[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F1Z2WPS01XH75684FSEKQW":3,"skill-same:01M7F1Z2WPS01XH75684FSEKQW":52},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7F1Z2WPS01XH75684FSEKQW","model-savings",null,"Estimate the dollars saved by routing eligible Claude Code work to a cheaper model family, using the Agent Monitor pricing engine. Re-prices each model's token mix at the target family's rates and quantifies the delta. Uses \u002Fapi\u002Fpricing (rates), \u002Fapi\u002Fpricing\u002Fcost (current per-model spend), \u002Fapi\u002Fsessions, and \u002Fapi\u002Fanalytics. Use when hunting for cost cuts or comparing model tiers.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fmodel-savings\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: model-savings\ndescription: >\n  Estimate the dollars saved by routing eligible Claude Code work to a cheaper\n  model family, using the Agent Monitor pricing engine. Re-prices each model's\n  token mix at the target family's rates and quantifies the delta. Uses\n  \u002Fapi\u002Fpricing (rates), \u002Fapi\u002Fpricing\u002Fcost (current per-model spend), \u002Fapi\u002Fsessions,\n  and \u002Fapi\u002Fanalytics. Use when hunting for cost cuts or comparing model tiers.\n---\n\n# Model Savings\n\nQuantify how much spend you would recover by moving eligible work to a cheaper model.\n\n## Input\n\nThe user provides: **$ARGUMENTS**\n\nThis is the routing question — e.g. `\"Opus → Sonnet\"`, `\"move simple work to Haiku\"`,\nor empty (analyze every premium model against the next tier down). If no target family\nis named, default to proposing the next-cheaper tier per model and say so.\n\n## Data Sources\n\n| Endpoint | Returns |\n|----------|---------|\n| `GET \u002Fapi\u002Fpricing` | `{ pricing: [{ model_pattern, display_name, input_per_mtok, output_per_mtok, cache_read_per_mtok, cache_write_per_mtok }] }` — the rate card for every family |\n| `GET \u002Fapi\u002Fpricing\u002Fcost` | `{ total_cost, breakdown: [{ model, input_tokens, output_tokens, cache_read_tokens, cache_write_tokens, cost, matched_rule }] }` — current spend and the exact token mix per model |\n| `GET \u002Fapi\u002Fsessions?limit=200` | Sessions with `model`, inline `cost`, and `metadata` (turn_count, thinking_blocks) — used to judge which work is *eligible* to downshift |\n| `GET \u002Fapi\u002Fanalytics` | `agent_types`, `tool_usage`, `total_subagents` — corroborate which task types are low-complexity and safe to route cheaper |\n\n## Savings method\n\nFor each candidate model in the cost `breakdown`, re-price its **exact token mix** at the target family's rates:\n\n```\ncost_at_target = (input_tokens      \u002F 1M) × target.input_per_mtok\n               + (output_tokens     \u002F 1M) × target.output_per_mtok\n               + (cache_read_tokens \u002F 1M) × target.cache_read_per_mtok\n               + (cache_write_tokens\u002F 1M) × target.cache_write_per_mtok\n\nsavings = current_model_cost − cost_at_target\n```\n\nPull `target.*_per_mtok` from `\u002Fapi\u002Fpricing` (longest `model_pattern` match wins). Default rates ($\u002FMtok in\u002Fout\u002FcacheRead\u002FcacheWrite): **Opus** $5\u002F$25\u002F$0.50\u002F$6.25, **Sonnet** $3\u002F$15\u002F$0.30\u002F$3.75, **Haiku** $1\u002F$5\u002F$0.10\u002F$1.25.\n\n### Eligibility — don't promise savings on work that needs the big model\n\nRe-pricing the full token mix is the *theoretical ceiling*. Scope it to **eligible** work:\n- Low-turn sessions (`metadata.turn_count` small) and simple subagent\u002Ftool work are safe to downshift.\n- Heavy-reasoning sessions (many thinking_blocks, high turn counts) likely need the premium model — exclude or discount them.\n- Report both the **full re-price** (ceiling) and an **eligible-only** estimate, and state the eligibility rule you applied.\n\n## Report Sections\n\n### 1. Current spend by model\nTable from `\u002Fapi\u002Fpricing\u002Fcost`: each model, its 4 token counts, and current cost. Note its share of `total_cost`.\n\n### 2. Re-priced at target family\nFor each candidate, show `cost_at_target` and `savings` (absolute $ and %). Make the target rate card explicit.\n\n### 3. Eligible-only estimate\nApply the eligibility rule and recompute savings over just the downshiftable token mix. Show how many sessions \u002F what share of tokens qualified.\n\n### 4. Recommended routing\nRank routing moves by eligible monthly savings (descending), top 5. For each: source → target, the token mix moved, estimated $ saved, and a confidence level (high\u002Fmedium\u002Flow) based on how clearly the work is low-complexity.\n\n### 5. Caveats\nCheaper models may need more turns or produce more output — note that realized savings can be lower than the static re-price, and that quality-sensitive work should stay on the premium tier.