[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78CGVWC91SFGMP0HXW2DXYY":3,"skill-same:01M78CGVWC91SFGMP0HXW2DXYY":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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M78CGVWC91SFGMP0HXW2DXYY","token-budget-governor",null,"Prevent token waste across GPT, Codex, Claude, DeepSeek and local\u002Ffree models by enforcing scoped prompts, compact context and narrow internal lenses contracts. Use when the user requests token budget governor or invokes token-budget-governor. Do NOT use to promote unverified claims or transient task status into durable memory.","paulosantanna\u002Fai-assistent-universal-coder","paulosantanna","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F16673722?v=4","01M78AQDTCV0KDCGW63S0GQG2Y","Paulo R Sant'Anna","01M78AQDTZ701ZFNQ2VAXEH81D",1,"CC-BY-4.0","https:\u002F\u002Fgithub.com\u002Fpaulosantanna\u002Fai-assistent-universal-coder\u002Fblob\u002Fmaster\u002F00_skills\u002F(learning)\u002Ftoken-budget-governor\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: token-budget-governor\ndescription: Prevent token waste across GPT, Codex, Claude, DeepSeek and local\u002Ffree models by enforcing scoped prompts, compact context and narrow internal lenses contracts. Use when the user requests token budget governor or invokes token-budget-governor. Do NOT use to promote unverified claims or transient task status into durable memory.\nlicense: CC-BY-4.0\nmetadata:\n  author: AEOS\n  version: 1.0.0\n  owner_agent: codenavi-agent\n---\n\n# Skill: token-budget-governor\n\nGovernance: CodENavi Full Workspace v2. Skill of `codenavi-agent`; inherit `AGENTS.md`.\nLifecycle: BRIEFING → RECON → PLAN → EXECUTE → VERIFY → DEBRIEF.\nSource roles\u002Fworkers are internal lenses. Never create agent identities or bypass runtime secret\u002Fpermission gates.\n\n## Mission\n\nPrevent token waste across GPT, Codex, Claude, DeepSeek and local\u002Ffree models by enforcing scoped prompts, compact context and narrow subagent contracts.\n\n## Allowed Actions\n\n- Estimate prompt and output token budgets.\n- Recommend context reduction.\n- Split budgets across subagents.\n- Block unbounded or unrequested work.\n- Generate token budget reports.\n\n## Forbidden Actions\n\n- Broadcast full context to all subagents.\n- Re-read whole repositories without evidence of need.\n- Expand scope without user approval.\n- Use long-context models when targeted reads are enough.\n- Continue after the requested task is satisfied.\n\n## Required Inputs\n\n- provider\n- prompt_scope\n- requested_output_tokens\n- task_priority\n- subagent_count\n\n## Output Schema\n\n```json\n{\n  \"status\": \"PASS|REVIEW|BLOCKED\",\n  \"estimated_tokens\": 0,\n  \"limit\": 0,\n  \"provider\": \"\",\n  \"subagent_budget\": 0,\n  \"recommendations\": [],\n  \"blocking_conditions\": []\n}\n```\n\n## Quality Gates\n\n- Prompt uses file refs instead of pasted files when possible.\n- Subagents receive only narrow task contracts.\n- Output schema is explicit.\n- Stop conditions are explicit.\n- Provider limits are respected.\n\n## Stop Conditions\n\n- Prompt exceeds provider budget.\n- Subagent scope is broad or duplicated.\n- Missing output schema.\n- Unrequested work detected.\n\nProvenance and source freshness: [provenance](references\u002Fprovenance.md).\n\nExample usage and failure handling: read [usage and verification](references\u002Fusage-and-verification.md) when selecting this skill or a required step fails.\n","# Skill: token-budget-governor\n\nGovernance: CodENavi Full Workspace v2. Skill of `codenavi-agent`; inherit `AGENTS.md`.\nLifecycle: BRIEFING → RECON → PLAN → EXECUTE → VERIFY → DEBRIEF.\nSource roles\u002Fworkers are internal lenses. Never create agent identities or bypass runtime secret\u002Fpermission gates.\n\n## Mission\n\nPrevent token waste across GPT, Codex, Claude, DeepSeek and local\u002Ffree models by enforcing scoped prompts, compact context and narrow subagent contracts.\n\n## Allowed Actions\n\n- Estimate prompt and output token budgets.\n- Recommend context reduction.\n- Split budgets across subagents.\n- Block unbounded or unrequested work.\n- Generate token budget reports.\n\n## Forbidden Actions\n\n- Broadcast full context to all subagents.\n- Re-read whole repositories without evidence of need.\n- Expand scope without user approval.\n- Use long-context models when targeted reads are enough.\n- Continue after the requested task is satisfied.\n\n## Required Inputs\n\n- provider\n- prompt_scope\n- requested_output_tokens\n- task_priority\n- subagent_count\n\n## Output Schema\n\n```json\n{\n  \"status\": \"PASS|REVIEW|BLOCKED\",\n  \"estimated_tokens\": 0,\n  \"limit\": 0,\n  \"provider\": \"\",\n  \"subagent_budget\": 0,\n  \"recommendations\": [],\n  \"blocking_conditions\": []\n}\n```\n\n## Quality Gates\n\n- Prompt uses file refs instead of pasted files when possible.\n- Subagents receive only narrow task contracts.\n- Output schema is explicit.\n- Stop conditions are explicit.\n- Provider limits are respected.\n\n## Stop Conditions\n\n- Prompt exceeds provider budget.\n- Subagent scope is broad or duplicated.\n- Missing output schema.\n- Unrequested work detected.\n\nProvenance and source freshness: [provenance](references\u002Fprovenance.md).