[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77M3EDZNV97EWNJ3BRZSW0M":3,"skill-same:01M77M3EDZNV97EWNJ3BRZSW0M":60},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":38,"ownerDescription":39,"updatedAt":40,"install":41,"resources":53},"01M77M3EDZNV97EWNJ3BRZSW0M","route",null,"Model and effort per agent role (orchestrator, worker, verifier, retrieval) for a multi-agent run, resolved through the bundled defaults and the user, team and personal override config layers into fenced JSON with single-agent and fan-out variants and the layer behind each value; fan-out stays off frontier models unless config opts in. Use when asked 'which model for the subagents', 'route the roles', 'what effort should the workers use', 'roles for the workflow args', 'model routing' or 'is fan-out on Fable', or before a skill launches a workflow that takes args.roles.","melodic-software\u002Fclaude-code-plugins","melodic-software","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F58273638?v=4","01M77JVQTXNGKCE4MDFY2BC936","Melodic Software","01M77JVQVN9QDWKAH6W03ANP76",30,"MIT","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fmulti-agent\u002Fskills\u002Froute\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\ndescription: \"Model and effort per agent role (orchestrator, worker, verifier, retrieval) for a multi-agent run, resolved through the bundled defaults and the user, team and personal override config layers into fenced JSON with single-agent and fan-out variants and the layer behind each value; fan-out stays off frontier models unless config opts in. Use when asked 'which model for the subagents', 'route the roles', 'what effort should the workers use', 'roles for the workflow args', 'model routing' or 'is fan-out on Fable', or before a skill launches a workflow that takes args.roles.\"\nargument-hint: \"\u003C\u003Crole>|all> [workload] [session=\u003Calias>]\"\nuser-invocable: true\ndisable-model-invocation: false\nmetadata:\n  workflow-stage: session\n  summary: Resolve model and effort per agent role for a multi-agent run\nallowed-tools: [\"Bash(${CLAUDE_SKILL_DIR}\u002Fscripts\u002Froute.sh:*)\"]\nshell: bash\n---\n\nKeys, layers and the fan-out guard are defined in\n[`${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fconfig.md`](${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fconfig.md);\nread it when a note or a user question concerns a key, a layer or the guard.\n\n## Arguments\n\n- `\u003C\u003Crole>|all>`: one of `orchestrator`, `worker`, `verifier`, `retrieval`, or\n  `all` for the whole map.\n- `[workload]`: optional, the second bare argument; applies the role's\n  `workloads.\u003Cw>` keys. The bundled layer declares `code`, `research` and\n  `mechanical`; a config layer may declare more (`workloads.\u003Cw>: true`).\n- `session=\u003Calias>`: the session model's alias. When the caller did not pass\n  one, fill it from your own model ID: the family name in it (`opus`,\n  `sonnet`, `haiku`, `fable`) is the alias. When you cannot tell, omit it; the\n  resolver then treats the session as frontier, so fan-out stages name\n  `fanout.model`.\n\n## Run\n\n```bash\n${CLAUDE_SKILL_DIR}\u002Fscripts\u002Froute.sh $ARGUMENTS\n```\n\nAppend `session=\u003Calias>` when `$ARGUMENTS` carries none and you know your model\nfamily.\n\n## Output\n\nThe JSON exactly as printed, in one fenced `json` block. Below it, one line per\nrole in this form:\n\n```text\n\u003Crole>: single \u003Cmodel|inherit: omit the model option> @ \u003Ceffort>; fanout \u003Cmodel|inherit: omit the model option> @ \u003Ceffort> (basis: model \u003Cbasis>, fanout model \u003Cbasis>, effort \u003Cbasis>)\n```\n\nWrite `inherit: omit the model option` wherever a variant's `omit_model` is\ntrue, so a caller copying the line passes no model and the agent runs on the\nsession model. Each `\u003Cbasis>` is the role's `basis` entry as printed:\n`upstream` (an upstream statement sets it), `judgment` (no upstream statement\ndoes; the reason is in `defaults.yaml`), `config` (a consumer layer set it) or\n`unrecorded`; the fanout model's basis is the guard's when `guarded` is true.\nAfter the per-role lines, write this line as is:\n\n```text\nEffort above maxEffortLevel runs at the cap; see reference\u002Fconfig.md \"Hard cap\".\n```\n\nThen list every entry of `notes` (a skipped layer, a rejected value, an ignored\nkey, a role that resolves to haiku) as written. A haiku note means the role\nruns on a model no role here has passed the routing eval on; the rule is in\n[`${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Frouting-rubric.md`](${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Frouting-rubric.md).