[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77M3MPQK40580V3D5SW34VJ":3,"skill-same:01M77M3MPQK40580V3D5SW34VJ":61},{"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":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":35,"ownerDescription":36,"updatedAt":37,"install":38,"resources":50},"01M77M3MPQK40580V3D5SW34VJ","setup",null,"Check the multi-agent role map (model and effort per role and the layer behind each value) or write confirmed keys into the user, team or local multi-agent.yaml layer.","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\u002Fsetup\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\ndescription: \"Check the multi-agent role map (model and effort per role and the layer behind each value) or write confirmed keys into the user, team or local multi-agent.yaml layer.\"\nargument-hint: \"[check|apply] [--layer user|team|local] [\u003Ckey>=\u003Cvalue> ...] [session=\u003Calias>]\"\nuser-invocable: true\ndisable-model-invocation: true\nallowed-tools: [\"Bash(${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fsetup.sh:*)\"]\nshell: bash\n---\n\n## Purpose\n\n`\u002Fmulti-agent:route` resolves the role map through four layers: the bundled\ndefaults, `~\u002F.claude\u002Fmulti-agent.yaml`, the team layer and\n`.claude\u002Fmulti-agent.local.yaml`. This skill shows what those layers resolve to\nand writes one of them. All three consumer layers absent is a valid state: the\nbundled defaults apply. Keys, values, layer paths and the fan-out guard are\ndefined in\n[`${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fconfig.md`](${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fconfig.md).\n\nNo argument means `check`. It installs nothing; the resolver needs only Bash,\nawk and git.\n\n## `check` (read-only)\n\n```bash\n${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fsetup.sh check session=\u003Calias>\n```\n\nPass `session=\u003Calias>` with the family in your own model ID (`opus`, `sonnet`,\n`haiku`, `fable`); omit it when you cannot tell, and the map is resolved as\nunder a frontier session. The JSON is the one `\u002Fmulti-agent:route all` prints.\nShow:\n\n1. one line per role: `single \u003Cmodel> @ \u003Ceffort>; fanout \u003Cmodel> @ \u003Ceffort>`,\n   with `inherit` written as `inherit: omit the model option`, and the layer\n   in `source` for each value;\n2. the `layers` rows (read, absent, skipped, or not applicable at a home or\n   non-repository root) and every entry of `notes` as written; each note (a\n   skipped layer, a rejected value, an ignored key) is a finding to report;\n3. the personal-override row: PASS when `.claude\u002Fmulti-agent.local.yaml` is gitignored,\n   else WARN with the recommended line `.claude\u002F**\u002F*.local.*`. Recommend the\n   line; do not edit `.gitignore`;\n4. each `WARN team:` row: a retired team file (the config block in\n   `docs\u002Fconventions\u002Fmulti-agent.md`, or `.claude\u002Fmulti-agent.yaml`) that the\n   resolver no longer reads. Relay the row's next step as written.\n\nIt modifies nothing.\n\n## `apply`\n\n1. Run `check` and show the map. This is the before state.\n2. Settle the layer with the user, recommendation first:\n   - `local` (`.claude\u002Fmulti-agent.local.yaml`): this checkout only, for this\n     person. The default for a personal preference.\n   - `team`: `docs\u002Fconventions\u002Fmulti-agent.yaml` (under the convention home the\n     repository binds). Shared with everyone who clones the repository.\n   - `user` (`~\u002F.claude\u002Fmulti-agent.yaml`): every repository on this machine.\n\n   `team` and `local` are refused at a home or non-repository root.\n3. Settle the keys. Ask only for what the user wants changed; each value comes\n   from the table in `config.md`. Pass every key to set as `\u003Ckey>=\u003Cvalue>`, and\n   `\u003Ckey>=` to remove one from that layer. Existing keys in the layer are kept.\n4. Preview, writing nothing:\n\n   ```bash\n   ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fsetup.sh apply --layer \u003Clayer> \u003Ckey>=\u003Cvalue> ...\n   ```\n\n   It prints the target path and a diff. It exits 1 without writing when the\n   resolver would reject or ignore a key; relay the reason and return to\n   step 3.\n5. Show the diff and ask for an explicit yes. Write only on that yes:\n\n   ```bash\n   ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fsetup.sh apply --layer \u003Clayer> --write \u003Ckey>=\u003Cvalue> ...\n   ```\n\n   It prints the path written and the keys it read back from the file.\n6. Run `check` again and show the after map beside the before one, naming each\n   value that changed and the layer that now supplies it. The file is what the\n   next `\u002Fmulti-agent:route` run reads; nothing about the running session\n   changes. For `team`, offer `git add` and a commit and run each only when the\n   user accepts.\n\n### The fan-out guard\n\nWith `fanout.frontier_guard: true`, the bundled value, a stage that runs more\nthan one agent never runs them on a frontier model: under a Fable\nsession, or a session the caller did not name, each fan-out variant that would\ninherit or name a frontier model takes `fanout.model` (`opus`) instead. A\nsingle synthesis or judge agent keeps the role's own model. The basis is\nrecorded beside the key in\n[`${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fdefaults.yaml`](${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fdefaults.yaml).