Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows
docs(llm-commits): describe the Codex model the command actually pins (#3867)
Worktrunk Botbe2c088a610a
diff --git a/docs/src/content/docs/llm-commits.md b/docs/src/content/docs/llm-commits.mdindex dc54ca96f..b521ff8c2 100644--- a/docs/src/content/docs/llm-commits.md+++ b/docs/src/content/docs/llm-commits.md@@ -33,7 +33,7 @@ command = "MAX_THINKING_TOKENS=0 claude -p --no-session-persistence --model=haikcommand = "codex exec -m gpt-5.6-luna -c model_reasoning_effort='low' -c system_prompt='' --sandbox=read-only --json - | jq -sr '[.[] | select(.item.type? == \"agent_message\")] | last.item.text'"```-Uses the fast mini model with low reasoning effort and an empty system prompt for faster output. Requires `jq` for JSON parsing. See [Codex CLI docs](https://developers.openai.com/codex/cli/).+Uses the fast, low-cost variant of the current Codex model family with low reasoning effort and an empty system prompt for faster output. Requires `jq` for JSON parsing. See [Codex CLI docs](https://developers.openai.com/codex/cli/).### Other toolsdiff --git a/plugins/worktrunk/skills/worktrunk/reference/llm-commits.md b/plugins/worktrunk/skills/worktrunk/reference/llm-commits.mdindex fb3f31adc..e3225f729 100644--- a/plugins/worktrunk/skills/worktrunk/reference/llm-commits.md+++ b/plugins/worktrunk/skills/worktrunk/reference/llm-commits.md@@ -22,7 +22,7 @@ command = "MAX_THINKING_TOKENS=0 claude -p --no-session-persistence --model=haikcommand = "codex exec -m gpt-5.6-luna -c model_reasoning_effort='low' -c system_prompt='' --sandbox=read-only --json - | jq -sr '[.[] | select(.item.type? == \"agent_message\")] | last.item.text'"```-Uses the fast mini model with low reasoning effort and an empty system prompt for faster output. Requires `jq` for JSON parsing. See [Codex CLI docs](https://developers.openai.com/codex/cli/).+Uses the fast, low-cost variant of the current Codex model family with low reasoning effort and an empty system prompt for faster output. Requires `jq` for JSON parsing. See [Codex CLI docs](https://developers.openai.com/codex/cli/).### Other toolsdiff --git a/skills/worktrunk/reference/llm-commits.md b/skills/worktrunk/reference/llm-commits.mdindex fb3f31adc..e3225f729 100644--- a/skills/worktrunk/reference/llm-commits.md+++ b/skills/worktrunk/reference/llm-commits.md@@ -22,7 +22,7 @@ command = "MAX_THINKING_TOKENS=0 claude -p --no-session-persistence --model=haikcommand = "codex exec -m gpt-5.6-luna -c model_reasoning_effort='low' -c system_prompt='' --sandbox=read-only --json - | jq -sr '[.[] | select(.item.type? == \"agent_message\")] | last.item.text'"```-Uses the fast mini model with low reasoning effort and an empty system prompt for faster output. Requires `jq` for JSON parsing. See [Codex CLI docs](https://developers.openai.com/codex/cli/).+Uses the fast, low-cost variant of the current Codex model family with low reasoning effort and an empty system prompt for faster output. Requires `jq` for JSON parsing. See [Codex CLI docs](https://developers.openai.com/codex/cli/).### Other tools