[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7A4TE95AF2YE2PXW8DNXP98":3,"skill-same:01M7A4TE95AF2YE2PXW8DNXP98":46},{"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":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7A4TE95AF2YE2PXW8DNXP98","codeburn-optimize",null,"Use when the user asks about CodeBurn, LLM spend, token usage, rate-limit pressure, model efficiency, Claude vs Codex usage, subscription value, or where coding-agent usage can be optimized.","jadenmaciel\u002Fjstack","jadenmaciel","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F195352788?v=4","01M7A4SG75RGMAMBX11WXWB6CP","Jaden L'vivski Maciel-Shapiro","01M7A4SG7T1STWS6BTBTN9EFTG",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjadenmaciel\u002Fjstack\u002Fblob\u002Fmain\u002Fskills\u002Fmisc\u002Fcodeburn-optimize\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: codeburn-optimize\ndescription: Use when the user asks about CodeBurn, LLM spend, token usage, rate-limit pressure, model efficiency, Claude vs Codex usage, subscription value, or where coding-agent usage can be optimized.\n---\n\n# CodeBurn Optimize\n\nUse `codeburn` to turn coding-agent logs into spend, usage, efficiency, and optimization advice.\n\n## Steps\n\n1. Confirm the CLI exists.\n   ```bash\n   command -v codeburn\n   codeburn --version\n   ```\n   Done when the executable path and version are known. If missing, say CodeBurn is unavailable and stop.\n\n2. Pick the smallest useful window.\n   - Today: `codeburn today --timezone America\u002FDenver`\n   - Yesterday: `codeburn models --from YYYY-MM-DD --to YYYY-MM-DD --provider all --format json`\n   - This month: `codeburn month --timezone America\u002FDenver`\n   - Last 30 days: `codeburn models --period 30days --provider all`\n   - All visible logs: `codeburn models --period all --provider all`\n\n   Done when the command matches the user's timeframe. Use exact dates for \"today\" and \"yesterday\".\n\n3. For spend and model mix, prefer non-interactive model tables.\n   ```bash\n   codeburn models --period 30days --provider all\n   codeburn models --period all --provider all --format json\n   ```\n   Done when totals are separated by provider and model.\n\n4. For waste, run optimize once per relevant provider.\n   ```bash\n   codeburn optimize --provider all\n   codeburn optimize --provider claude\n   codeburn optimize --provider codex\n   ```\n   Done when savings, waste type, and exact fix are identified. Skip provider-specific runs if the all-provider result already answers the question.\n\n5. For Claude vs Codex decisions, compare efficiency, not only dollars.\n   Report:\n   - API-equivalent cost\n   - calls and sessions\n   - one-shot rate\n   - retries\u002Fedit when visible\n   - top projects and activities\n   - cache hit rate\n\n   Done when the recommendation says which plan\u002Fmodel should be the workhorse and why.\n\n6. Keep the money caveat explicit.\n   CodeBurn cost is API-equivalent token value unless the data proves actual billing. Subscription-covered usage is not the same as card spend.\n   Done when the answer separates \"API-equivalent\" from \"cash paid\".\n\n## Output\n\nLead with the answer, then the evidence.\n\nUse this shape:\n\n```text\nTotal: $X API-equivalent.\n\nProvider split:\n- Claude: $X\n- Codex: $X\n\nOptimization read:\n- Biggest waste: ...\n- Best fix: ...\n- Subscription read: ...\n\nVerified with: `command`\n```\n\n## Guardrails\n\n- Do not use `codeburn report` unless the user asks for the interactive dashboard.\n- Do not paste full JSON. Aggregate with `jq`, tables, or a short summary.\n- Do not treat API-equivalent value as actual subscription billing.\n- Do not recommend upgrading a plan from raw spend alone. Use one-shot rate and retry pressure too.\n","# CodeBurn Optimize\n\nUse `codeburn` to turn coding-agent logs into spend, usage, efficiency, and optimization advice.\n\n## Steps\n\n1. Confirm the CLI exists.\n   ```bash\n   command -v codeburn\n   codeburn --version\n   ```\n   Done when the executable path and version are known. If missing, say CodeBurn is unavailable and stop.\n\n2. Pick the smallest useful window.\n   - Today: `codeburn today --timezone America\u002FDenver`\n   - Yesterday: `codeburn models --from YYYY-MM-DD --to YYYY-MM-DD --provider all --format json`\n   - This month: `codeburn month --timezone America\u002FDenver`\n   - Last 30 days: `codeburn models --period 30days --provider all`\n   - All visible logs: `codeburn models --period all --provider all`\n\n   Done when the command matches the user's timeframe. Use exact dates for \"today\" and \"yesterday\".\n\n3. For spend and model mix, prefer non-interactive model tables.\n   ```bash\n   codeburn models --period 30days --provider all\n   codeburn models --period all --provider all --format json\n   ```\n   Done when totals are separated by provider and model.