\nExit 2 means an unknown role, workload or argument: relay the valid roles or\ndeclared workloads from the error and stop.\n\nA caller launching a workflow passes the JSON's `roles` object as\n`args.roles`, unchanged. A caller spawning a subagent through the Agent tool\nwith no named type applies one variant to that call: it passes the variant's\nmodel as `model`, or omits `model` when `omit_model` is true, and always\npasses its effort as `effort`.\n\n- **Pointer**: when a routed Agent dispatch runs at a different level than\n  the one passed, or you need the values the call accepts, fetch\n  [sub-agents: choose an effort level](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fsub-agents#choose-an-effort-level),\n  [sub-agents: choose a model](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fsub-agents#choose-a-model)\n  and [model config: set the effort level](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fmodel-config#set-the-effort-level)\n  live.\n\n## What this skill does NOT do\n\n- Write any configuration layer. That is `\u002Fmulti-agent:setup apply`.\n- Route a named agent. An agent dispatched by its own type, such as\n  `implementation:implementer`, `implementation:scoped-implementer` or\n  `implementation:phase-verifier`, owns its tier through its own frontmatter\n  and its dispatcher's rules. The map governs generic `agent()` calls and\n  Agent dispatches without a named type.\n- Choose between a workflow and subagents. That is `\u002Fmulti-agent:assess`.\n- Check the defaults against upstream. That is `\u002Fmulti-agent:audit-defaults`.\n\n## Next\n\n\u002Fmulti-agent:audit-defaults\nRechecks a default that looks wrong for the current models.\n\n## Gotchas\n\n- Only aliases are accepted. A full model id in a layer is rejected and the\n  layer below supplies the key. Why aliases: [Model aliases](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fmodel-config#model-aliases).\n- `fanout` and `single` differ only under a frontier or unknown session. Under\n  an Opus session both say `inherit`, and `opus` would name the same model.\n- The map never routes a named agent (`agentType`, or an Agent dispatch by\n  subagent type), so the fan-out guard does not reach it on its own. Its\n  dispatcher may pass `model` or `effort` on the call; for which source wins\n  over the definition's pins, see the pointer record under Output. Keeping a\n  named agent such as `scoped-implementer` off a frontier session model is\n  that dispatcher's rule to keep.\n- The route output never reflects `maxEffortLevel`; the cap applies at run\n  time.\n- The bundled defaults set only the `mechanical` workload, which runs the\n  worker on `sonnet`; `code` keeps the role's model, and any other workload key\n  comes from a config layer. A caller that wants the session model for\n  mechanical work sets `roles.worker.workloads.mechanical.model: inherit`.\n- Team and personal override layers resolve against the repository root of the working\n  directory. Inside a second worktree, run from that worktree.\n","Keys, layers and the fan-out guard are defined in\n[`${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fconfig.md`](${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fconfig.md);\nread it when a note or a user question concerns a key, a layer or the guard.\n\n## Arguments\n\n- `\u003C\u003Crole>|all>`: one of `orchestrator`, `worker`, `verifier`, `retrieval`, or\n  `all` for the whole map.\n- `[workload]`: optional, the second bare argument; applies the role's\n  `workloads.\u003Cw>` keys. The bundled layer declares `code`, `research` and\n  `mechanical`; a config layer may declare more (`workloads.\u003Cw>: true`).\n- `session=\u003Calias>`: the session model's alias. When the caller did not pass\n  one, fill it from your own model ID: the family name in it (`opus`,\n  `sonnet`, `haiku`, `fable`) is the alias. When you cannot tell, omit it; the\n  resolver then treats the session as frontier, so fan-out stages name\n  `fanout.model`.\n\n## Run\n\n```bash\n${CLAUDE_SKILL_DIR}\u002Fscripts\u002Froute.sh $ARGUMENTS\n```\n\nAppend `session=\u003Calias>` when `$ARGUMENTS` carries none and you know your model\nfamily.