[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-plugin-TheQmaks-crowdcast-en":3,"guides-for-TheQmaks-crowdcast":378,"similar-k171tdhndgm24735r23nyaccz586ncrj-en":379},{"_creationTime":4,"_id":5,"children":6,"community":48,"display":49,"evaluation":52,"identity":281,"isFallback":267,"parentExtension":284,"providers":311,"relations":316,"repo":317,"tags":375,"workflow":376},1778698083702.1262,"k171tdhndgm24735r23nyaccz586ncrj",[7],{"_creationTime":8,"_id":9,"community":10,"display":12,"identity":18,"providers":24,"relations":41,"tags":43,"workflow":44},1778698083702.1265,"k17brwh7tfw6mws70s3qjj8z4n86m5w9",{"reviewCount":11},0,{"description":13,"installMethods":14,"name":16,"sourceUrl":17},"Run multi-agent social simulations for prediction and creative exploration. Use when the user wants to simulate group behavior, predict public reactions, explore fictional scenarios, or analyze how agents would interact. Trigger words - \"simulate\", \"prediction\", \"multi-agent\", \"what would happen if\", \"social simulation\", \"crowdcast\".",{"claudeCode":15},"TheQmaks/crowdcast","Crowdcast","https://github.com/TheQmaks/crowdcast",{"basePath":19,"githubOwner":20,"githubRepo":21,"locale":22,"slug":21,"type":23},"skills/crowdcast","TheQmaks","crowdcast","en","skill",{"evaluate":25,"extract":38},{"promptVersionExtension":26,"promptVersionScoring":27,"score":28,"tags":29,"targetMarket":36,"tier":37},"3.0.0","4.4.0",98,[30,31,32,33,34,35],"simulation","multi-agent","social-dynamics","prediction","creative-writing","ai-orchestration","global","verified",{"commitSha":39,"license":40},"HEAD","MIT",{"parentExtensionId":5,"repoId":42},"kd760z3j82spgwn0tjtqghm9q586nsyy",[35,34,31,33,30,32],{"evaluatedAt":45,"extractAt":46,"updatedAt":47},1778698138126,1778698083702,1778698177653,{"reviewCount":11},{"description":50,"installMethods":51,"name":21,"sourceUrl":17},"Multi-agent social simulation for prediction and creative exploration. Zero external dependencies — runs entirely within Claude Code.",{"claudeCode":21},{"_creationTime":53,"_id":54,"extensionId":5,"locale":22,"result":55,"trustSignals":265,"workflow":279},1778698118412.656,"kn7a3vekazdzv5j4gfgq6wekk186ngp7",{"checks":56,"evaluatedAt":241,"extensionSummary":242,"features":243,"nonGoals":250,"promptVersionExtension":26,"promptVersionScoring":27,"purpose":254,"rationale":255,"score":28,"summary":256,"tags":257,"targetMarket":36,"tier":37,"useCases":260},[57,62,65,68,72,75,79,83,86,89,93,97,101,105,108,111,114,117,120,123,127,131,135,139,143,146,149,152,156,159,162,165,168,171,174,178,182,186,189,193,196,199,202,205,208,211,214,217,220,223,227,230,233,237],{"category":58,"check":59,"severity":60,"summary":61},"Practical Utility","Problem relevance","pass","The description clearly articulates the problem of needing a multi-agent social simulation for prediction and exploration, directly addressing a user need for such simulations without external dependencies.",{"category":58,"check":63,"severity":60,"summary":64},"Unique selling proposition","The extension offers significant value over simple prompting by providing a structured, multi-agent simulation framework with agent profiling, interaction modeling, and reporting, all within Claude Code, which is a unique capability.",{"category":58,"check":66,"severity":60,"summary":67},"Production readiness","The extension covers the complete lifecycle from document analysis and agent profiling to simulation and reporting, with a resume capability, indicating it is ready for production workflows.",{"category":69,"check":70,"severity":60,"summary":71},"Scope","Single responsibility principle","The plugin focuses on multi-agent social simulation, with related sub-commands like analyze, resume, report, and interview, all falling under the coherent domain of simulation management.",{"category":69,"check":73,"severity":60,"summary":74},"Description quality","The displayed description accurately reflects