\n\n4. For waste, run optimize once per relevant provider.\n   ```bash\n   codeburn optimize --provider all\n   codeburn optimize --provider claude\n   codeburn optimize --provider codex\n   ```\n   Done when savings, waste type, and exact fix are identified. Skip provider-specific runs if the all-provider result already answers the question.\n\n5. For Claude vs Codex decisions, compare efficiency, not only dollars.\n   Report:\n   - API-equivalent cost\n   - calls and sessions\n   - one-shot rate\n   - retries\u002Fedit when visible\n   - top projects and activities\n   - cache hit rate\n\n   Done when the recommendation says which plan\u002Fmodel should be the workhorse and why.\n\n6. Keep the money caveat explicit.\n   CodeBurn cost is API-equivalent token value unless the data proves actual billing. Subscription-covered usage is not the same as card spend.\n   Done when the answer separates \"API-equivalent\" from \"cash paid\".\n\n## Output\n\nLead with the answer, then the evidence.\n\nUse this shape:\n\n```text\nTotal: $X API-equivalent.\n\nProvider split:\n- Claude: $X\n- Codex: $X\n\nOptimization read:\n- Biggest waste: ...\n- Best fix: ...\n- Subscription read: ...\n\nVerified with: `command`\n```\n\n## Guardrails\n\n- Do not use `codeburn report` unless the user asks for the interactive dashboard.\n- Do not paste full JSON. Aggregate with `jq`, tables, or a short summary.\n- Do not treat API-equivalent value as actual subscription billing.\n- Do not recommend upgrading a plan from raw spend alone. Use one-shot rate and retry pressure too.\n",{"name":5,"description":7},"main","2409dbb520b0891ed4f668f01c3a140dcf9d77c5","skills\u002Fmisc\u002Fcodeburn-optimize","https:\u002F\u002Fgithub.com\u002Fjadenmaciel\u002Fjstack","https:\u002F\u002Fgithub.com\u002Fjadenmaciel","https:\u002F\u002Fjadenmacielshapiro.dev","Applied AI engineer. Payment systems and AI agents in Rust, Go, and Python.","2026-11-07 06:44:09",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add jadenmaciel\u002Fjstack --skill codeburn-optimize",{"tool":38,"command":39},"bunx","bunx skills add jadenmaciel\u002Fjstack --skill codeburn-optimize",{"tool":41,"command":42},"pnpm","pnpm dlx skills add jadenmaciel\u002Fjstack --skill codeburn-optimize","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjadenmaciel\u002Fjstack\u002Fblob\u002Fmain\u002Fskills\u002Fmisc\u002Fcodeburn-optimize\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7A4W9JDKD7AAY8G5PAP0XQ2","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fjadenmaciel\u002Fjstack\u002Fblob\u002Fmain\u002Fskills\u002Fstyle\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7A4W84DPXKDH0STE7EESQ68","wait-what","Stop. That last message did not land — re-pitch it.","https:\u002F\u002Fgithub.com\u002Fjadenmaciel\u002Fjstack\u002Fblob\u002Fmain\u002Fskills\u002Fstyle\u002Fwait-what\u002FSKILL.md",[],[],{"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},"01M7A4W65736YGRF5N529B4FEF","ponytail","Lazy senior dev mode for any coding task (write, refactor, fix, review): YAGNI, stdlib first, no unrequested abstractions. Not for non-coding requests.","https:\u002F\u002Fgithub.com\u002Fjadenmaciel\u002Fjstack\u002Fblob\u002Fmain\u002Fskills\u002Fstyle\u002Fponytail\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},"01M7A4W1R831XHNVD9B6XDRN7F","i-have-adhd","Shape output for a reader with ADHD. Use this skill whenever responding to ANY user message including coding tasks, debugging, explanations, planning, and casual conversation. Output should lead with concrete next actions, number multi-step work, externalize state across turns, suppress tangents, give specific time estimates, and make wins visible. Trigger even on casual messages and even when the user did not explicitly ask for brevity.","https:\u002F\u002Fgithub.com\u002Fjadenmaciel\u002Fjstack\u002Fblob\u002Fmain\u002Fskills\u002Fstyle\u002Fi-have-adhd\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7A4W00D3RMTMMWHG3QQ3FZF","x-research","Use when the task needs live posts from X\u002FTwitter, or when deep-research needs its X pass.","https:\u002F\u002Fgithub.com\u002Fjadenmaciel\u002Fjstack\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Fx-research\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7A4VWZ6Y9XWXDG3TQB15ABC","slop","Answer an empirical question, or explore\u002Ftest something about real code, by building and running throwaway code in ~\u002Fslop\u002F — harnesses, lint rules, load tests, ports, API probes. Never merged. Use whenever disposable code would answer, explore, or test something faster or more reliably than reasoning about it.","https:\u002F\u002Fgithub.com\u002Fjadenmaciel\u002Fjstack\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Fslop\u002FSKILL.md",[],[]]