mcpField
G
gemini-runner

gemini-runner

github.com/robsonrungAgent workflows277 installsUpdated 3d ago
Repository

About gemini-runner

A skill that dispatches a caller-scoped prompt through the local Antigravity CLI, `agy`, while following an approved Gemini model snapshot. It checks the serving model and route outcome rather than treating process completion as proof of success.

Key features

  1. 01Run prompts through local `agy` CLI
  2. 02Use an approved Gemini model snapshot
  3. 03Check provider and serving-model receipt
  4. 04Report fallback and malformed output
  5. 05Resume shared conversations when configured

Use cases

  1. 01Dispatching a scoped task to Gemini
  2. 02Verifying which provider answered
  3. 03Handling unavailable or unverified model routes
  4. 04Continuing a shared CLI conversation

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/robsonrung/rar-skills --skill gemini-runner

After installing, type/gemini-runnerin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

agents/
openai.yaml
references/
command-reference.md
continuation.md
runtime-reference.md
scripts/
run_gemini.py
tests/
test_run_gemini.py

Details

From the project README

Gemini Runner

Use shared/references/model-preview.md to choose the branch first. Deterministic checks need no model selection. Actual dispatch uses one concrete approved snapshot; nested calls consume it without re-resolution or extra workers.

Execute the caller's scoped prompt through the local CLI. Shared roles, envelope keys, and result handling live in shared/references/runner-common.md. Preserve seat fidelity: name the provider that actually answered, and report unavailable or unverified seats honestly.

Native routing

Read shared/references/host-model-execution.md before choosing an external route. If the current host can dispatch the exact selected Gemini model with the required effort, isolation, and receipt policy in a native subagent or task thread, use that route. agents/openai.yaml is host UI metadata; it does not dispatch a native model.

Invocation

Set SKILL_DIR to this loaded skill directory in the same shell call:

SKILL_DIR="<absolute path of this skill directory>";
python3 "$SKILL_DIR/scripts/run_gemini.py" "<scoped prompt>" \
  --model <approved-model-id> --disable-fallback --json

Copy the selected model label, role, tool mode, receipt policy, and supported limits from the snapshot. This runner has no effort flag or native effort control. A route requiring unsupported control stays blocked. Nested calls use the saved options without resolving defaults again. The example does not grant source sharing or tool authority.

Runtime boundaries

  • Use the local authenticated Antigravity CLI, agy, in print mode.
  • The user configures the model in agy. --model and output-format flags are request labels or prompt hints, not native model or format controls.
  • Permission checks follow local configuration. Prompt and file context may be sent to the configured provider.
  • Analysis roles use a read-only prompt overlay, not an enforced sandbox. Isolate the workspace for untrusted input; --restrict-tools alone is not a security boundary.
  • Missing-CLI fallback is labelled and described in the runtime reference. Approved routes use --disable-fallback; an unverified model requires the caller's explicit receipt policy.
  • Native output has no session ID. --agy-continue resumes the latest shared conversation and must not run concurrently against the same home.

Load by need

Result

Read agent_message and the wrapper envelope. Check success, serving-model receipt, effective runner/provider, and any fallback or malformed-output status. A completed process alone does not prove the requested task or model was used. Report touched files when the caller authorized edits.

Comments

Markdown supported