the extension's core functionality: multi-agent social simulation, prediction, creative exploration, and zero external dependencies within Claude Code.",{"category":76,"check":77,"severity":60,"summary":78},"Invocation","Scoped tools","Tools like `simulate`, `analyze`, `resume`, `report`, and `interview` are narrow verb-noun specialists, making them easy for the agent to select and reducing attack surface.",{"category":80,"check":81,"severity":60,"summary":82},"Documentation","Configuration & parameter reference","The README and SKILL.md provide detailed documentation for all commands, file paths, and optional flags, including structure and parameters. Specific simulation parameters are documented in `config.json` which is explained as modifiable.",{"category":69,"check":84,"severity":60,"summary":85},"Tool naming","Tool names like `simulate`, `analyze`, `resume`, `report`, and `interview` are descriptive, verb-noun based, and fit the declared domain.",{"category":69,"check":87,"severity":60,"summary":88},"Minimal I/O surface","Inputs are well-defined file paths and prompts, and outputs are structured reports or simulation state files, adhering to minimal and documented schemas.",{"category":90,"check":91,"severity":60,"summary":92},"License","License usability","The extension is licensed under MIT, a permissive open-source license, clearly stated in the README.",{"category":94,"check":95,"severity":60,"summary":96},"Maintenance","Commit recency","The last commit was on May 8, 2026, well within the last 90 days, indicating active maintenance.",{"category":94,"check":98,"severity":99,"summary":100},"Dependency Management","not_applicable","The extension explicitly states 'Zero external dependencies — runs entirely within Claude Code,' meaning no third-party dependencies require management.",{"category":102,"check":103,"severity":99,"summary":104},"Security","Secret Management","The extension does not appear to use or handle any secrets, as it runs entirely within Claude Code without external API integrations or configurations.",{"category":102,"check":106,"severity":60,"summary":107},"Injection","The extension isolates user inputs (documents, prompts) and agent-generated data within its own simulation environment, treating external files as data and not instructions.",{"category":102,"check":109,"severity":60,"summary":110},"Transitive Supply-Chain Grenades","All code and data are bundled within the repository, with no runtime downloads or execution of external scripts, ensuring a contained supply chain.",{"category":102,"check":112,"severity":60,"summary":113},"Sandbox Isolation","The plugin operates within the Claude Code environment and stores simulation state in `.crowdcast/simulations/`, adhering to local file paths and not attempting to modify external system files.",{"category":102,"check":115,"severity":60,"summary":116},"Sandbox escape primitives","No evidence of detached processes or retry loops around denied tool calls is found; the simulation logic appears contained within sequential agent dispatches.",{"category":102,"check":118,"severity":60,"summary":119},"Data Exfiltration","The extension is designed to run locally within Claude Code and does not make any outbound network calls for data submission or telemetry, thus preventing data exfiltration.",{"category":102,"check":121,"severity":60,"summary":122},"Hidden Text Tricks","Bundled content appears to be clean, readable code and documentation without hidden steering characters or obfuscation techniques.",{"category":124,"check":125,"severity":60,"summary":126},"Hooks","Opaque code execution","The extension's logic is primarily defined in readable SKILL.md and reference files, with no evidence of obfuscated or minified code execution.",{"category":128,"check":129,"severity":60,"summary":130},"Portability","Structural Assumption","The skill uses relative paths within its own designated simulation directory and