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-model-finetuninggit 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-model-finetuning)<a href="https://agentmods.dev/skills/rlaope/oh-my-hermes/omh-model-finetuning"><img src="https://agentmods.dev/badge/skills/rlaope/oh-my-hermes/omh-model-finetuning/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-model-finetuning"><img src="https://agentmods.dev/badge/skills/rlaope/oh-my-hermes/omh-model-finetuning.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00118 | $0.01970 |
| Opus 5.5 | $0.00047 | $0.00788 |
| Sonnet 5.5 | $0.00024 | $0.00394 |
| Haiku 4.5 | $0.00012 | $0.00197 |
Grade A, and why
omh-model-finetuning 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 yesterday.
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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Finetuning
This is an OMH model-finetuning workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
Why This Exists
model-finetuning exists because producing a model had no owner: inference-serving serves one that exists and llm-app-dev builds on top of one, while an SFT or DPO question had no baseline comparison and no way to answer that training is not needed.
First Steps
- Ask what the untuned model and the best prompt score on the held-out examples before discussing any method.
- Ask what shape the data has -- demonstrations, preference pairs, or answers a program can check.
Do Not Use When
- The ask is onboarding a new model generation into OMH's routing, calibration, or pricing.
- The ask is serving an existing model behind an endpoint or benchmarking that endpoint; use
omh-inference-serving. - The ask is building an application on top of a hosted model -- RAG, structured output, prompt versions; use
omh-llm-app-dev. - The ask is learning from an OMH run, a missed route, or a skill improvement candidate.
Examples
Good example:
- Prompt: should we fine-tune a model for our support replies or is a better prompt enough
- Expected behavior: Ask for the held-out examples and the current prompt's score, try few-shot and retrieval against them, and return
do_not_finetuneif one closes the gap; otherwise pick SFT from the reply demonstrations and gate promotion on beating the untuned baseline. - Why: Most prompt-shaped gaps close without training, and training first hides that the cheaper fix was enough.
Bad example:
- Prompt: the fine-tuned checkpoint got 0.82 on our eval, ship it
- Expected behavior: Refuse to promote on a standalone score: run the same held-out eval on the untuned baseline and compare before promotion.
- Why: A score with no baseline cannot show the training helped at all.
Completion Checklist
- The fine-tune decision is stated, and
do_not_finetunewas considered first. - The method is chosen from the data's shape and its failure mode is named.
- The held-out split was drawn before training and checked for overlap.
- Promotion cites the same eval observed on the untuned baseline and the candidate.
- OMH ran nothing, and every score cites observed output or is marked unverified.
What ships with it
1 file 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.
- yesterday Changed cc00eb627798
- 3d ago Changed · +1 lines 8698458e0204
- 16d ago Changed · +3 lines b1cf221ee30b
- 18d ago First seen · 135 lines · 118 tokens per session scan A bdddf920ea23
omh-model-finetuning is a skill published in the GitHub repository rlaope/oh-my-hermes (3,392 stars, last pushed today), licensed MIT. It adds 118 tokens to every session and 1,970 once invoked, about $0.0005 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 2026-09-29.
Other skills, from other repositories
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.
prompt-optimizer
Refine prompts or ambiguous requirements into testable specifications when the user asks to improve wording, scope, constraints, or acceptance criteria.
baoyu-skill
A Chinese-language approach to explaining AI tools and writing prompts—instructions that tell an AI what you want. It emphasizes step-by-step teaching, hands-on testing, plain-language technical explanations, and organized knowledge sharing.
openai-docs
Find current official OpenAI guidance for Codex, APIs, models, prompting, or migrations. Preserve a named target model and cite fetched documentation.
fetch-llm-apps
Regenerate the ranked GitHub LLM applications pool (section/xllmapps.md) with fetchllmapps.py. USE FOR: refreshing the pool linked from applications.md. DO NOT USE FOR: hand-curating entries in applications.md or adding star badges to the generated file.