\n\nExample usage and failure handling: read [usage and verification](references\u002Fusage-and-verification.md) when selecting this skill or a required step fails.\n",{"name":5,"license":15,"metadata":24,"description":7},{"author":25,"version":26,"owner_agent":27},"AEOS","1.0.0","codenavi-agent","master","8dfe7d11f607b33af4b491639236e387afbe05b2","00_skills\u002F(learning)\u002Ftoken-budget-governor",0,"https:\u002F\u002Fgithub.com\u002Fpaulosantanna\u002Fai-assistent-universal-coder","https:\u002F\u002Fgithub.com\u002Fpaulosantanna","Java Engineer Sênior \r\nPython developer\r\nAI Engineer","2026-11-14 00:01:10",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add paulosantanna\u002Fai-assistent-universal-coder --skill token-budget-governor",{"tool":42,"command":43},"bunx","bunx skills add paulosantanna\u002Fai-assistent-universal-coder --skill token-budget-governor",{"tool":45,"command":46},"pnpm","pnpm dlx skills add paulosantanna\u002Fai-assistent-universal-coder --skill token-budget-governor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpaulosantanna\u002Fai-assistent-universal-coder\u002Fblob\u002Fmaster\u002F00_skills\u002F(learning)\u002Ftoken-budget-governor\u002FSKILL.md",true,[50,56],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fprovenance.md","REFERENCE","参考文档",549,"https:\u002F\u002Fgithub.com\u002Fpaulosantanna\u002Fai-assistent-universal-coder\u002Fblob\u002Fmaster\u002F00_skills\u002F(learning)\u002Ftoken-budget-governor\u002Freferences\u002Fprovenance.md",{"path":57,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fusage-and-verification.md",1142,"https:\u002F\u002Fgithub.com\u002Fpaulosantanna\u002Fai-assistent-universal-coder\u002Fblob\u002Fmaster\u002F00_skills\u002F(learning)\u002Ftoken-budget-governor\u002Freferences\u002Fusage-and-verification.md",[61,69,76,83,90,97],{"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":65,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7BDKK40ZSWSV7X6KHRNJP29","workspace-brain","Operate the CodENavi workspace brain MCP and CLI — cloud DeepSeek RAG, disk corpus at WORKSPACE_BRAIN_ROOT, Jev URL curation, and event logging for Cursor\u002FCodex\u002FOpenCode\u002FClaude. Use when ingesting repo knowledge, asking the brain, mapping web seeds, or recording AI-driven file changes. Do NOT use for local Ollama RAG or storing API keys in git.","MIT","https:\u002F\u002Fgithub.com\u002Fpaulosantanna\u002Fai-assistent-universal-coder\u002Fblob\u002Fmaster\u002Fworkspace-brain\u002Fskills\u002Fworkspace-brain\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},"01M78DJYQ4H328EBYWDFCT2QXW","workbench-profile-resolver","Provide enterprise-grade capability for `workbench-profile-resolver` inside AEOS v1.1. Use when the user requests workbench profile resolver or invokes workbench-profile-resolver. Do NOT use for unrelated tools or unapproved remote writes.","https:\u002F\u002Fgithub.com\u002Fpaulosantanna\u002Fai-assistent-universal-coder\u002Fblob\u002Fmaster\u002Fskills\u002Fworkbench-profile-resolver\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},"01M78DJVQKMPGWEWY6QFVQ1DW3","wordpress-expert","Staff-level WordPress engineering super-skill for one-shot site mapping, clean-code AI-assisted project creation\u002Fmodification, the complete installed plugin universe, governed remote wp-admin operations, themes\u002Fblocks\u002Flayout, third-party integrations and production-safe changes. Use when the user requests wordpress expert or invokes wordpress-expert. Do NOT use for unrelated languages, domains or production deployment.","https:\u002F\u002Fgithub.com\u002Fpaulosantanna\u002Fai-assistent-universal-coder\u002Fblob\u002Fmaster\u002Fskills\u002Fwordpress-expert\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M78DJSDCV70SJ61NPHWDN6HX","whatsapp-simulator","Generate synthetic WhatsApp-style conversation fixtures for testing conversational systems, support flows and automation. Use when the user requests whatsapp simulator or invokes whatsapp-simulator. Do NOT use for unrelated tools or unapproved remote writes.","https:\u002F\u002Fgithub.com\u002Fpaulosantanna\u002Fai-assistent-universal-coder\u002Fblob\u002Fmaster\u002Fskills\u002Fwhatsapp-simulator\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M78DJPXK26JZCZ811HX9AKHT","web-quality-audit","Assimilated TLC\u002Fweb-quality multi-area audit. Review performance, accessibility, SEO and best practices in one pass. Triggers: audit my site, review web quality, check page quality, optimize my website across areas. Do not use for a single-area job (core-web-vitals, ai-seo, best-practices, perf-lighthouse).","https:\u002F\u002Fgithub.com\u002Fpaulosantanna\u002Fai-assistent-universal-coder\u002Fblob\u002Fmaster\u002Fskills\u002Fweb-quality-audit\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M78DJM1ZVZ98C79H4R4SVZQA","voiceai","Provide an evidence-backed voice interface for AEOS. Activating this skill is treated as explicit current-session consent for `voiceai` to record user audio or transcribe audio from user-authorized audio\u002Fvideo media within the declared scope. The skill can: Use when the user requests voiceai or invokes voiceai. Do NOT use for unrelated tools or unapproved remote writes.","https:\u002F\u002Fgithub.com\u002Fpaulosantanna\u002Fai-assistent-universal-coder\u002Fblob\u002Fmaster\u002Fskills\u002Fvoiceai\u002FSKILL.md",[],[]]