clearly outlines installation methods, avoiding assumptions about user project structure.",{"category":132,"check":133,"severity":60,"summary":134},"Trust","Issues Attention","There are 0 open and 0 closed issues in the last 90 days, indicating minimal current activity but no signs of neglect. Closure rate is not applicable.",{"category":136,"check":137,"severity":60,"summary":138},"Versioning","Release Management","A manifest version (`0.1.0`) is present in `plugin.json` and `SKILL.md`, and installation instructions reference specific tags or clone methods, providing clear versioning.",{"category":140,"check":141,"severity":60,"summary":142},"Code Execution","Validation","Input validation appears robust, with specific handling for file paths, prompts, and simulation IDs, and schema definitions are referenced for data structures.",{"category":102,"check":144,"severity":60,"summary":145},"Unguarded Destructive Operations","The simulation process involves file writes but is contained within the plugin's designated directory and is not inherently destructive to the user's system outside of its own state.",{"category":140,"check":147,"severity":60,"summary":148},"Error Handling","The SKILL.md outlines specific error handling for subagent failures, simulation not found, agent not found, and seed file issues, providing clear user messages and resume options.",{"category":140,"check":150,"severity":99,"summary":151},"Logging","The extension does not appear to perform destructive actions or outbound calls that would necessitate a local audit log, focusing on internal state management.",{"category":153,"check":154,"severity":99,"summary":155},"Compliance","GDPR","The extension operates on user-provided documents and simulates agent interactions internally, without submitting personal data to third parties.",{"category":153,"check":157,"severity":60,"summary":158},"Target market","The extension is designed to run within Claude Code and does not have any regional or jurisdictional limitations, making it globally applicable.",{"category":128,"check":160,"severity":60,"summary":161},"Runtime stability","The extension is designed to run within Claude Code, using standard bash and Python scripts, making it platform-independent as long as Claude Code is supported.",{"category":80,"check":163,"severity":60,"summary":164},"README","The README provides a comprehensive overview of the extension's purpose, features, comparison to alternatives, installation, and usage.",{"category":69,"check":166,"severity":60,"summary":167},"Tool surface size","The plugin exposes 5 primary commands (`simulate`, `analyze`, `resume`, `report`, `interview`), which is within the target range of 3-10 tools.",{"category":76,"check":169,"severity":60,"summary":170},"Overlapping near-synonym tools","Each tool (`simulate`, `analyze`, `resume`, `report`, `interview`) has a distinct function, avoiding redundant or overlapping near-synonym names.",{"category":80,"check":172,"severity":60,"summary":173},"Phantom features","All described features, including simulation modes, resumption, reporting, and interviewing, are directly implemented and documented in the SKILL.md and README.",{"category":175,"check":176,"severity":60,"summary":177},"Install","Installation instruction","The README provides clear, copy-pasteable installation instructions for three methods (direct clone, symlink, marketplace) and usage examples.",{"category":179,"check":180,"severity":60,"summary":181},"Errors","Actionable error messages","Error messages clearly state the problem (e.g., simulation not found, agent not found) and provide remediation steps (e.g., list simulations, choose agent).",{"category":183,"check":184,"severity":99,"summary":185},"Execution","Pinned dependencies","The extension uses no third-party dependencies, thus requiring no pinning or interpreter declaration beyond what Claude Code provides.",{"category":69,"check":187,"severity":99,"summary":188},"Dry-run