omp

A shortcut for running the Oh My Pi command-line tool through the Elves environment for one task at a time.

In plain words
What is it for?
Use it when someone asks for /omp or says to use omp; it runs read-only by default and can optionally select a model.
Why use it?
It provides a defined way to invoke Oh My Pi without relying on unrelated settings from the host computer.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/aigorahub/elves/omp
Any agent
npx skills add aigorahub/elves --skill omp
Clone the repo
git clone --depth 1 https://github.com/aigorahub/elves

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 250 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00034 $0.00250
Opus 5 $0.00017 $0.00125
Sonnet 5 $0.00007 $0.00050
Haiku 4.5 $0.00003 $0.00025

Measured 2d ago against content hash 4c336f52f1a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

omp 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 2d 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.

aliases/claude/omp/SKILL.md · 23 lines

What it actually says

/omp

Resolve the runner from the active Elves skill root and keep the target repository as cwd:

"$ELVES_SKILL_ROOT/scripts/run_omp.sh" <task>
  • CLI binary is omp (Oh My Pi), never opm.
  • Read-only by default (--approval-mode always-ask). Set ELVES_OMP_WRITE=1 only when the host independently authorizes writes.
  • Optional model pin: ELVES_OMP_MODEL=<provider/model>.
  • Uses a run-scoped --profile (no ambient host HOME / ~/.claude/tools inheritance).
  • Never grants PR, merge, protected-ref, or landing authority.
  • For trusted overnight labor, use the full-run omp-cli worker path instead of this shortcut.

Codex/Grok: $elves omp … or natural language — do not invent top-level Codex slash commands.

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. 2d ago First seen · 23 lines · 34 tokens per session scan A 4c336f52f1a6

Subscribe to this mod's changes

omp is a skill published in the GitHub repository aigorahub/elves (213 stars, last pushed 6d ago), licensed MIT. It adds 34 tokens to every session and 250 once invoked, about $0.0002 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 2026-08-30.