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/opm)<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/opm"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/opm.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 | $0.00015 | $0.03680 |
| Opus 5 | $0.00008 | $0.01840 |
| Sonnet 5 | $0.00003 | $0.00736 |
| Haiku 4.5 | $0.00002 | $0.00368 |
Grade A, and why
opm 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 — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
olm:opm
Synopsis
/olm:opm build-index-image <catalog-path> <index-image-tag> [--cacheless] [--arch=<arch>] [--base-image=<image>] [--builder-image=<image>]
/olm:opm build-semver-index-image <semver-template-file> <index-image-tag> [--cacheless] [--arch=<arch>] [--base-image=<image>] [--builder-image=<image>]
/olm:opm generate-semver-template <bundle-list> [--output=<file>] [--major=true|false] [--minor=true|false]
/olm:opm list packages <index-ref>
/olm:opm list channels <index-ref> [package-name]
/olm:opm list bundles <index-ref> [package-name]
Description
The olm:opm command provides a unified interface to opm (Operator Package Manager) operations for building and managing operator catalog indexes. It supports building catalog indexes, generating semver templates, and querying catalog contents.
Arguments
$1: action - The action to perform:build-index-image: Build an index from an existing catalog directorybuild-semver-index-image: Build an index from a semver templategenerate-semver-template: Generate a semver template filelist: List catalog contents (requires second argument:packages,channels, orbundles)
$2+: Additional arguments specific to each action (see Actions section below)
Actions
build-index-image
Build an operator catalog index image from an existing catalog directory.
Synopsis:
/olm:opm build-index-image <catalog-path> <index-image-tag> [--cacheless] [--arch=<arch>] [--base-image=<image>] [--builder-image=<image>]
Arguments:
$2: catalog-path - Path to the catalog directory containing the index configuration$3: index-image-tag - Full image tag for the resulting index image (e.g.,quay.io/myorg/mycatalog:v1.0.0)--cacheless: Optional flag to build a cacheless image (usesscratchas base image;--base-imageand--builder-imageare ignored when this is set)--arch=<arch>: Optional architecture specification (default:multifor multi-arch build; can specify single arch likeamd64,arm64,ppc64le,s390x)--base-image=<image>: Optional base image for the index (default:quay.io/operator-framework/opm:latest; ignored if--cachelessis set)--builder-image=<image>: Optional builder image (default:quay.io/operator-framework/opm:latest; ignored if--cachelessis set)
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 · 360 lines · 15 tokens per session scan A 289172093e9a
opm is a command published in the GitHub repository wangke19/gemini-ai-helpers (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 3,680 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
start
Starts the Supabase local development stack.
stop
Stops the Supabase local development stack.
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).
claude-request
Send a prompt to Claude Code via the LLM gateway with session tracking.
redteam
Find likely failure paths, abuse cases, and proportionate mitigations.
ocean-stop
Gracefully stop the boil-ocean run and its scheduler.