preview","The extension is primarily analytical and simulation-focused; state changes occur within its own isolated directory and do not require a dry-run mode.",{"category":190,"check":191,"severity":60,"summary":192},"Protocol","Idempotent retry & timeouts","The simulation is designed to be resumable, indicating idempotency for state changes. Sequential dispatch of simulation chunks implies handling of state persistence without explicit timeouts mentioned for individual agent calls.",{"category":153,"check":194,"severity":99,"summary":195},"Telemetry opt-in","The extension does not emit any telemetry, operating entirely locally within Claude Code.",{"category":76,"check":197,"severity":60,"summary":198},"Name collisions","The plugin's main command is `/crowdcast`, which is distinct and unlikely to collide with Claude Code built-ins or other skills.",{"category":76,"check":200,"severity":99,"summary":201},"Hooks-off mechanism","As a plugin that orchestrates sub-agents rather than directly applying hooks to user prompts or tool calls, a hooks-off mechanism is not applicable.",{"category":76,"check":203,"severity":99,"summary":204},"Hook matcher tightness","The extension does not appear to use explicit hooks defined in `plugin.json`; it orchestrates agents via SKILL.md.",{"category":102,"check":206,"severity":99,"summary":207},"Hook security","The extension does not utilize `PreToolUse` or other hooks that could mutate prompts or perform network actions.",{"category":124,"check":209,"severity":99,"summary":210},"Silent prompt rewriting","The extension does not employ `UserPromptSubmit` hooks that would rewrite user prompts.",{"category":102,"check":212,"severity":99,"summary":213},"Permission Hook","There are no `PermissionRequest` hooks present in the plugin.",{"category":153,"check":215,"severity":99,"summary":216},"Hook privacy","The extension does not use hooks for logging or telemetry that would send data over the network.",{"category":140,"check":218,"severity":99,"summary":219},"Hook dependency","The extension's core logic is in readable SKILL.md and reference files, and it does not rely on external hooks.",{"category":80,"check":221,"severity":60,"summary":222},"Feature Transparency","The README and SKILL.md clearly explain the simulation modes, commands, and their functionalities, aligning with the implementation.",{"category":224,"check":225,"severity":60,"summary":226},"Convention","Layout convention adherence","The plugin follows Claude Code conventions, storing `plugin.json` in `.claude-plugin/` and using `SKILL.md` for orchestration, with no `bin/` directory entries to document.",{"category":224,"check":228,"severity":60,"summary":229},"Plugin state","Simulation state is managed within the `.crowdcast/simulations/` directory, which aligns with best practices for persistent state within the plugin's scope.",{"category":102,"check":231,"severity":99,"summary":232},"Keychain-stored secrets","The extension does not handle secrets, so it does not route them through `userConfig`.",{"category":234,"check":235,"severity":99,"summary":236},"Dependencies","Tagged release sourcing","There are no bundled MCP servers; the extension is a self-contained skill.",{"category":238,"check":239,"severity":60,"summary":240},"Installation","Clean uninstall","The installation methods focus on cloning or symlinking into the Claude Code skills directory, and state is managed locally, ensuring a clean uninstall by removing the directory.",1778698117792,"This plugin provides a multi-agent social simulation environment that runs entirely within Claude Code, requiring no external dependencies. Users can upload documents, define simulation parameters, and run predictions or creative narratives, with features for resuming interrupted simulations and interviewing agents.",[244,245,246,247,248,249],"Multi-agent social simulation","Zero external dependencies","Prediction and