\n\n## Output\n\nThe JSON exactly as printed, in one fenced `json` block. Below it, one line per\nrole in this form:\n\n```text\n\u003Crole>: single \u003Cmodel|inherit: omit the model option> @ \u003Ceffort>; fanout \u003Cmodel|inherit: omit the model option> @ \u003Ceffort> (basis: model \u003Cbasis>, fanout model \u003Cbasis>, effort \u003Cbasis>)\n```\n\nWrite `inherit: omit the model option` wherever a variant's `omit_model` is\ntrue, so a caller copying the line passes no model and the agent runs on the\nsession model. Each `\u003Cbasis>` is the role's `basis` entry as printed:\n`upstream` (an upstream statement sets it), `judgment` (no upstream statement\ndoes; the reason is in `defaults.yaml`), `config` (a consumer layer set it) or\n`unrecorded`; the fanout model's basis is the guard's when `guarded` is true.\nAfter the per-role lines, write this line as is:\n\n```text\nEffort above maxEffortLevel runs at the cap; see reference\u002Fconfig.md \"Hard cap\".\n```\n\nThen list every entry of `notes` (a skipped layer, a rejected value, an ignored\nkey, a role that resolves to haiku) as written. A haiku note means the role\nruns on a model no role here has passed the routing eval on; the rule is in\n[`${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Frouting-rubric.md`](${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Frouting-rubric.md).\nExit 2 means an unknown role, workload or argument: relay the valid roles or\ndeclared workloads from the error and stop.\n\nA caller launching a workflow passes the JSON's `roles` object as\n`args.roles`, unchanged. A caller spawning a subagent through the Agent tool\nwith no named type applies one variant to that call: it passes the variant's\nmodel as `model`, or omits `model` when `omit_model` is true, and always\npasses its effort as `effort`.\n\n- **Pointer**: when a routed Agent dispatch runs at a different level than\n  the one passed, or you need the values the call accepts, fetch\n  [sub-agents: choose an effort level](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fsub-agents#choose-an-effort-level),\n  [sub-agents: choose a model](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fsub-agents#choose-a-model)\n  and [model config: set the effort level](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fmodel-config#set-the-effort-level)\n  live.\n\n## What this skill does NOT do\n\n- Write any configuration layer. That is `\u002Fmulti-agent:setup apply`.\n- Route a named agent. An agent dispatched by its own type, such as\n  `implementation:implementer`, `implementation:scoped-implementer` or\n  `implementation:phase-verifier`, owns its tier through its own frontmatter\n  and its dispatcher's rules. The map governs generic `agent()` calls and\n  Agent dispatches without a named type.\n- Choose between a workflow and subagents. That is `\u002Fmulti-agent:assess`.\n- Check the defaults against upstream. That is `\u002Fmulti-agent:audit-defaults`.\n\n## Next\n\n\u002Fmulti-agent:audit-defaults\nRechecks a default that looks wrong for the current models.\n\n## Gotchas\n\n- Only aliases are accepted. A full model id in a layer is rejected and the\n  layer below supplies the key. Why aliases: [Model aliases](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fmodel-config#model-aliases).\n- `fanout` and `single` differ only under a frontier or unknown session. Under\n  an Opus session both say `inherit`, and `opus` would name the same model.\n- The map never routes a named agent (`agentType`, or an Agent dispatch by\n  subagent type), so the fan-out guard does not reach it on its own. Its\n  dispatcher may pass `model` or `effort` on the call; for which source wins\n  over the definition's pins, see the pointer record under Output. Keeping a\n  named agent such as `scoped-implementer` off a frontier session model is\n  that dispatcher's rule to keep.\n- The route output never reflects `maxEffortLevel`; the cap applies at run\n  time.\n- The bundled defaults set only the `mechanical` workload, which runs the\n  worker on `sonnet`; `code` keeps the role's model, and any other workload key\n  comes from a config layer. A caller that wants the session model for\n  mechanical work sets `roles.worker.workloads.mechanical.model: inherit`.\n- Team and personal override layers resolve against the repository root of the working\n  directory. Inside a second worktree, run from that worktree.