\n\n`fanout.frontier_guard=false` is an explicit opt-in to frontier fan-outs: every\nparallel worker then runs on the session model, so a frontier session runs\nevery agent of the stage on the frontier model (rates:\n[Pricing: model pricing](https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Fabout-claude\u002Fpricing#model-pricing); usage:\n[Manage costs: Track your costs](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fcosts#track-your-costs)).\nBefore writing it, say this and ask the user to confirm that specific key,\nseparately from the rest of the change. Recommend the narrowest layer that\ncovers what they mean: `local` for one checkout, `user` for one machine, `team`\nonly when the whole team has agreed.\n\n## What this skill does NOT do\n\n- Edit `.gitignore`, `CLAUDE.md` or `AGENTS.md`.\n- Write a model ID. Only aliases are accepted, so the map stays portable across\n  providers.\n- Change a named agent's model or effort. An agent such as\n  `implementation:implementer` or `implementation:scoped-implementer` owns its\n  tier through its own frontmatter and whatever its dispatcher passes on the\n  call; the role map governs generic `agent()` and Agent dispatches only.\n- Recheck a default against upstream. That is `\u002Fmulti-agent:audit-defaults`.\n\n## Next\n\n\u002Fmulti-agent:route all\nPrints the map the next workflow reads from `args.roles`.\n\n## Gotchas\n\n- A layer file is rewritten whole, so its comments are not kept; the preview\n  says so when the file has any.\n- An existing layer that does not parse stops `apply` with the line and the\n  reason. Fix or remove the file first; setup never overwrites content it could\n  not read.\n- The first `team` write creates the YAML. A retired team file, which the\n  resolver no longer reads, seeds its keys and stays as it was; `check` names\n  it until it is deleted.\n- Team and local layers resolve against the repository root of the working\n  directory. Inside a second worktree, run from that worktree.\n","## Purpose\n\n`\u002Fmulti-agent:route` resolves the role map through four layers: the bundled\ndefaults, `~\u002F.claude\u002Fmulti-agent.yaml`, the team layer and\n`.claude\u002Fmulti-agent.local.yaml`. This skill shows what those layers resolve to\nand writes one of them. All three consumer layers absent is a valid state: the\nbundled defaults apply. Keys, values, layer paths and the fan-out guard are\ndefined in\n[`${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fconfig.md`](${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fconfig.md).\n\nNo argument means `check`. It installs nothing; the resolver needs only Bash,\nawk and git.\n\n## `check` (read-only)\n\n```bash\n${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fsetup.sh check session=\u003Calias>\n```\n\nPass `session=\u003Calias>` with the family in your own model ID (`opus`, `sonnet`,\n`haiku`, `fable`); omit it when you cannot tell, and the map is resolved as\nunder a frontier session. The JSON is the one `\u002Fmulti-agent:route all` prints.\nShow:\n\n1. one line per role: `single \u003Cmodel> @ \u003Ceffort>; fanout \u003Cmodel> @ \u003Ceffort>`,\n   with `inherit` written as `inherit: omit the model option`, and the layer\n   in `source` for each value;\n2. the `layers` rows (read, absent, skipped, or not applicable at a home or\n   non-repository root) and every entry of `notes` as written; each note (a\n   skipped layer, a rejected value, an ignored key) is a finding to report;\n3. the personal-override row: PASS when `.claude\u002Fmulti-agent.local.yaml` is gitignored,\n   else WARN with the recommended line `.claude\u002F**\u002F*.local.*`. Recommend the\n   line; do not edit `.gitignore`;\n4. each `WARN team:` row: a retired team file (the config block in\n   `docs\u002Fconventions\u002Fmulti-agent.md`, or `.claude\u002Fmulti-agent.yaml`) that the\n   resolver no longer reads. Relay the row's next step as written.\n\nIt modifies nothing.\n\n## `apply`\n\n1. Run `check` and show the map. This is the before state.\n2. Settle the layer with the user, recommendation first:\n   - `local` (`.claude\u002Fmulti-agent.local.yaml`): this checkout only, for this\n     person. The default for a personal preference.\n   - `team`: `docs\u002Fconventions\u002Fmulti-agent.yaml` (under the convention home the\n     repository binds). Shared with everyone who clones the repository.\n   - `user` (`~\u002F.claude\u002Fmulti-agent.yaml`): every repository on this machine.\n\n   `team` and `local` are refused at a home or non-repository root.\n3. Settle the keys. Ask only for what the user wants changed; each value comes\n   from the table in `config.md`. Pass every key to set as `\u003Ckey>=\u003Cvalue>`, and\n   `\u003Ckey>=` to remove one from that layer. Existing keys in the layer are kept.\n4. Preview, writing nothing:\n\n   ```bash\n   ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fsetup.sh apply --layer \u003Clayer> \u003Ckey>=\u003Cvalue> ...