Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows
fix(docs): unset CLAUDECODE in Claude Code commit command (#1020)
Maximilian Roos7676d0f9fbd3
diff --git a/docs/content/llm-commits.md b/docs/content/llm-commits.mdindex 6b2dd0cc3..fab2fc20e 100644--- a/docs/content/llm-commits.md+++ b/docs/content/llm-commits.md@@ -23,10 +23,10 @@ Any command that reads a prompt from stdin and outputs a commit message works. A```toml[commit.generation]-command = "MAX_THINKING_TOKENS=0 claude -p --model=haiku --tools='' --disable-slash-commands --setting-sources='' --system-prompt=''"+command = "CLAUDECODE= MAX_THINKING_TOKENS=0 claude -p --model=haiku --tools='' --disable-slash-commands --setting-sources='' --system-prompt=''"```-The flags disable tools, skills, settings, and system prompt for fast text-only output. See [Claude Code docs](https://docs.anthropic.com/en/docs/build-with-claude/claude-code) for installation.+`CLAUDECODE=` unsets the nesting guard so `claude -p` works from within a Claude Code session. The other flags disable tools, skills, settings, and system prompt for fast text-only output. See [Claude Code docs](https://docs.anthropic.com/en/docs/build-with-claude/claude-code) for installation.### llmdiff --git a/skills/worktrunk/reference/llm-commits.md b/skills/worktrunk/reference/llm-commits.mdindex 2d1b82df6..e5d1d6604 100644--- a/skills/worktrunk/reference/llm-commits.md+++ b/skills/worktrunk/reference/llm-commits.md@@ -10,10 +10,10 @@ Any command that reads a prompt from stdin and outputs a commit message works. A```toml[commit.generation]-command = "MAX_THINKING_TOKENS=0 claude -p --model=haiku --tools='' --disable-slash-commands --setting-sources='' --system-prompt=''"+command = "CLAUDECODE= MAX_THINKING_TOKENS=0 claude -p --model=haiku --tools='' --disable-slash-commands --setting-sources='' --system-prompt=''"```-The flags disable tools, skills, settings, and system prompt for fast text-only output. See [Claude Code docs](https://docs.anthropic.com/en/docs/build-with-claude/claude-code) for installation.+`CLAUDECODE=` unsets the nesting guard so `claude -p` works from within a Claude Code session. The other flags disable tools, skills, settings, and system prompt for fast text-only output. See [Claude Code docs](https://docs.anthropic.com/en/docs/build-with-claude/claude-code) for installation.### llm