[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CS2BSDP3M9A1SQ4J0A0DEE":3,"skill-same:01M7CS2BSDP3M9A1SQ4J0A0DEE":48},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7CS2BSDP3M9A1SQ4J0A0DEE","context-budget",null,"Audits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations.","Henrique1601\u002FSkiilsToIAs","Henrique1601","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F92006691?v=4","01M7CRXVT0GVXVK80JT1GR687S","Henrique Bezerra Dos Santos","01M7CRXVTN5Y8TMWJ1MDSKCQ1T",0,"MIT","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fcontext-budget\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: context-budget\ndescription: Audits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations.\nmetadata:\n  origin: ECC\n---\n\n# Context Budget\n\nAnalyze token overhead across every loaded component in a Claude Code session and surface actionable optimizations to reclaim context space.\n\n## When to Use\n\n- Session performance feels sluggish or output quality is degrading\n- You've recently added many skills, agents, or MCP servers\n- You want to know how much context headroom you actually have\n- Planning to add more components and need to know if there's room\n- Running `\u002Fcontext-budget` command (this skill backs it)\n\n## How It Works\n\n### Phase 1: Inventory\n\nScan all component directories and estimate token consumption:\n\n**Agents** (`agents\u002F*.md`)\n- Count lines and tokens per file (words × 1.3)\n- Extract `description` frontmatter length\n- Flag: files >200 lines (heavy), description >30 words (bloated frontmatter)\n\n**Skills** (`skills\u002F*\u002FSKILL.md`)\n- Count tokens per SKILL.md\n- Flag: files >400 lines\n- Check for duplicate copies in `.agents\u002Fskills\u002F` — skip identical copies to avoid double-counting\n\n**Rules** (`rules\u002F**\u002F*.md`)\n- Count tokens per file\n- Flag: files >100 lines\n- Detect content overlap between rule files in the same language module\n\n**MCP Servers** (`.mcp.json` or active MCP config)\n- Count configured servers and total tool count\n- Estimate schema overhead at ~500 tokens per tool\n- Flag: servers with >20 tools, servers that wrap simple CLI commands (`gh`, `git`, `npm`, `supabase`, `vercel`)\n\n**CLAUDE.md** (project + user-level)\n- Count tokens per file in the CLAUDE.md chain\n- Flag: combined total >300 lines\n\n### Phase 2: Classify\n\nSort every component into a bucket:\n\n| Bucket | Criteria | Action |\n|--------|----------|--------|\n| **Always needed** | Referenced in CLAUDE.md, backs an active command, or matches current project type | Keep |\n| **Sometimes needed** | Domain-specific (e.g. language patterns), not referenced in CLAUDE.md | Consider on-demand activation |\n| **Rarely needed** | No command reference, overlapping content, or no obvious project match | Remove or lazy-load |\n\n### Phase 3: Detect Issues\n\nIdentify the following problem patterns:\n\n- **Bloated agent descriptions** — description >30 words in frontmatter loads into every Task tool invocation\n- **Heavy agents** — files >200 lines inflate Task tool context on every spawn\n- **Redundant components** — skills that duplicate agent logic, rules that duplicate CLAUDE.md\n- **MCP over-subscription** — >10 servers, or servers wrapping CLI tools available for free\n- **CLAUDE.md bloat** — verbose explanations, outdated sections, instructions that should be rules\n\n### Phase 4: Report\n\nProduce the context budget report:\n\n```\nContext Budget Report\n═══════════════════════════════════════\n\nTotal estimated overhead: ~XX,XXX tokens\nContext model: Claude Sonnet (200K window)\nEffective available context: ~XXX,XXX tokens (XX%)\n\nComponent Breakdown:\n┌─────────────────┬────────┬───────────┐\n│ Component       │ Count  │ Tokens    │\n├─────────────────┼────────┼───────────┤\n│ Agents          │ N      │ ~X,XXX    │\n│ Skills          │ N      │ ~X,XXX    │\n│ Rules           │ N      │ ~X,XXX    │\n│ MCP tools       │ N      │ ~XX,XXX   │\n│ CLAUDE.md       │ N      │ ~X,XXX    │\n└─────────────────┴────────┴───────────┘\n\nWARNING: Issues Found (N):\n[ranked by token savings]\n\nTop 3 Optimizations:\n1. [action] → save ~X,XXX tokens\n2. [action] → save ~X,XXX tokens\n3. [action] → save ~X,XXX tokens\n\nPotential savings: ~XX,XXX tokens (XX% of current overhead)\n```\n\nIn verbose mode, additionally output per-file token counts, line-by-line breakdown of the heaviest files, specific redundant lines between overlapping components, and MCP tool list with per-tool schema size estimates.