Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/wangke19/gemini-ai-helpers/installgit clone --depth 1 https://github.com/wangke19/gemini-ai-helpersWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/wangke19/gemini-ai-helpers/install)<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/install"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/install.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00010 | $0.02370 |
| Opus 5 | $0.00005 | $0.01185 |
| Sonnet 5 | $0.00002 | $0.00474 |
| Haiku 4.5 | $0.00001 | $0.00237 |
Grade A, and why
install scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
gwapi:install
Synopsis
/gwapi:install [namespace]
Description
The gwapi:install command applies Gateway API YAML resources to a Kubernetes or OpenShift cluster. It installs:
gatewayclass.yaml- Defines the GatewayClass resourcegateway.yaml- Defines the Gateway resource with cluster-specific domain configuration
The command automatically retrieves the cluster's ingress domain and substitutes it into the gateway.yaml before applying. It uses oc (preferred) or kubectl to install the resources.
The command waits for all resources to reach a successful status before completing (up to 5 minutes timeout). This ensures that the Gateway API resources are fully reconciled and ready for use.
Arguments
$1(optional): Target namespace for installing Gateway API resources. If not specified, uses the namespace defined in the YAML files or the current namespace context.
Implementation
-
Tool Detection
- Check if
ocis available:which oc - If not available, check for
kubectl:which kubectl - If neither is available, inform the user to install one of these tools:
- Check if
-
Cluster Connection Verification
- Verify cluster connectivity:
oc whoamiorkubectl cluster-info - If connection fails, inform the user to authenticate to their cluster:
- For OpenShift:
oc login <cluster-url> - For Kubernetes: Configure kubeconfig properly
- For OpenShift:
- Verify cluster connectivity:
-
Retrieve Cluster Domain
- Get the cluster's ingress domain:
DOMAIN=$(oc get ingresses.config/cluster -o jsonpath={.spec.domain}) - If this fails (e.g., on non-OpenShift clusters), ask the user to provide the domain manually
- Verify domain is not empty:
echo $DOMAIN
- Get the cluster's ingress domain:
-
Namespace Handling
- If namespace argument is provided:
- Check if namespace exists:
oc get namespace <namespace>orkubectl get namespace <namespace> - If it doesn't exist, create it:
oc create namespace <namespace>orkubectl create namespace <namespace> - Set context to use this namespace for subsequent commands
- Check if namespace exists:
- If namespace argument is provided:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 209 lines · 10 tokens per session scan A fff3eec3adc3
install is a command published in the GitHub repository wangke19/gemini-ai-helpers (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 10 tokens to every session and 2,370 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
test-ephemeral
Deploy and test a merge request in ephemeral environment.
vpn
Connect to Red Hat VPN for internal resources.
10_gofer_cloud
Deploy and configure the Gofer cloud integration for remote pipeline execution.
deploy-ai
description: "Deploy AI system to production".
create-docker-mcp-tunnel
Stand up an Google MCP tunnel locally with Docker Compose so Gemini can call a private MCP server (manual-credentials quickstart).
checklist
Generate a custom checklist for the current feature based on user requirements.