\n   ```\n\n   It prints the target path and a diff. It exits 1 without writing when the\n   resolver would reject or ignore a key; relay the reason and return to\n   step 3.\n5. Show the diff and ask for an explicit yes. Write only on that yes:\n\n   ```bash\n   ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fsetup.sh apply --layer \u003Clayer> --write \u003Ckey>=\u003Cvalue> ...\n   ```\n\n   It prints the path written and the keys it read back from the file.\n6. Run `check` again and show the after map beside the before one, naming each\n   value that changed and the layer that now supplies it. The file is what the\n   next `\u002Fmulti-agent:route` run reads; nothing about the running session\n   changes. For `team`, offer `git add` and a commit and run each only when the\n   user accepts.\n\n### The fan-out guard\n\nWith `fanout.frontier_guard: true`, the bundled value, a stage that runs more\nthan one agent never runs them on a frontier model: under a Fable\nsession, or a session the caller did not name, each fan-out variant that would\ninherit or name a frontier model takes `fanout.model` (`opus`) instead. A\nsingle synthesis or judge agent keeps the role's own model. The basis is\nrecorded beside the key in\n[`${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fdefaults.yaml`](${CLAUDE_PLUGIN_ROOT}\u002Freference\u002Fdefaults.yaml).\n\n`fanout.frontier_guard=false` is an explicit opt-in to frontier fan-outs: every\nparallel worker then runs on the session model, so a frontier session runs\nevery agent of the stage on the frontier model (rates:\n[Pricing: model pricing](https:\u002F\u002Fplatform.claude.com\u002Fdocs\u002Fen\u002Fabout-claude\u002Fpricing#model-pricing); usage:\n[Manage costs: Track your costs](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fcosts#track-your-costs)).\nBefore writing it, say this and ask the user to confirm that specific key,\nseparately from the rest of the change. Recommend the narrowest layer that\ncovers what they mean: `local` for one checkout, `user` for one machine, `team`\nonly when the whole team has agreed.\n\n## What this skill does NOT do\n\n- Edit `.gitignore`, `CLAUDE.md` or `AGENTS.md`.\n- Write a model ID. Only aliases are accepted, so the map stays portable across\n  providers.\n- Change a named agent's model or effort. An agent such as\n  `implementation:implementer` or `implementation:scoped-implementer` owns its\n  tier through its own frontmatter and whatever its dispatcher passes on the\n  call; the role map governs generic `agent()` and Agent dispatches only.\n- Recheck a default against upstream. That is `\u002Fmulti-agent:audit-defaults`.\n\n## Next\n\n\u002Fmulti-agent:route all\nPrints the map the next workflow reads from `args.roles`.\n\n## Gotchas\n\n- A layer file is rewritten whole, so its comments are not kept; the preview\n  says so when the file has any.\n- An existing layer that does not parse stops `apply` with the line and the\n  reason. Fix or remove the file first; setup never overwrites content it could\n  not read.\n- The first `team` write creates the YAML. A retired team file, which the\n  resolver no longer reads, seeds its keys and stays as it was; `check` names\n  it until it is deleted.\n- Team and local layers resolve against the repository root of the working\n  directory. Inside a second worktree, run from that worktree.\n",{"shell":24,"description":7,"allowed-tools":25,"argument-hint":27,"user-invocable":28,"disable-model-invocation":28},"bash",[26],"Bash(${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fsetup.sh:*)","[check|apply] [--layer user|team|local] [\u003Ckey>=\u003Cvalue> ...] [session=\u003Calias>]",true,"main","d0e68c3f36b92a1d6381f0ba0060d7a0b8b886c5","plugins\u002Fmulti-agent\u002Fskills\u002Fsetup",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":39,"prompt":49,"zipAvailable":28},[40,43,46],{"tool":41,"command":42},"npx","npx skills add melodic-software\u002Fclaude-code-plugins --skill setup",{"tool":44,"command":45},"bunx","bunx skills add melodic-software\u002Fclaude-code-plugins --skill setup",{"tool":47,"command":48},"pnpm","pnpm dlx skills add melodic-software\u002Fclaude-code-plugins --skill setup","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fmulti-agent\u002Fskills\u002Fsetup\u002FSKILL.md",[51,57],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"scripts\u002Fsetup.sh","SCRIPT","脚本",10864,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fmulti-agent\u002Fskills\u002Fsetup\u002Fscripts\u002Fsetup.sh",{"path":58,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":59,"sourceHtmlUrl":60},"scripts\u002Fsetup.test.sh",12474,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fmulti-agent\u002Fskills\u002Fsetup\u002Fscripts\u002Fsetup.test.sh",[62,69,76,83,88,95],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7DYRZ5YD44AMYH26YR25GZ8","route","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":84,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"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":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"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":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"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",[],[]]