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.
git 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/search)<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/search"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/search.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 | $0.00007 | $0.01961 |
| Opus 5 | $0.00003 | $0.00981 |
| Sonnet 5 | $0.00001 | $0.00392 |
| Haiku 4.5 | $0.00001 | $0.00196 |
Grade A, and why
search 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 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.
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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
olm:search
Synopsis
/olm:search [query] [--catalog <catalog-name>]
Description
The olm:search command searches for available operators in the cluster's catalog sources (OperatorHub). It helps you discover operators that can be installed, showing their names, descriptions, versions, channels, and catalog sources.
This command helps you:
- Find operators by name, description, or keywords
- Discover what operators are available for installation
- View operator details before installing
- Check available versions and channels
- Identify which catalog source contains a specific operator
The command searches across all available catalog sources (redhat-operators, certified-operators, community-operators, redhat-marketplace, and custom catalogs) and presents results in an easy-to-read format.
Implementation
The command performs the following steps:
-
Parse Arguments:
$1: Query string (optional) - Search term for filtering operators- If not provided, lists all available operators
- Can be partial name, keyword, or description
$2+: Flags (optional):--catalog <catalog-name>: Limit search to specific catalog source--exact: Only show exact name matches--installed: Show only installed operators (combination with /olm:list)
-
Prerequisites Check:
- Verify
ocCLI is installed:which oc - Verify cluster access:
oc whoami - If not installed or not authenticated, provide clear instructions
- Verify
-
Fetch Catalog Data:
- Get all PackageManifests from openshift-marketplace:
oc get packagemanifests -n openshift-marketplace -o json - If
--catalogflag is specified, filter by catalog source:oc get packagemanifests -n openshift-marketplace -o json | jq '.items[] | select(.status.catalogSource=="{catalog-name}")'
- Get all PackageManifests from openshift-marketplace:
-
Parse PackageManifest Data:
- For each PackageManifest, extract:
- Name:
.metadata.name - Display Name:
.status.channels[0].currentCSVDesc.displayName - Description:
.status.channels[0].currentCSVDesc.description - Provider:
.status.provider.name - Catalog Source:
.status.catalogSource - Catalog Namespace:
.status.catalogSourceNamespace - Default Channel:
.status.defaultChannel - All Channels:
.status.channels[].name - Latest Version:
.status.channels[] | select(.name==.status.defaultChannel) | .currentCSVDesc.version - Categories:
.status.channels[0].currentCSVDesc.annotations["categories"] - Capabilities:
.status.channels[0].currentCSVDesc.annotations["capabilities"]
- Name:
- For each PackageManifest, extract:
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 · 248 lines · 7 tokens per session scan A 9e074f6baedc
search is a command published in the GitHub repository wangke19/gemini-ai-helpers (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 7 tokens to every session and 1,961 once invoked, about $0.0000 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
5_gofer_implement
Execute all tasks from tasks.md phase by phase with feedback loops and engineering review.
eai-update
Use this command to install or update EAI Gofer for the current AI coding app. This command works without an EAI project, a Gofer scaffold, or EAI sign-in.
modernize-extract-rules
Mine business logic from legacy code into testable, human-readable rule specifications.
mem-search
Full-text search in the memory vault (archives, contexts, histories, index).
bmad-agent-pm
Product manager for PRD creation and requirements discovery. Use when the user asks to talk to John or requests the product manager.
help
Get help with the hookify plugin.