\n\n## Examples\n\n**Basic audit**\n```\nUser: \u002Fcontext-budget\nSkill: Scans setup → 16 agents (12,400 tokens), 28 skills (6,200), 87 MCP tools (43,500), 2 CLAUDE.md (1,200)\n       Flags: 3 heavy agents, 14 MCP servers (3 CLI-replaceable)\n       Top saving: remove 3 MCP servers → -27,500 tokens (47% overhead reduction)\n```\n\n**Verbose mode**\n```\nUser: \u002Fcontext-budget --verbose\nSkill: Full report + per-file breakdown showing planner.md (213 lines, 1,840 tokens),\n       MCP tool list with per-tool sizes, duplicated rule lines side by side\n```\n\n**Pre-expansion check**\n```\nUser: I want to add 5 more MCP servers, do I have room?\nSkill: Current overhead 33% → adding 5 servers (~50 tools) would add ~25,000 tokens → pushes to 45% overhead\n       Recommendation: remove 2 CLI-replaceable servers first to stay under 40%\n```\n\n## Best Practices\n\n- **Token estimation**: use `words × 1.3` for prose, `chars \u002F 4` for code-heavy files\n- **MCP is the biggest lever**: each tool schema costs ~500 tokens; a 30-tool server costs more than all your skills combined\n- **Agent descriptions are loaded always**: even if the agent is never invoked, its description field is present in every Task tool context\n- **Verbose mode for debugging**: use when you need to pinpoint the exact files driving overhead, not for regular audits\n- **Audit after changes**: run after adding any agent, skill, or MCP server to catch creep early\n","# Context Budget\n\nAnalyze token overhead across every loaded component in a Claude Code session and surface actionable optimizations to reclaim context space.\n\n## When to Use\n\n- Session performance feels sluggish or output quality is degrading\n- You've recently added many skills, agents, or MCP servers\n- You want to know how much context headroom you actually have\n- Planning to add more components and need to know if there's room\n- Running `\u002Fcontext-budget` command (this skill backs it)\n\n## How It Works\n\n### Phase 1: Inventory\n\nScan all component directories and estimate token consumption:\n\n**Agents** (`agents\u002F*.md`)\n- Count lines and tokens per file (words × 1.3)\n- Extract `description` frontmatter length\n- Flag: files >200 lines (heavy), description >30 words (bloated frontmatter)\n\n**Skills** (`skills\u002F*\u002FSKILL.md`)\n- Count tokens per SKILL.md\n- Flag: files >400 lines\n- Check for duplicate copies in `.agents\u002Fskills\u002F` — skip identical copies to avoid double-counting\n\n**Rules** (`rules\u002F**\u002F*.md`)\n- Count tokens per file\n- Flag: files >100 lines\n- Detect content overlap between rule files in the same language module\n\n**MCP Servers** (`.mcp.json` or active MCP config)\n- Count configured servers and total tool count\n- Estimate schema overhead at ~500 tokens per tool\n- Flag: servers with >20 tools, servers that wrap simple CLI commands (`gh`, `git`, `npm`, `supabase`, `vercel`)\n\n**CLAUDE.md** (project + user-level)\n- Count tokens per file in the CLAUDE.md chain\n- Flag: combined total >300 lines\n\n### Phase 2: Classify\n\nSort every component into a bucket:\n\n| Bucket | Criteria | Action |\n|--------|----------|--------|\n| **Always needed** | Referenced in CLAUDE.md, backs an active command, or matches current project type | Keep |\n| **Sometimes needed** | Domain-specific (e.g. language patterns), not referenced in CLAUDE.md | Consider on-demand activation |\n| **Rarely needed** | No command reference, overlapping content, or no obvious project match | Remove or lazy-load |\n\n### Phase 3: Detect Issues\n\nIdentify the following problem patterns:\n\n- **Bloated agent descriptions** — description >30 words in frontmatter loads into every Task tool invocation\n- **Heavy agents** — files >200 lines inflate Task tool context on every spawn\n- **Redundant components** — skills that duplicate agent logic, rules that duplicate CLAUDE.md\n- **MCP over-subscription** — >10 servers, or servers wrapping CLI tools available for free\n- **CLAUDE.md bloat** — verbose explanations, outdated sections, instructions that should be rules\n\n### Phase 4: Report\n\nProduce the context budget report:\n\n```\nContext Budget Report\n═══════════════════════════════════════\n\nTotal estimated overhead: ~XX,XXX tokens\nContext model: Claude Sonnet (200K window)\nEffective available context: ~XXX,XXX tokens (XX%)\n\nComponent Breakdown:\n┌─────────────────┬────────┬───────────┐\n│ Component       │ Count  │ Tokens    │\n├─────────────────┼────────┼───────────┤\n│ Agents          │ N      │ ~X,XXX    │\n│ Skills          │ N      │ ~X,XXX    │\n│ Rules           │ N      │ ~X,XXX    │\n│ MCP tools       │ N      │ ~XX,XXX   │\n│ CLAUDE.md       │ N      │ ~X,XXX    │\n└─────────────────┴────────┴───────────┘\n\nWARNING: Issues Found (N):\n[ranked by token savings]\n\nTop 3 Optimizations:\n1. [action] → save ~X,XXX tokens\n2. [action] → save ~X,XXX tokens\n3. [action] → save ~X,XXX tokens\n\nPotential savings: ~XX,XXX tokens (XX% of current overhead)\n```\n\nIn verbose mode, additionally output per-file token counts, line-by-line breakdown of the heaviest files, specific redundant lines between overlapping components, and MCP tool list with per-tool schema size estimates.