gemini-sub-agent

Use Google Gemini (via subscription, $0 API cost) as a sub-agent inside OpenClaw workflows.

Setup

Run once on a fresh machine:

bash skills/gemini-sub-agent/scripts/setup.sh

Then authenticate (headless VPS flow):

1. On VPS: gcloud auth application-default login --no-browser → copy the --remote-bootstrap URL
2. On laptop: gcloud auth application-default login --remote-bootstrap="" → copy the localhost:8085 output
3. Paste localhost:8085 output back into VPS prompt
4. Complete Gemini CLI OAuth: GOOGLE_GENAI_USE_GCA=true gemini -p "hello" → paste auth code

Credentials are cached indefinitely and auto-refresh.

Available Models

Usage Patterns

1. Simple text task (exec)

ask-gemini "your prompt here"
ask-gemini -m gemini-2.5-pro "your prompt"

2. Pipe large content (long-context)

cat large_file.txt | ask-gemini "summarize this in 5 bullets"
cat report.md | ask-gemini "extract all action items"

3. Agentic coding (replaces Swift/Sonnet for 30-200 line tasks)

cd /path/to/project
GOOGLE_GENAI_USE_GCA=true gemini -m gemini-2.5-pro -y -p "write a script that..."

-y = yolo mode (auto-approves all file writes and shell commands). Gemini reads/writes files autonomously.

4. Pipe files directly into agentic session

cat existing_script.py | GOOGLE_GENAI_USE_GCA=true gemini -m gemini-2.5-pro -y -p "refactor this to add error handling"

Routing Rules (when to use Gemini vs others)

Escalation

If Gemini returns wrong output twice on the same task → escalate to Swift (Sonnet) or Codex (Opus).

Log the failure in failures/hot_antipatterns.md with the task type.

Scripts

• scripts/setup.sh — Full install: gemini-cli + gcloud + ask-gemini wrapper
• scripts/ask-gemini — The wrapper script itself (copy to /usr/local/bin/)