[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F96W8GWMDMRAZ29NX72ZEN":3,"skill-same:01M7F96W8GWMDMRAZ29NX72ZEN":49},{"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":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":31,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7F96W8GWMDMRAZ29NX72ZEN","context-budget",null,"Routes live context checks to the native Codex or Claude Code meter without scanning files, and performs a bounded static component audit only when explicitly requested. Use for context-budget requests about remaining capacity or installed context overhead.","siddu1004\u002FSFP","siddu1004","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F260113491?v=4","01M7F8W1SAJAR49097VRTE1TW5","Siddhardh Vanguri","01M7F8W1SYGY7JE15AHAECCT9R",5,"MIT","https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fagent-dev\u002Fskills\u002Fcontext-budget\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: context-budget\ndescription: Routes live context checks to the native Codex or Claude Code meter without scanning files, and performs a bounded static component audit only when explicitly requested. Use for context-budget requests about remaining capacity or installed context overhead.\nmetadata:\n  origin: ECC\n---\n\n# Context Budget\n\nUse the provider's native meter for live session usage. Keep the separate,\nestimated installation audit behind an explicit opt-in.\n\n## Default: Live Context\n\nTreat an invocation with no audit request as a live-context request. This\nincludes requests for the current window, remaining capacity, headroom, token\nusage, or a context breakdown.\n\nFor this default path:\n\n- Do not call or use tools.\n- Do not scan or read files.\n- Do not run shell commands, provider CLIs, debug logging, or MCP discovery.\n- Reply with only the native command and one short explanation.\n\nRoute by the active harness:\n\n| Harness | Native command | Guidance |\n| --- | --- | --- |\n| Codex CLI | `\u002Fstatus` | Shows current token usage and remaining context capacity. Use `\u002Fstatusline` and enable **Context stats** plus **Token counters** for a persistent footer meter. |\n| Codex app | `\u002Fstatus` | Shows current thread context usage and rate limits. |\n| Claude Code | `\u002Fcontext` | Shows the live context breakdown. Use `\u002Fcontext all` for expanded items. |\n| Other or unknown | None verified | State that ECC cannot read live provider state and ask which harness is active. |\n\nThese commands are documented in the [Codex command reference](https:\u002F\u002Fdevelopers.openai.com\u002Fcodex\u002Fcli\u002Fslash-commands) and [Claude Code command reference](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fcommands).\n\nA skill cannot invoke a TUI slash command on the user's behalf. Never replace\nthe native command with an estimated scan and never infer an audit request from\nphrases such as “context is heavy” or “how much is left.”\n\n## Explicit Static Audit\n\nRun an installation\u002Fconfiguration audit only when the user explicitly says\n`--audit`, “audit installed components,” or equivalent unambiguous wording.\n`--verbose` changes report detail; it does not opt into an audit by itself.\n\nIf the audit scope is ambiguous, ask for the harness and installation root\nbefore reading anything. Keep every audit bounded and read-only:\n\n1. Inspect only the named plugin\u002Finstall root and the named harness's known\n   configuration files.\n2. Never recursively enumerate the workspace root, home directory, provider\n   cache, transcripts, debug logs, or unrelated worktrees.\n3. Never launch a provider CLI, MCP server, or debug session to count tools.\n4. Cap inventory output at 50 entries per component class. Summarize the rest.\n5. Do not write temporary logs or copy configuration content into the report.\n\nAudit only the component metadata relevant to eager discovery:\n\n- agent and skill descriptions;\n- command descriptions when the harness discovers them eagerly;\n- always-loaded instruction files in the explicitly named scope;\n- configured MCP tool schemas when an existing bounded manifest exposes them.\n\nFull skill, agent, command, and rule bodies are generally on-demand content.\nReport their disk size separately from estimated eager overhead instead of\nadding every body to the session baseline.\n\n## Audit Output\n\nReturn a compact report containing:\n\n- harness and exact paths inspected;\n- estimated eager\u002Fdiscovery overhead by component class;\n- installed counts and the heaviest metadata entries;\n- assumptions, unavailable measurements, and up to three optimizations.\n\nEvery calculated token number is an estimate of static configuration overhead,\nnot live session context. Do not claim that an estimate is provider-reported,\ncurrent, exact, or evidence of realized savings. Direct the user back to the\nnative live-context command for current usage.\n\n## Optional Selected-Record Diagnostic\n\nInspect a persisted record only when the user explicitly selects that file for this diagnostic. This is separate from the default live-context request and the installation audit.\n\nFor a local file diagnostic, explicitly select a stable, regular JSONL file or a snapshot you\nintend to inspect. Replace the example path below; this does not find or reconnect a session.\nThe snippet prints aggregate byte counts only. It reads one line at a time, so memory use depends\non the largest record; avoid very large records and actively growing files.