Models

Provider models with prompting guidance scoped to model behavior — not the tool around them. No rankings; entries document observed and documented behavior.

Claude Opus 5
Anthropic · active
anthropic-claude-opus-5
Anthropic's model for complex agentic coding and long-horizon work. These notes describe model behavior, not Claude Code behavior.
AnthropicCurrent · verified Sep 17, 2026
Claude Sonnet 5
Anthropic · active
anthropic-claude-sonnet-5
Anthropic's active Sonnet model for general reasoning, coding, and agentic tasks. These notes describe model behavior, not Claude Code behavior.
AnthropicCurrent · verified Sep 17, 2026
Gemini 3.8 Flash
Google · active
google-gemini-3-8-flash
Google's stable Gemini 3.8 Flash model for coding, agentic, and complex multistep work. These notes describe model behavior, not Gemini CLI behavior.
GoogleCurrent · verified Sep 17, 2026
GPT-5.3-Codex
OpenAI · active
openai-gpt-5-3-codex
OpenAI's agentic coding model for Codex or similar environments. These notes cover model-level behavior; instruction files, permissions, and context discovery belong to the harness using it.
OpenAICurrent · verified Sep 17, 2026
GPT-6 Astra
OpenAI · active
openai-gpt-6-astra
OpenAI's current model for demanding multistep work, including software engineering and tool-supported tasks. These notes describe model behavior, not Codex behavior.
OpenAICurrent · verified Sep 17, 2026