creative narrative modes","Document analysis and knowledge graph extraction","Resumable simulations","In-character agent interviews",[251,252,253],"Massive scale simulations beyond ~100 agents","Replacing dedicated forecasting or narrative generation tools for highly specialized tasks","Running externally via web servers or complex infrastructure","To enable users to conduct sophisticated multi-agent social simulations for prediction and creative exploration directly within Claude Code, offering a simpler, cheaper, and more accessible alternative to complex external tools.","The extension is exceptionally well-documented, secure, and production-ready, with a clear focus on its core simulation functionality and excellent adherence to best practices. No significant issues were found.","A highly polished and self-contained plugin for multi-agent social simulations within Claude Code.",[30,31,258,259,33,34],"ai-agents","social-simulation",[261,262,263,264],"Predicting public reaction to news or policy changes","Exploring fictional scenarios and character arcs","Analyzing stakeholder interactions","Simulating social media dynamics",{"codeQuality":266,"collectedAt":268,"documentation":269,"maintenance":272,"security":277,"testCoverage":278},{"hasLockfile":267},false,1778698099115,{"descriptionLength":270,"readmeSize":271},133,6141,{"closedIssues90d":11,"forks":273,"hasChangelog":267,"manifestVersion":274,"openIssues90d":11,"pushedAt":275,"stars":276},1,"0.1.0",1778251877000,4,{"hasNpmPackage":267,"smitheryVerified":267},{"hasCi":267,"hasTests":267},{"updatedAt":280},1778698118412,{"basePath":282,"githubOwner":20,"githubRepo":21,"locale":22,"slug":21,"type":283},"","plugin",{"_creationTime":285,"_id":286,"community":287,"display":288,"identity":291,"parentExtension":293,"providers":294,"relations":306,"tags":307,"workflow":308},1778698083702.126,"k1777shvk6f4zhzpnan7nm5ma586m6kf",{"reviewCount":11},{"description":289,"installMethods":290,"name":16,"sourceUrl":17},"TheQmaks Claude Code marketplace — hosts the Crowdcast multi-agent social simulation plugin.",{"claudeCode":15},{"basePath":282,"githubOwner":20,"githubRepo":21,"locale":22,"slug":21,"type":292},"marketplace",null,{"evaluate":295,"extract":301},{"promptVersionExtension":296,"promptVersionScoring":27,"score":297,"tags":298,"targetMarket":36,"tier":37},"3.1.0",99,[30,31,33,299,23,300],"creative","zero-dependency",{"commitSha":39,"license":40,"marketplace":302,"plugin":304},{"name":303,"pluginCount":273},"theqmaks",{"mcpCount":11,"provider":305,"skillCount":11},"classify",{"repoId":42},[299,31,33,30,23,300],{"evaluatedAt":309,"extractAt":46,"updatedAt":310},1778698098814,1778698177285,{"evaluate":312,"extract":314},{"promptVersionExtension":26,"promptVersionScoring":27,"score":28,"tags":313,"targetMarket":36,"tier":37},[30,31,258,259,33,34],{"commitSha":39,"plugin":315},{"mcpCount":11,"provider":305,"skillCount":273},{"parentExtensionId":286,"repoId":42},{"_creationTime":318,"_id":42,"identity":319,"providers":320,"workflow":371},1778698079325.3296,{"githubOwner":20,"githubRepo":21,"sourceUrl":17},{"classify":321,"discover":361,"github":364},{"commitSha":39,"extensions":322},[323,333,343],{"basePath":282,"description":289,"displayName":303,"installMethods":324,"rationale":325,"selectedPaths":326,"source":332,"sourceLanguage":22,"type":292},{"claudeCode":15},"marketplace.json at .claude-plugin/marketplace.json",[327,330],{"path":328,"priority":329},".claude-plugin/marketplace.json","mandatory",{"path":331,"priority":329},"README.md","rule",{"basePath":282,"description":50,"displayName":21,"installMethods":334,"rationale":335,"selectedPaths":336,"source":332,"sourceLanguage":22,"type":283},{"claudeCode":21},"plugin manifest at .claude-plugin/plugin.json",[337,339,340],{"path":338,"priority":329},".claude-plugin/plugin.json",{"path":331,"priority":329},{"path":341,"priority":342},"skills/crowdcast/SKILL.md","medium",{"basePath":19,"description":13,"displayName":21,"installMethods":344,"rationale":345,"selectedPaths":346,"source":332,"sourceLanguage":22,"type":23},{"claudeCode":15},"SKILL.md