{"nextCursor":null,"query":"","results":[{"id":"prof_8d14c0854bfdd11cf75a5f0226b6441a","kind":{"value":"general","controlled":true},"models":["openai-codex/gpt-5.6-luna","openai-codex/gpt-5.6-luna:max","openai-codex/gpt-5.5"],"name":"sub-codex","ompVersion":null,"owner":"thekidnamedkd","providers":["openai-codex"],"revision":"61803d08aebe1d09ddff27148f5f7a4dbed4a780","source":"https://gist.github.com/4257cbb9b3439a3d48647636770f230b","structural":"valid","summary":"One provider, differentiated by task — the max-reasoning tier for planning, the standard tier for the everyday, a cheaper tier for chores. All OpenAI Codex, so it runs in a single-provider harness (Codex) as well as omp/pi. Reach for it when you are all-in on one provider but still want per-task model selection.","tags":["single-provider","openai","codex","task-routing"],"updatedAt":"2026-08-15T21:28:25.593Z","url":"/p/prof_8d14c0854bfdd11cf75a5f0226b6441a"},{"id":"prof_db9da061f373a7fc8612ddae8c8cd423","kind":{"value":"general","controlled":true},"models":["anthropic/claude-sonnet-4.6","anthropic/claude-opus-4-8","anthropic/claude-haiku-4.6"],"name":"sub-claude","ompVersion":null,"owner":"thekidnamedkd","providers":["anthropic"],"revision":"9d0b7e8dbd21cf4840500328aa5f1df20abca891","source":"https://gist.github.com/7e2060107cda52105b758d02ab80ee66","structural":"valid","summary":"One provider, differentiated by task — Opus for planning, Sonnet for the everyday, Haiku for cheap chores. All Anthropic, so it runs anywhere Claude runs (Claude Code included), not only multi-provider harnesses. Reach for it when you live in one provider but still want the right model per task.","tags":["single-provider","anthropic","claude","task-routing"],"updatedAt":"2026-08-15T21:28:22.918Z","url":"/p/prof_db9da061f373a7fc8612ddae8c8cd423"},{"id":"prof_3858e8c9fe61d2b5bcbf207be98db8b8","kind":{"value":"research","controlled":true},"models":["openai/gpt-5.6","anthropic/claude-opus-4-8","anthropic/claude-sonnet-4.6","anthropic/claude-haiku-4.6"],"name":"research","ompVersion":null,"owner":"thekidnamedkd","providers":["openai","anthropic"],"revision":"3f537e59363afc1d1b6b17ca133123e098624359","source":"https://gist.github.com/e6c328896825056a26a6bc190fac7b01","structural":"valid","summary":"Optimized for investigation — frontier reasoning by default, Opus for planning the approach, and generous thinking budgets. Reach for it when the goal is understanding a problem deeply rather than shipping code fast.","tags":["research","high-reasoning","exploration"],"updatedAt":"2026-08-15T17:10:16.119Z","url":"/p/prof_3858e8c9fe61d2b5bcbf207be98db8b8"},{"id":"prof_d2c4ffc29a30f50f68cedfd1bb1139c8","kind":{"value":"budget","controlled":true},"models":["deepseek/deepseek-v4-flash","ollama/qwen3.6","moonshotai/kimi-k2.6","z-ai/glm-5.2"],"name":"budget","ompVersion":null,"owner":"thekidnamedkd","providers":["deepseek","ollama","moonshotai","z-ai"],"revision":"70d1123f2a07b8f3faa046c5b168123937be3489","source":"https://gist.github.com/98c5887be22842e59a6a2176a5c5784b","structural":"valid","summary":"The cheapest way to keep working — DeepSeek Flash for the bulk, a local model for chores, Kimi for planning, GLM for review. Reach for it on high-volume, low-stakes work where throughput per dollar matters more than peak quality.","tags":["budget","cost-sensitive","deepseek","open-weight"],"updatedAt":"2026-08-15T17:10:12.692Z","url":"/p/prof_d2c4ffc29a30f50f68cedfd1bb1139c8"},{"id":"prof_446297f3a63be7851ffb8aaecebd8f1b","kind":{"value":"general","controlled":true},"models":["anthropic/claude-opus-4-8","openai/gpt-5.6","google/gemini-3.5-pro","anthropic/claude-sonnet-4.6"],"name":"max-quality","ompVersion":null,"owner":"thekidnamedkd","providers":["anthropic","openai","google"],"revision":"4a209b4c75ec85fca950a8d0bfa63fd62d791ed0","source":"https://gist.github.com/28bcab0866629a801d4b544df5ca34fc","structural":"valid","summary":"No