\n",{"shell":24,"metadata":25,"description":7,"allowed-tools":28,"argument-hint":30,"user-invocable":31,"disable-model-invocation":20},"bash",{"summary":26,"workflow-stage":27},"Resolve model and effort per agent role for a multi-agent run","session",[29],"Bash(${CLAUDE_SKILL_DIR}\u002Fscripts\u002Froute.sh:*)","\u003C\u003Crole>|all> [workload] [session=\u003Calias>]",true,"main","4f2dcaaff35e8f9fccc6a9f4d82a5830ab17a5c5","plugins\u002Fmulti-agent\u002Fskills\u002Froute",7,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins","https:\u002F\u002Fgithub.com\u002Fmelodic-software","https:\u002F\u002Fmelodicsoftware.com","Independent software studio building developer tools, automation, and application services, with roots in music.","2026-11-15 05:15:06",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":31},[43,46,49],{"tool":44,"command":45},"npx","npx skills add melodic-software\u002Fclaude-code-plugins --skill route",{"tool":47,"command":48},"bunx","bunx skills add melodic-software\u002Fclaude-code-plugins --skill route",{"tool":50,"command":51},"pnpm","pnpm dlx skills add melodic-software\u002Fclaude-code-plugins --skill route","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fmulti-agent\u002Fskills\u002Froute\u002FSKILL.md",[54],{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"scripts\u002Froute.sh","SCRIPT","脚本",795,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fmulti-agent\u002Fskills\u002Froute\u002Fscripts\u002Froute.sh",[61,68,75,81,86,93],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7DYYDG31B9YX7N9MB9QW2GW","track","Backlog reads through the bound tracker: search open and closed items, view one item with its comments and state history. Use when another skill searches or reads tracker items.","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsession-flow\u002Fevals\u002Frecall-still-reports-reopened-bug\u002Fwork-items-stub\u002Fskills\u002Ftrack\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7DYXVBAVG3NV30PA7GKW9Q6","reviewer-media","Reviewer media for one pull request: decides whether it needs a narrated walkthrough, builds the storyboard from \u002Freview:explain-change's digest, has \u002Fexplainer-video:produce render it and hands the manifest to \u002Fsource-control:pull-request media. Use when asked for 'reviewer media', 'a walkthrough video for this PR', 'a produced video of this change', or when pull-request ready or monitor hands a PR over.","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Freview\u002Fskills\u002Freviewer-media\u002FSKILL.md",[],[],{"skillNo":76,"name":5,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7DYRZ5YD44AMYH26YR25GZ8","Model and effort per agent role (orchestrator, worker, verifier, retrieval) for a multi-agent run, resolved through the bundled defaults and the user, team and personal override config layers into fenced JSON with single-agent and fan-out variants and the layer behind each value. Use when asked 'which model for the subagents', 'route the roles' or 'model routing', or before a skill passes a role's model on a spawn.","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fdiscovery\u002Fevals\u002Fex-model-pin-without-override\u002Fmulti-agent-stub\u002Fskills\u002Froute\u002FSKILL.md",[],[],{"skillNo":82,"name":5,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7DYRTVT4FWTGDJY0HCCFJMZ","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fdiscovery\u002Fevals\u002Fex-model-override-from-route\u002Fmulti-agent-stub\u002Fskills\u002Froute\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7DYNZC8PNW3T27V2ADKECKJ","principles","Module-design vocabulary for architecture findings, and the checks built on it. Use when: 'what is a deep module', 'what is a seam', 'deep vs shallow module', 'what is the deletion test', 'leverage and locality', 'module design vocabulary', 'which word do we use for X in architecture findings'. Scanning a codebase for friction is \u002Farchitecture:improve.","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Farchitecture\u002Fskills\u002Fprinciples\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7DYNMCZNEWBFHV9KTSS6H60","write","Structured five-field bug report (title, steps to reproduce, expected vs actual, justified severity, suggested fix location) from an informal description, read-only. Use when the user names a defect they observed, or asks for one written up ('report a bug', 'file a bug', 'write this up as a bug').","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Farchitecture\u002Fevals\u002Fdeepening-defect-goes-to-bugs-write\u002Fbugs-stub\u002Fskills\u002Fwrite\u002FSKILL.md",[],[]]