frontmatter at skills/crowdcast/SKILL.md",[347,349,351,353,355,357,359],{"path":348,"priority":329},"SKILL.md",{"path":350,"priority":342},"references/data-schemas.md",{"path":352,"priority":342},"references/phase1-analyzer.md",{"path":354,"priority":342},"references/phase2-profiler.md",{"path":356,"priority":342},"references/phase3-simulator-creative.md",{"path":358,"priority":342},"references/phase3-simulator-forecast.md",{"path":360,"priority":342},"references/phase4-reporter.md",{"sources":362},[363],"manual",{"closedIssues90d":11,"description":365,"forks":273,"openIssues90d":11,"pushedAt":275,"readmeSize":271,"stars":276,"topics":366},"Multi-agent social simulation as a Claude Code skill. Zero dependencies — predict anything with /crowdcast simulate.",[367,258,368,369,370,31,33,30,259,21],"agent-skills","claude","claude-code","claude-skill",{"classifiedAt":372,"discoverAt":373,"extractAt":374,"githubAt":374,"updatedAt":372},1778698083527,1778698079325,1778698081672,[258,34,31,33,30,259],{"evaluatedAt":280,"extractAt":46,"updatedAt":377},1778698177457,[],[380,410,442,472,497,525],{"_creationTime":381,"_id":382,"community":383,"display":384,"identity":389,"providers":393,"relations":404,"tags":406,"workflow":407},1778685949178.788,"k176z1bn53zzf0sm269h9x914x86nmtv",{"reviewCount":11},{"description":385,"installMethods":386,"name":387,"sourceUrl":388},"Build AG2 (AutoGen) multi-agent systems with slash commands: scaffold agents, wire workflows, create tools, and review code",{"claudeCode":387},"ag2-agent-builder","https://github.com/davepoon/buildwithclaude",{"basePath":390,"githubOwner":391,"githubRepo":392,"locale":22,"slug":387,"type":283},"plugins/ag2-agent-builder","davepoon","buildwithclaude",{"evaluate":394,"extract":402},{"promptVersionExtension":26,"promptVersionScoring":27,"score":395,"tags":396,"targetMarket":36,"tier":37},100,[397,31,398,399,400,401],"autogen","agent-building","workflow","tools","python",{"commitSha":39,"license":403},"Apache-2.0",{"repoId":405},"kd719kw54vhmcscq7ckdp59fg586mnt6",[398,397,31,401,400,399],{"evaluatedAt":408,"extractAt":409,"updatedAt":408},1778687364609,1778685949178,{"_creationTime":411,"_id":412,"community":413,"display":414,"identity":420,"providers":422,"relations":436,"tags":438,"workflow":439},1778695548458.3262,"k170h0janaa9kwn7cfgfz2ykss86mmh9",{"reviewCount":11},{"description":415,"installMethods":416,"name":418,"sourceUrl":419},"350 agentic skills across 64 domains, 72 agent personas, and 16 team compositions following the agentskills.io open standard",{"claudeCode":417},"agent-almanac","Agent Almanac","https://github.com/pjt222/agent-almanac",{"basePath":282,"githubOwner":421,"githubRepo":417,"locale":22,"slug":417,"type":283},"pjt222",{"evaluate":423,"extract":433},{"promptVersionExtension":26,"promptVersionScoring":27,"score":297,"tags":424,"targetMarket":36,"tier":37},[258,425,426,427,428,429,430,431,432],"skills","development-tools","workflow-automation","knowledge-management","r-development","python-development","typescript-development","cli-tools",{"commitSha":39,"license":40,"plugin":434},{"mcpCount":11,"provider":305,"skillCount":435},353,{"repoId":437},"kd7aryv63z61j39n2td1aeqkvh86mh12",[258,432,426,428,430,429,425,431,427],{"evaluatedAt":440,"extractAt":441,"updatedAt":440},1778695566886,1778695548458,{"_creationTime":443,"_id":444,"community":445,"display":446,"identity":451,"providers":454,"relations":465,"tags":468,"workflow":469},1778699234184.6104,"k17brg5egdw1jbncj1j4wfv3fh86n639",{"reviewCount":11},{"description":447,"installMethods":448,"name":449,"sourceUrl":450},"Multi-agent orchestration system for Claude