Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/destroy-cluster)<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/destroy-cluster"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/destroy-cluster.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 5.1 | $0.00011 | $0.02604 |
| Opus 5 | $0.00005 | $0.01302 |
| Sonnet 5 | $0.00002 | $0.00521 |
| Haiku 4.5 | $0.00001 | $0.00260 |
Grade C, and why
destroy-cluster scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$INSTALL_DIR" How it starts
The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
openshift:destroy-cluster
Synopsis
/openshift:destroy-cluster [install-dir]
Description
The destroy-cluster command safely destroys an OpenShift Container Platform (OCP) cluster that was previously created using the /openshift:create-cluster command. It locates the appropriate installer binary, verifies the cluster information, and performs cleanup of all cloud resources.
This command is useful for:
- Cleaning up development/test clusters after testing
- Removing failed cluster installations
- Freeing up cloud resources and quotas
⚠️ WARNING: This operation is irreversible and will permanently delete:
- All cluster resources (VMs, load balancers, storage, etc.)
- All data stored in the cluster
- All configuration and credentials
- DNS records (if managed by the installer)
Prerequisites
Before using this command, ensure you have:
-
Installation directory from the original cluster creation
- Contains the cluster metadata and terraform state
- Located at
{cluster-name}-install-{timestamp}by default
-
OpenShift installer binary that matches the cluster version
- Should be available at
~/.openshift-installers/openshift-install-{version} - Same version used to create the cluster
- Should be available at
-
Cloud Provider Credentials still configured and valid
- Same credentials used during cluster creation
- Must have permissions to delete resources
-
Network connectivity to the cloud provider
- Required to communicate with cloud APIs
Arguments
- install-dir (optional): Path to the cluster installation directory
- Default: Interactive prompt to select from available installation directories
- Must contain cluster metadata files (metadata.json, terraform.tfstate, etc.)
- Example:
./my-cluster-install-20251028-120000
Implementation
The command performs the following steps:
1. Locate Installation Directory
If install-dir is not provided:
- Search for installation directories in the current directory
- Look for directories matching pattern
*-install-*or containing.openshift_install_state.json - Present a list of found directories to the user for selection
- Allow user to manually enter a path if directory not found
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.
- 4d ago First seen · 361 lines · 11 tokens per session scan C 9fd1d82c7612
destroy-cluster is a command published in the GitHub repository wangke19/gemini-ai-helpers (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 11 tokens to every session and 2,604 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
10_gofer_cloud
Deploy and configure the Gofer cloud integration for remote pipeline execution.
deploy-ai
description: "Deploy AI system to production".
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.