compromises — Opus and GPT-5.6 at high reasoning for everything, an independent frontier reviewer, and a dedicated security pass. Reach for it on high-stakes work where a wrong answer costs far more than the tokens.","tags":["max-quality","frontier","high-reasoning","independent-review","security"],"updatedAt":"2026-08-15T17:10:09.347Z","url":"/p/prof_446297f3a63be7851ffb8aaecebd8f1b"},{"id":"prof_3f7db280f4670673ddf28fe23553d5b7","kind":{"value":"local","controlled":true},"models":["ollama/qwen3.6","openai/gpt-5.6","anthropic/claude-opus-4-8"],"name":"local","ompVersion":null,"owner":"thekidnamedkd","providers":["ollama","openai","anthropic"],"revision":"35beadde748a3c89e6ef0955fd9c6680e668f954","source":"https://gist.github.com/14f560fc333b0c700d3071539e87d3de","structural":"valid","summary":"Runs day-to-day work on a local open-weight model for privacy and zero marginal cost, escalating only planning and review to cloud frontier models. Reach for it when you want most tokens to stay on your machine but still want a strong second opinion on the hard calls.","tags":["local","open-weight","privacy","ollama","cloud-escalation"],"updatedAt":"2026-08-15T17:10:05.832Z","url":"/p/prof_3f7db280f4670673ddf28fe23553d5b7"},{"id":"prof_54094903ec3ca438c78dcb6418160c55","kind":{"value":"general","controlled":true},"models":["anthropic/claude-sonnet-4.6","anthropic/claude-opus-4-8","anthropic/claude-haiku-4.6"],"name":"subscription","ompVersion":null,"owner":"thekidnamedkd","providers":["anthropic"],"revision":"a667ec8d3caff890b522e373ea00cab91429adbf","source":"https://gist.github.com/abb24cf3532972f81f9088ff96ca4f92","structural":"valid","summary":"Everything on one Claude subscription — Opus for planning, Sonnet for day-to-day, Haiku for cheap chores. Reach for it when you want strong quality at a flat, predictable monthly cost with no metered-API surprises.","tags":["subscription","anthropic","predictable-cost","general"],"updatedAt":"2026-08-15T17:10:01.491Z","url":"/p/prof_54094903ec3ca438c78dcb6418160c55"},{"id":"prof_458c04dcb6228b2429aff3e1d0781bae","kind":{"value":"general","controlled":true},"models":["anthropic/claude-sonnet-4.6","openai/gpt-5.6","google/gemini-3.5-pro","anthropic/claude-haiku-4.6","ollama/qwen3.6","anthropic/claude-opus-4-8","google/gemini-3.5-flash"],"name":"hybrid","ompVersion":null,"owner":"thekidnamedkd","providers":["anthropic","openai","google","ollama"],"revision":"fcd8abe85aa897c2349dfbd778847e3d24667d74","source":"https://gist.github.com/44cfc552982441327d6bb204ab76afa0","structural":"valid","summary":"The everyday driver — Sonnet subscription for most work, GPT-5.6 for planning, Gemini as an independent reviewer, and a local model for cheap background chores. Fallback chains keep you working when a provider degrades. Reach for it when you want strong results without paying frontier rates for every token.","tags":["hybrid","multi-provider","fallback","advisor","general"],"updatedAt":"2026-08-15T17:09:45.618Z","url":"/p/prof_458c04dcb6228b2429aff3e1d0781bae"},{"id":"prof_0e5a022da1cc6305b99b5fe806137b61","kind":null,"models":["opencode-go/kimi-k2.7-code","opencode-go/glm-5.2","opencode-go/kimi-k3","ollama/qwen3.6:latest"],"name":"metered-lab-kimi","ompVersion":null,"owner":"thekidnamedkd","providers":["opencode-go","ollama"],"revision":"92a08aef1d67525afb11f239588883be94401d84","source":"https://gist.github.com/57b4d8511b804f5857586dd19648335d","structural":"valid","summary":null,"tags":[],"updatedAt":"2026-08-12T14:54:05.478Z","url":"/p/prof_0e5a022da1cc6305b99b5fe806137b61"}]}