Code",{"claudeCode":449},"oh-my-claudecode","https://github.com/Yeachan-Heo/oh-my-claudecode",{"basePath":282,"githubOwner":452,"githubRepo":449,"locale":453,"slug":449,"type":283},"Yeachan-Heo","fr",{"evaluate":455,"extract":462},{"promptVersionExtension":26,"promptVersionScoring":27,"score":297,"tags":456,"targetMarket":36,"tier":37},[31,457,458,459,460,399,461],"orchestration","automation","ai-agent","development-tool","cli",{"commitSha":39,"license":40,"plugin":463},{"mcpCount":11,"provider":305,"skillCount":464},38,{"parentExtensionId":466,"repoId":467},"k17faea1fme9qa3pf4hzs9x78d86n2kj","kd74zv63fryf9prygtq7gf4es986n22y",[459,458,461,460,31,457,399],{"evaluatedAt":470,"extractAt":471,"updatedAt":470},1778699261932,1778699234184,{"_creationTime":473,"_id":474,"community":475,"display":476,"identity":480,"providers":482,"relations":493,"tags":494,"workflow":495},1778685949178.7883,"k17eq6cjyjedtcvvzycxanmpg586naxx",{"reviewCount":11},{"description":477,"installMethods":478,"name":479,"sourceUrl":388},"Multi-agent development system with three specialized agents (PM, Dev, QA) coordinated through checklist methodology based on The Checklist Manifesto and Boeing's checklist engineering",{"claudeCode":479},"agent-triforce",{"basePath":481,"githubOwner":391,"githubRepo":392,"locale":22,"slug":479,"type":283},"plugins/agent-triforce",{"evaluate":483,"extract":490},{"promptVersionExtension":26,"promptVersionScoring":27,"score":297,"tags":484,"targetMarket":36,"tier":37},[31,485,399,486,487,488,489],"development","pm","dev","qa","checklist",{"commitSha":39,"license":40,"plugin":491},{"mcpCount":11,"provider":305,"skillCount":492},6,{"repoId":405},[489,487,485,31,486,488,399],{"evaluatedAt":496,"extractAt":409,"updatedAt":496},1778687396752,{"_creationTime":498,"_id":499,"community":500,"display":501,"identity":506,"providers":510,"relations":518,"tags":521,"workflow":522},1778675056600.2036,"k17ecjvwgk0pnvb9557bdnq7wd86m7yq",{"reviewCount":11},{"description":502,"installMethods":503,"name":504,"sourceUrl":505},"Multi-agent collaboration plugin for Claude Code. Spawn N parallel subagents that compete on code optimization, content drafts, research approaches, or any problem that benefits from diverse solutions. Evaluate by metric or LLM judge, merge the winner. 7 slash commands, agent templates, git DAG orchestration, message board coordination.",{"claudeCode":504},"agenthub","https://github.com/alirezarezvani/claude-skills",{"basePath":507,"githubOwner":508,"githubRepo":509,"locale":22,"slug":504,"type":283},"engineering/agenthub","alirezarezvani","claude-skills",{"evaluate":511,"extract":515},{"promptVersionExtension":26,"promptVersionScoring":27,"score":297,"tags":512,"targetMarket":36,"tier":37},[31,513,514,457,458,460],"collaboration","git",{"commitSha":39,"license":40,"plugin":516},{"mcpCount":11,"provider":305,"skillCount":517},8,{"parentExtensionId":519,"repoId":520},"k17dce6sbramb6sxm7ksr3928x86ncfs","kd7ff9s1w43mfyy1n7hf87816186m6px",[458,513,460,514,31,457],{"evaluatedAt":523,"extractAt":524,"updatedAt":523},1778675441637,1778675056600,{"_creationTime":526,"_id":527,"community":528,"display":529,"identity":534,"providers":536,"relations":545,"tags":547,"workflow":548},1778685949178.7812,"k175x7gdgm96tx3er9fvtsc71586mrnn",{"reviewCount":11},{"description":530,"installMethods":531,"name":533,"sourceUrl":388},"Commands for scenario simulation and decision modeling",{"claudeCode":532},"commands-simulation-modeling","Simulation Modeling Commands",{"basePath":535,"githubOwner":391,"githubRepo":392,"locale":22,"slug":532,"type":283},"plugins/commands-simulation-modeling",{"evaluate":537,"extract":544},{"promptVersionExtension":26,"promptVersionScoring":27,"score":297,"tags":538,"targetMarket":36,"tier":37},[30,539,540,541,542,543,283],"modeling","decision-making","business-analysis","scenario-planning","command",{"commitSha":39,"license":40},{"parentExtensionId":546,"repoId":405},"k17dg0d5d8g0a5nhm59gm0tkwx86nbt4",[541,543,540,539,283,542,30],{"evaluatedAt":549,"extractAt":409,"updatedAt":549},1778686713853]