\n\n## Examples\n\n**Basic audit**\n```\nUser: \u002Fcontext-budget\nSkill: Scans setup → 16 agents (12,400 tokens), 28 skills (6,200), 87 MCP tools (43,500), 2 CLAUDE.md (1,200)\n       Flags: 3 heavy agents, 14 MCP servers (3 CLI-replaceable)\n       Top saving: remove 3 MCP servers → -27,500 tokens (47% overhead reduction)\n```\n\n**Verbose mode**\n```\nUser: \u002Fcontext-budget --verbose\nSkill: Full report + per-file breakdown showing planner.md (213 lines, 1,840 tokens),\n       MCP tool list with per-tool sizes, duplicated rule lines side by side\n```\n\n**Pre-expansion check**\n```\nUser: I want to add 5 more MCP servers, do I have room?\nSkill: Current overhead 33% → adding 5 servers (~50 tools) would add ~25,000 tokens → pushes to 45% overhead\n       Recommendation: remove 2 CLI-replaceable servers first to stay under 40%\n```\n\n## Best Practices\n\n- **Token estimation**: use `words × 1.3` for prose, `chars \u002F 4` for code-heavy files\n- **MCP is the biggest lever**: each tool schema costs ~500 tokens; a 30-tool server costs more than all your skills combined\n- **Agent descriptions are loaded always**: even if the agent is never invoked, its description field is present in every Task tool context\n- **Verbose mode for debugging**: use when you need to pinpoint the exact files driving overhead, not for regular audits\n- **Audit after changes**: run after adding any agent, skill, or MCP server to catch creep early\n",{"name":5,"metadata":24,"description":7},{"origin":25},"ECC","main","a73152352c0612252131e5cf84e91312a6cf17dc","ai-agents\u002Fcontext-budget","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs","https:\u002F\u002Fgithub.com\u002FHenrique1601","https:\u002F\u002Fbezerraportifolio.netlify.app\u002F","Full Stack Developer | React, Next.js, TypeScript, Node.js & IA | Construindo produtos digitais e soluções SaaS","2026-11-15 02:56:04",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add Henrique1601\u002FSkiilsToIAs --skill context-budget",{"tool":40,"command":41},"bunx","bunx skills add Henrique1601\u002FSkiilsToIAs --skill context-budget",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Henrique1601\u002FSkiilsToIAs --skill context-budget","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fcontext-budget\u002FSKILL.md",true,[],[49,56,63,71,78,85],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7E2ANBW9V6AVX5JXNCEAWF8","rag-architect-agent","Agente Arquiteto de RAG, Embeddings & Busca Vetorial. Especialista em design e implementação de pipelines de Retrieval-Augmented Generation de alta fidelidade: chunking semântico, modelagem pgvector no PostgreSQL (Neon\u002FSupabase), busca híbrida (cosseno + BM25), reranking, validação via TypeSafe AI e filosofia Ponytail (anti-overengineering).","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fcustom-agents\u002Frag-architect-agent\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7E29KKF8R02ZRGYE2MJM67G","rag-architecture-patterns","Padrões arquiteturais e implementação de pipelines RAG (Retrieval-Augmented Generation) de alta fidelidade para qualquer projeto ou sistema. Cobre chunking semântico, embeddings, busca híbrida (pgvector + BM25), reranking, validação via TypeSafe AI e filosofia Ponytail (anti-overengineering).","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Frag-architecture-patterns\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7CWRA8E3BJ7CPY8N8EG28J1","skill-repair","Use this to fix and re-install agent skills that have failed installation.\nThis skill provides the necessary context and permissions to surgically update\nthe `manifest.json` after a fix has been applied.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fskill-repair\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7CWR66FZP8FA47WVZ4Z2EXC","security-scan","Scan your Claude Code configuration (.claude\u002F directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fsecurity-scan\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7CWR0QPY58QPTR1P759TFNG","security-review","Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment\u002Fsensitive features. Provides comprehensive security checklist and patterns.","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fsecurity-review\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7CWQXCE40XWT4FZ3VWZFGDP","security-bounty-hunter","Hunt for exploitable, bounty-worthy security issues in repositories. Focuses on remotely reachable vulnerabilities that qualify for real reports instead of noisy local-only findings.","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fsecurity-bounty-hunter\u002FSKILL.md",[],[]]