oh-my-hermes is an operating layer for Hermes Agent that organizes requests into workflows for planning, research, creation, coding handoffs, operations, and project memory. Hermes users run these workflows through the desktop app, CLI, or messenger app, while the catalogue add-ons extend its native capabilities.
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.
npx skills add rlaope/oh-my-hermes --skill omh-inference-servinggit clone --depth 1 https://github.com/rlaope/oh-my-hermesWrote 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/skills/rlaope/oh-my-hermes/omh-inference-serving)<a href="https://agentmods.dev/skills/rlaope/oh-my-hermes/omh-inference-serving"><img src="https://agentmods.dev/badge/skills/rlaope/oh-my-hermes/omh-inference-serving/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.
<a href="https://agentmods.dev/skills/rlaope/oh-my-hermes/omh-inference-serving"><img src="https://agentmods.dev/badge/skills/rlaope/oh-my-hermes/omh-inference-serving.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 78 Potential security issue detected. Manual review is recommended.Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00092 | $0.01846 |
| Opus 5.5 | $0.00037 | $0.00738 |
| Sonnet 5.5 | $0.00018 | $0.00369 |
| Haiku 4.5 | $0.00009 | $0.00185 |
Grade A, and why
omh-inference-serving 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inference Serving
This is an OMH inference-serving workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
Why This Exists
inference-serving exists so serving an LLM runs as one decided, gated, measured process instead of scattered flag folklore: the engine choice is a table, the deployment is an idempotent runbook whose only completion evidence is the observed verification, and the benchmark speaks the standard metric vocabulary.
Do Not Use When
- A new model generation needs recognition, calibration, routing, and pricing onboarding.
- The user wants their own machine's model routing or providers configured.
- The question is whether a coding runtime/executor can run at all.
- The goal is application or system performance rather than the serving endpoint itself; use
ulw-perf.
Examples
Good example:
- Prompt: Serve Qwen on our two A100s for the team and tell me if prefix caching is worth turning on.
- Expected behavior: Engine verdict (vLLM, TP as a power of two), quantization check, the k8s or docker runbook with its gates and verification, then the prefix-cache A/B protocol with hit-rate assumptions recorded - numbers only from observed runs.
- Why: Serving plus a measured tuning question is exactly the decide-deploy-measure process this workflow owns.
Bad example:
- Prompt: Just tell me the endpoint is fast enough, we already know it works.
- Expected behavior: Refuse the unmeasured claim; run the benchmark protocol against the stated SLO or report the capacity question as unanswered.
- Why: A fast-enough claim without a load shape and observed results is the folklore this skill replaces.
Completion Checklist
- The engine/quantization verdict names the situation-table row it came from and the rejected options.
- Every runbook step's status is prepared or observed, never assumed, and the port invariant was honored.
- Benchmark numbers carry metrics, load shape, dataset, SLO, and saved metadata, or are not reported.
- Anything the workflow started for measurement was stopped, and credentials never appear in artifacts.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +1 lines 4fdc93ce2ca5
- 11d ago Changed cc29559cccf9
- 13d ago Changed · +1 lines 9d1710177063
- 26d ago Changed · +3 lines 531c14aa88ff
- 1mo ago Changed · +2 tokens per session 1828dc444b9c
- 1mo ago Changed · +6 lines d357a82bf576
- 1mo ago Changed 195333cfa972
- 1mo ago Changed · -11 lines 0923a8ffe816
- 1mo ago Changed a5bb180534ec
- 1mo ago First seen · 130 lines · 90 tokens per session scan A 3d0112c1cf6c
omh-inference-serving is a skill published in the GitHub repository rlaope/oh-my-hermes (4,314 stars, last pushed today), licensed MIT. It adds 92 tokens to every session and 1,846 once invoked, about $0.0004 per session on Opus 5.5. 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 skills, from other repositories
x-cpu
Display CPU information and detect system endianness. Shows model, cores, frequency, vendor, cache size. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
prompt
Prompt engineering conventions for x-cmd — reuse via template variables, structure rules, safety enforcement patterns.
x-ohmyposh
Oh-My-Posh prompt theme engine with theme management. Cross-platform tool to render your prompt with consistent experience. Auto-downloads oh-my-posh binary if not available. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
lijigang-skill
A Chinese-language approach to writing precise, highly structured prompts, sometimes using Lisp-like notation. It combines concise wording, philosophical questioning, and a process for defining roles, conditions, output formats, and revisions.
prism
Consultant for NotebookLM steering prompt design. Optimizes Audio/Video/Slide/Infographic output quality through source preparation, prompt engineering, and Custom Goals persona design.
aws-solution-architect
Design or review AWS architecture and infrastructure as code for serverless systems, migrations, scaling, reliability, and cost constraints.