omni-prime

omni-prime is a command for Claude Code from basher83/lunar-claude. It costs 14 tokens per session (650 once invoked), scanned A, original, MIT.

A command that starts a new agent session by examining the repository file structure and README. It produces a short overview of the project and its operating conventions.

In plain words
What is it for?
Use it at the beginning of a session to understand an unfamiliar codebase, its purpose, setup instructions, structure, and available infrastructure tools.
Why use it?
It gives an agent the basic project context before it starts making changes, reducing confusion about where files live and how the project is intended to work.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the omni-scale plugin — 1 skill, 5 commands, 2 agents shipped together

Good fit Use it at the beginning of a session to understand an unfamiliar codebase, its purpose, setup instructions, structure, and available infrastructure tools.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add basher83/lunar-claude
Claude Code
/plugin install omni-scale

Made for: Claude Code.

Or install omni-scale, the plugin that ships this one along with the rest of its 1 skill, 5 commands, 2 agents.

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.

agentmods badge for omni-prime

README.md
[![agentmods](https://agentmods.dev/badge/commands/basher83/lunar-claude/omni-prime/github.svg)](https://agentmods.dev/commands/basher83/lunar-claude/omni-prime)
Your own site
<a href="https://agentmods.dev/commands/basher83/lunar-claude/omni-prime"><img src="https://agentmods.dev/badge/commands/basher83/lunar-claude/omni-prime/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for omni-prime

Your own site · 80×15
<a href="https://agentmods.dev/commands/basher83/lunar-claude/omni-prime"><img src="https://agentmods.dev/badge/commands/basher83/lunar-claude/omni-prime.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 650 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00014 $0.00650
Opus 5 $0.00007 $0.00325
Sonnet 5 $0.00003 $0.00130
Haiku 4.5 $0.00001 $0.00065

Measured 7d ago against content hash db318a8149f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

omni-prime 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 7d 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.

plugins/homelab/omni-scale/commands/omni-prime.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prime

This command loads essential context for a new agent session.

Instructions

  • Run git ls-files to understand the codebase structure and file organization
  • Read the README.md to understand the project purpose, setup instructions, and key information
  • Provide a concise overview of the project based on the gathered context

Context

  • Codebase structure git accessible: !git ls-files
  • Codebase structure all: !eza . --tree
  • Project README: @${CLAUDE_PROJECT_DIR}/README.md
  • Kernel context: @${CLAUDE_PLUGIN_ROOT}/references/kernel.md

Tool Usage Patterns

MCP Kubernetes Tools

Use mcp__plugin_omni-scale_kubernetes__* for cluster operations.

Validation checks — gather this data:

  • ArgoCD: Sync status + health status (per app). Flag any NOT Synced+Healthy.
  • External Secrets: ClusterSecretStore health, ExternalSecret sync status. Flag failures.
  • Longhorn: Volume state (attached/detached) + robustness (healthy/degraded). Flag unhealthy.

Use MCP first. Fall back to kubectl CLI only if MCP output lacks required fields.

Helm via MCP

Limited to: install, upgrade, uninstall. ArgoCD handles Helm for this stack — MCP Helm rarely needed.

omnictl

Cluster status (includes machine health):

omnictl cluster status <cluster-name>

List machines (if needed separately):

omnictl get machines -l omni.sidero.dev/cluster=<cluster-name>

Note: --cluster flag does not exist. Use label selector -l instead.

Operational Pattern

When an infrastructure operation fails on first attempt:

  1. Check for skill coverage before retrying with variations
  2. Skills encode operational knowledge — "how do I access X" is exactly what they're for
  3. Don't guess hostnames, paths, or commands — if it's not documented, ask

CLI Fallback Context

When MCP kubernetes tools fail and you need CLI fallback, specify the context:

kubectl --context omni-talos-prod-01 get pods

Do NOT pass context to MCP tools — they handle kubeconfig internally.

Read the full file on GitHub · 80 lines

Changes

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.

  1. 7d ago First seen · 80 lines · 14 tokens per session scan A db318a8149f2

Subscribe to this mod's changes

omni-prime is a command published in the GitHub repository basher83/lunar-claude (23 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 650 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.