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 rhtevan/agentfs --skill hermes-litellm-providergit clone --depth 1 https://github.com/rhtevan/agentfsWrote 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/rhtevan/agentfs/hermes-litellm-provider)<a href="https://agentmods.dev/skills/rhtevan/agentfs/hermes-litellm-provider"><img src="https://agentmods.dev/badge/skills/rhtevan/agentfs/hermes-litellm-provider/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/rhtevan/agentfs/hermes-litellm-provider"><img src="https://agentmods.dev/badge/skills/rhtevan/agentfs/hermes-litellm-provider.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 | $0.00021 | $0.01883 |
| Opus 5 | $0.00010 | $0.00941 |
| Sonnet 5 | $0.00004 | $0.00377 |
| Haiku 4.5 | $0.00002 | $0.00188 |
Grade A, and why
hermes-litellm-provider 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 9d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configure Hermes Agent with Local LiteLLM Proxy
Set up Hermes Agent (CLI and Desktop) to use a locally hosted LiteLLM
proxy as its custom LLM provider. The proxy is backed by Vertex AI
Claude models (no auth, http://127.0.0.1:4000).
Prerequisites
- Hermes Agent installed (
~/.hermes/) - LiteLLM proxy running locally (see skill
litellm-vertex-ai-proxy) - The proxy must be accessible at
http://127.0.0.1:4000(default port) - Python3 with
pyyamlinstalled (used byscripts/restore.sh)
Model Selection Architecture
Hermes stores the default model in three locations that must stay
in sync. There is no separate fast_model concept (unlike Goose).
| Field | Location | Purpose |
|---|---|---|
model.default |
Top-level in config.yaml |
Active default model |
providers.<name>.default_model |
Provider entry | Provider-level default |
providers.<name>.model |
Provider entry | Currently selected model |
The restore.sh script updates all three atomically.
Note:
hermes modelmay not persist changes toconfig.yaml. Usescripts/restore.shor direct file editing for reliable updates.
Reference Configuration
File: ~/.hermes/config.yaml (relevant sections only)
⚠️ Use this exact schema. Do NOT write from memory or improvise field names. Copy this template and substitute only the marked placeholders.
model:
base_url: http://127.0.0.1:4000/v1
default: claude-opus-4-6 # default model for conversation
provider: litellm-vertex-ai
key_env: HERMES_CUSTOM_LITELLM_VERTEX_AI_API_KEY
providers:
litellm-vertex-ai:
api: http://127.0.0.1:4000/v1
name: LiteLLM Vertex AI
discover_models: true
default_model: claude-opus-4-6 # must match model.default
base_url: http://127.0.0.1:4000/v1
model: claude-opus-4-6 # must match model.default
models:
claude-opus-4-6: {}
claude-sonnet-4-6: {}
claude-haiku-4-5: {}
key_env: HERMES_CUSTOM_LITELLM_VERTEX_AI_API_KEY
What ships with it
3 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.
- 9d ago First seen · 205 lines · 21 tokens per session scan A 9c179abc9330
hermes-litellm-provider is a skill published in the GitHub repository rhtevan/agentfs (2 stars, last pushed today), licensed Apache-2.0. It adds 21 tokens to every session and 1,883 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…