\n\n```sh\npython3 - \"\u002Fpath\u002Fto\u002Fselected-session.jsonl\" \u003C\u003C'EOF'\nimport json\nimport sys\n\ntotal = attachment = other = unclassified = 0\ntry:\n    with open(sys.argv[1], \"rb\") as source:\n        for raw in source:\n            size = len(raw)\n            total += size\n            try:\n                record = json.loads(raw.decode(\"utf-8\"))\n            except (UnicodeDecodeError, json.JSONDecodeError):\n                unclassified += size\n                continue\n            record_type = record.get(\"type\") if isinstance(record, dict) else None\n            if not isinstance(record_type, str):\n                unclassified += size\n            elif record_type == \"attachment\":\n                attachment += size\n            else:\n                other += size\nexcept OSError:\n    print(\"Cannot read selected JSONL file.\", file=sys.stderr)\n    raise SystemExit(1)\n\npct = attachment * 100.0 \u002F total if total else 0.0\nprint(f\"persisted {total}B | attachment records {attachment}B ({pct:.1f}%) | \"\n      f\"other records {other}B | unclassified {unclassified}B\")\nEOF\n```\n\nThe three categories add up to the original file bytes, including line endings and blank lines.\n`attachment` is an exact record-type filter, not a guarantee about a harness's current internal\nschema. Other records have a different string `type`; malformed JSON, invalid UTF-8, nonobject\nvalues, missing or non-string types, and blank lines are unclassified. Neither category means\n\"conversation,\" and the percentage is only a share of persisted bytes.\n\nThese counts do not establish active context, remaining room, token usage, billing, or what a\nreconnect loads. For current harness-reported context and usage, use the version-appropriate\n[`\u002Fcontext` and `\u002Fusage` commands (`\u002Fcost` is an alias)](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fcommands).\n","# Context Budget\n\nUse the provider's native meter for live session usage. Keep the separate,\nestimated installation audit behind an explicit opt-in.\n\n## Default: Live Context\n\nTreat an invocation with no audit request as a live-context request. This\nincludes requests for the current window, remaining capacity, headroom, token\nusage, or a context breakdown.\n\nFor this default path:\n\n- Do not call or use tools.\n- Do not scan or read files.\n- Do not run shell commands, provider CLIs, debug logging, or MCP discovery.\n- Reply with only the native command and one short explanation.\n\nRoute by the active harness:\n\n| Harness | Native command | Guidance |\n| --- | --- | --- |\n| Codex CLI | `\u002Fstatus` | Shows current token usage and remaining context capacity. Use `\u002Fstatusline` and enable **Context stats** plus **Token counters** for a persistent footer meter. |\n| Codex app | `\u002Fstatus` | Shows current thread context usage and rate limits. |\n| Claude Code | `\u002Fcontext` | Shows the live context breakdown. Use `\u002Fcontext all` for expanded items. |\n| Other or unknown | None verified | State that ECC cannot read live provider state and ask which harness is active. |\n\nThese commands are documented in the [Codex command reference](https:\u002F\u002Fdevelopers.openai.com\u002Fcodex\u002Fcli\u002Fslash-commands) and [Claude Code command reference](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fcommands).\n\nA skill cannot invoke a TUI slash command on the user's behalf. Never replace\nthe native command with an estimated scan and never infer an audit request from\nphrases such as “context is heavy” or “how much is left.”\n\n## Explicit Static Audit\n\nRun an installation\u002Fconfiguration audit only when the user explicitly says\n`--audit`, “audit installed components,” or equivalent unambiguous wording.\n`--verbose` changes report detail; it does not opt into an audit by itself.\n\nIf the audit scope is ambiguous, ask for the harness and installation root\nbefore reading anything. Keep every audit bounded and read-only:\n\n1. Inspect only the named plugin\u002Finstall root and the named harness's known\n   configuration files.\n2. Never recursively enumerate the workspace root, home directory, provider\n   cache, transcripts, debug logs, or unrelated worktrees.\n3. Never launch a provider CLI, MCP server, or debug session to count tools.\n4. Cap inventory output at 50 entries per component class. Summarize the rest.\n5. Do not write temporary logs or copy configuration content into the report.\n\nAudit only the component metadata relevant to eager discovery:\n\n- agent and skill descriptions;\n- command descriptions when the harness discovers them eagerly;\n- always-loaded instruction files in the explicitly named scope;\n- configured MCP tool schemas when an existing bounded manifest exposes them.\n\nFull skill, agent, command, and rule bodies are generally on-demand content.\nReport their disk size separately from estimated eager overhead instead of\nadding every body to the session baseline.\n\n## Audit Output\n\nReturn a compact report containing:\n\n- harness and exact paths inspected;\n- estimated eager\u002Fdiscovery overhead by component class;\n- installed counts and the heaviest metadata entries;\n- assumptions, unavailable measurements, and up to three optimizations.\n\nEvery calculated token number is an estimate of static configuration overhead,\nnot live session context. Do not claim that an estimate is provider-reported,\ncurrent, exact, or evidence of realized savings. Direct the user back to the\nnative live-context command for current usage.\n\n## Optional Selected-Record Diagnostic\n\nInspect a persisted record only when the user explicitly selects that file for this diagnostic. This is separate from the default live-context request and the installation audit.\n\nFor a local file diagnostic, explicitly select a stable, regular JSONL file or a snapshot you\nintend to inspect. Replace the example path below; this does not find or reconnect a session.\nThe snippet prints aggregate byte counts only. It reads one line at a time, so memory use depends\non the largest record; avoid very large records and actively growing files.