\n\n## Output\n\nMarkdown tables. Currency as USD to 4 decimal places; token counts with thousands separators; rates as $\u002FMtok. Always present both the ceiling (full re-price) and the eligible-only estimate so the number is honest.\n","# Model Savings\n\nQuantify how much spend you would recover by moving eligible work to a cheaper model.\n\n## Input\n\nThe user provides: **$ARGUMENTS**\n\nThis is the routing question — e.g. `\"Opus → Sonnet\"`, `\"move simple work to Haiku\"`,\nor empty (analyze every premium model against the next tier down). If no target family\nis named, default to proposing the next-cheaper tier per model and say so.\n\n## Data Sources\n\n| Endpoint | Returns |\n|----------|---------|\n| `GET \u002Fapi\u002Fpricing` | `{ pricing: [{ model_pattern, display_name, input_per_mtok, output_per_mtok, cache_read_per_mtok, cache_write_per_mtok }] }` — the rate card for every family |\n| `GET \u002Fapi\u002Fpricing\u002Fcost` | `{ total_cost, breakdown: [{ model, input_tokens, output_tokens, cache_read_tokens, cache_write_tokens, cost, matched_rule }] }` — current spend and the exact token mix per model |\n| `GET \u002Fapi\u002Fsessions?limit=200` | Sessions with `model`, inline `cost`, and `metadata` (turn_count, thinking_blocks) — used to judge which work is *eligible* to downshift |\n| `GET \u002Fapi\u002Fanalytics` | `agent_types`, `tool_usage`, `total_subagents` — corroborate which task types are low-complexity and safe to route cheaper |\n\n## Savings method\n\nFor each candidate model in the cost `breakdown`, re-price its **exact token mix** at the target family's rates:\n\n```\ncost_at_target = (input_tokens      \u002F 1M) × target.input_per_mtok\n               + (output_tokens     \u002F 1M) × target.output_per_mtok\n               + (cache_read_tokens \u002F 1M) × target.cache_read_per_mtok\n               + (cache_write_tokens\u002F 1M) × target.cache_write_per_mtok\n\nsavings = current_model_cost − cost_at_target\n```\n\nPull `target.*_per_mtok` from `\u002Fapi\u002Fpricing` (longest `model_pattern` match wins). Default rates ($\u002FMtok in\u002Fout\u002FcacheRead\u002FcacheWrite): **Opus** $5\u002F$25\u002F$0.50\u002F$6.25, **Sonnet** $3\u002F$15\u002F$0.30\u002F$3.75, **Haiku** $1\u002F$5\u002F$0.10\u002F$1.25.\n\n### Eligibility — don't promise savings on work that needs the big model\n\nRe-pricing the full token mix is the *theoretical ceiling*. Scope it to **eligible** work:\n- Low-turn sessions (`metadata.turn_count` small) and simple subagent\u002Ftool work are safe to downshift.\n- Heavy-reasoning sessions (many thinking_blocks, high turn counts) likely need the premium model — exclude or discount them.\n- Report both the **full re-price** (ceiling) and an **eligible-only** estimate, and state the eligibility rule you applied.\n\n## Report Sections\n\n### 1. Current spend by model\nTable from `\u002Fapi\u002Fpricing\u002Fcost`: each model, its 4 token counts, and current cost. Note its share of `total_cost`.\n\n### 2. Re-priced at target family\nFor each candidate, show `cost_at_target` and `savings` (absolute $ and %). Make the target rate card explicit.\n\n### 3. Eligible-only estimate\nApply the eligibility rule and recompute savings over just the downshiftable token mix. Show how many sessions \u002F what share of tokens qualified.\n\n### 4. Recommended routing\nRank routing moves by eligible monthly savings (descending), top 5. For each: source → target, the token mix moved, estimated $ saved, and a confidence level (high\u002Fmedium\u002Flow) based on how clearly the work is low-complexity.\n\n### 5. Caveats\nCheaper models may need more turns or produce more output — note that realized savings can be lower than the static re-price, and that quality-sensitive work should stay on the premium tier.\n\n## Output\n\nMarkdown tables. Currency as USD to 4 decimal places; token counts with thousands separators; rates as $\u002FMtok. Always present both the ceiling (full re-price) and the eligible-only estimate so the number is honest.\n",{"name":5,"description":7},"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fmodel-savings",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill model-savings",{"tool":38,"command":39},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill model-savings",{"tool":41,"command":42},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill model-savings","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fmodel-savings\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",266,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fmodel-savings\u002Fagents\u002Fopenai.yaml",[53,60,65,72,79,86],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":61,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"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},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\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},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]