":376,"tags":378,"workflow":379},1778696712851.9753,"k177hk154d2wjt39bm54ke8kyn86mz3n",{"reviewCount":8},{"description":360,"installMethods":361,"name":362,"sourceUrl":363},"Context cleaning for Claude Code — prune bloated sessions, protect Agent Teams from context loss, auto-guard with tiered pruning",{"npm":362,"pypi":362},"cozempic","https://github.com/Ruya-AI/cozempic",{"basePath":252,"githubOwner":365,"githubRepo":362,"locale":17,"slug":362,"type":220},"Ruya-AI",{"evaluate":367,"extract":375},{"promptVersionExtension":209,"promptVersionScoring":210,"score":368,"tags":369,"targetMarket":222,"tier":223},99,[217,370,371,372,373,220,374],"session","context","pruning","optimization","python",{"commitSha":260},{"repoId":377},"kd79d77qmyh3826dwhk7ynx9xd86nmqm",[217,220,371,373,372,374,370],{"evaluatedAt":380,"extractAt":381,"updatedAt":382},1778696840607,1778696712852,1778696925194,{"_creationTime":384,"_id":385,"community":386,"display":387,"identity":393,"providers":397,"relations":406,"tags":408,"workflow":409},1778697845392.8054,"k174gqerpcdxtz9jn0xrdqdtes86nve5",{"reviewCount":8},{"description":388,"installMethods":389,"name":391,"sourceUrl":392},"Supabase CLI. Manage postgres migrations, run Supabase locally, deploy edge functions. Postgres backups. Generating types from your database schema.",{"go":390},"github.com/supabase/cli","Supabase CLI","https://github.com/supabase/cli",{"basePath":394,"githubOwner":395,"githubRepo":220,"locale":17,"slug":396,"type":220},"apps/cli-go","supabase","cli-go",{"evaluate":398,"extract":405},{"promptVersionExtension":209,"promptVersionScoring":210,"score":368,"tags":399,"targetMarket":222,"tier":223},[395,220,400,401,402,403,404,219],"postgres","database","functions","storage","gitops",{"commitSha":260,"license":247},{"repoId":407},"kd74vngfftabd9esp2y5djjm4x86m8q4",[220,401,219,402,404,400,403,395],{"evaluatedAt":410,"extractAt":411,"updatedAt":412},1778697879372,1778697845392,1778697968361,{"_creationTime":414,"_id":415,"community":416,"display":417,"identity":423,"providers":425,"relations":433,"tags":435,"workflow":436},1778699617694.4897,"k17fzvw7q4e13rbrdphydzdfwx86nqag",{"reviewCount":8},{"description":418,"installMethods":419,"name":421,"sourceUrl":422},"A fact-forcing hook gate for Claude Code. Makes the AI pause and investigate before editing.",{"pypi":420},"gateguard-ai","gateguard","https://github.com/zunoworks/gateguard",{"basePath":252,"githubOwner":424,"githubRepo":421,"locale":17,"slug":421,"type":220},"zunoworks",{"evaluate":426,"extract":432},{"promptVersionExtension":209,"promptVersionScoring":210,"score":427,"tags":428,"targetMarket":222,"tier":223},98,[217,429,430,374,220,343,431],"ai-agent","guardrail","code-quality",{"commitSha":260},{"repoId":434},"kd7cpymv9nv5641nqx7d2mj0p586nzwt",[429,217,220,431,343,430,374],{"evaluatedAt":437,"extractAt":438,"updatedAt":439},1778699634441,1778699617694,1778699656961,{"_creationTime":441,"_id":442,"community":443,"display":444,"identity":449,"providers":451,"relations":459,"tags":461,"workflow":462},1778692788604.3567,"k17e35aavwxe13gv0vzvf138rs86mw72",{"reviewCount":8},{"description":445,"installMethods":446,"name":447,"sourceUrl":448},"Visual cockpit for Claude Code. Plan visually, track progress, let AI execute. Same engine, better cockpit.",{"npm":447},"kanbaii","https://github.com/martinmsaavedra/kanbaii",{"basePath":252,"githubOwner":450,"githubRepo":447,"locale":17,"slug":447,"type":220},"martinmsaavedra",{"evaluate":452,"extract":458},{"promptVersionExtension":209,"promptVersionScoring":210,"score":453,"tags":454,"targetMarket":222,"tier":223},92,[455,217,216,456,220,457],"kanban","project-management","automation",{"commitSha":260,"license":247},{"repoId":460},"kd7c6vsr8vjjnvww6swrrysfvx86nceg",[216,457,217,220,455,456],{"evaluatedAt":463,"extractAt":464,"updatedAt":465},1778692808371,1778692788604,1778692833602]