\n\n```sh\npython3 - \"\u002Fpath\u002Fto\u002Fselected-session.jsonl\" \u003C\u003C'EOF'\nimport json\nimport sys\n\ntotal = attachment = other = unclassified = 0\ntry:\n    with open(sys.argv[1], \"rb\") as source:\n        for raw in source:\n            size = len(raw)\n            total += size\n            try:\n                record = json.loads(raw.decode(\"utf-8\"))\n            except (UnicodeDecodeError, json.JSONDecodeError):\n                unclassified += size\n                continue\n            record_type = record.get(\"type\") if isinstance(record, dict) else None\n            if not isinstance(record_type, str):\n                unclassified += size\n            elif record_type == \"attachment\":\n                attachment += size\n            else:\n                other += size\nexcept OSError:\n    print(\"Cannot read selected JSONL file.\", file=sys.stderr)\n    raise SystemExit(1)\n\npct = attachment * 100.0 \u002F total if total else 0.0\nprint(f\"persisted {total}B | attachment records {attachment}B ({pct:.1f}%) | \"\n      f\"other records {other}B | unclassified {unclassified}B\")\nEOF\n```\n\nThe three categories add up to the original file bytes, including line endings and blank lines.\n`attachment` is an exact record-type filter, not a guarantee about a harness's current internal\nschema. Other records have a different string `type`; malformed JSON, invalid UTF-8, nonobject\nvalues, missing or non-string types, and blank lines are unclassified. Neither category means\n\"conversation,\" and the percentage is only a share of persisted bytes.\n\nThese counts do not establish active context, remaining room, token usage, billing, or what a\nreconnect loads. For current harness-reported context and usage, use the version-appropriate\n[`\u002Fcontext` and `\u002Fusage` commands (`\u002Fcost` is an alias)](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fcommands).\n",{"name":5,"metadata":24,"description":7},{"origin":25},"ECC","main","15fa5201935d2b1d172b4e61c2360c908d876d20","plugins\u002Fagent-dev\u002Fskills\u002Fcontext-budget",0,"https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP","https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fsfp-hive","https:\u002F\u002Fgithub.com\u002Fsiddu1004","I am a student at Amrita Vishwa Vidyapeetham pursuing my BTECH degree in Electronics and Electrical Engineering (2024-2028).","2026-11-09 16:04:40",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add siddu1004\u002FSFP --skill context-budget",{"tool":41,"command":42},"bunx","bunx skills add siddu1004\u002FSFP --skill context-budget",{"tool":44,"command":45},"pnpm","pnpm dlx skills add siddu1004\u002FSFP --skill context-budget","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fagent-dev\u002Fskills\u002Fcontext-budget\u002FSKILL.md",true,[],[50,57,64,71,78,85],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7FEEDADZBNBVY19H3XZKCBQ","scientific-schematics","Generates scientific diagram drafts using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.7 Flash for quality review. Refines when the review requests improvement, with at most two generations. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.","https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fscience-hardware\u002Fskills\u002Fscientific-schematics\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M7FEE0JS04FE58MST48D0MMC","polyhaven-texture-apply","Apply realistic PBR textures from PolyHaven to any Blender object. Supports metals, wood, concrete, fabric, and more. Trigger when asked to texture an object, apply a material from PolyHaven, make something look like metal\u002Fwood\u002Fmarble, or change object surface.","https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fscience-hardware\u002Fskills\u002Fpolyhaven-texture-apply\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7FEDJRWV194TY411WVRS84W","polyhaven-studio-setup","Set up a professional product photography studio in Blender using PolyHaven HDRIs and PBR ground materials. Trigger when asked to create a studio setup, add HDRI lighting, set up product photography, or create a showroom scene.","https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fscience-hardware\u002Fskills\u002Fpolyhaven-studio-setup\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},"01M7FED5H2FGS50XGETMGSM0RV","polyhaven-scene-builder","Build complete product scenes using PolyHaven assets — HDRI environment, textured ground\u002Fpedestal, and optional props from the 3D model library. Trigger when asked to build a product scene, create a showcase setup, add a pedestal, or compose a product shot.","https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fscience-hardware\u002Fskills\u002Fpolyhaven-scene-builder\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},"01M7FECSNZ2CJA7Z8TPE5R844R","polyhaven-material-swap","Cycle through multiple PolyHaven materials on a product and render each variant. Great for showing color\u002Ffinish options. Trigger when asked to show material variants, swap textures, create color options, show finish comparisons, or render product in different materials.","https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fscience-hardware\u002Fskills\u002Fpolyhaven-material-swap\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},"01M7FECBPQ6YWH48PYAMS0C5CE","polyhaven-hdri-showcase","Render the same product across multiple HDRI environments and output a comparison grid. Trigger when asked to compare lighting setups, test different environments, show product in multiple settings, or create an HDRI comparison.","https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fscience-hardware\u002Fskills\u002Fpolyhaven-hdri-showcase\u002FSKILL.md",[],[]]