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 davidtoby/agent-skills --skill hermes-agent-litellm-vertex-gatewaygit clone --depth 1 https://github.com/davidtoby/agent-skillsWrote 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/davidtoby/agent-skills/hermes-agent-litellm-vertex-gateway)<a href="https://agentmods.dev/skills/davidtoby/agent-skills/hermes-agent-litellm-vertex-gateway"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/hermes-agent-litellm-vertex-gateway/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/davidtoby/agent-skills/hermes-agent-litellm-vertex-gateway"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/hermes-agent-litellm-vertex-gateway.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 | $0.00070 | $0.01303 |
| Opus 5 | $0.00035 | $0.00651 |
| Sonnet 5 | $0.00014 | $0.00261 |
| Haiku 4.5 | $0.00007 | $0.00130 |
Grade A, and why
hermes-agent-litellm-vertex-gateway scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -H "Authorization: Bearer <LITELLM_MASTER_KEY>" http://127.0.0.1:4000/v1/models How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hermes Agent — Connect to Local LiteLLM Vertex Proxy
让 Hermes Agent 连接到本地已有的 LiteLLM Vertex Proxy,以使用 Gemini 模型,不影响现有配置。
Situation
本地已部署 LiteLLM Vertex Proxy(http://127.0.0.1:4000),现在需要让 Hermes Agent 在不更改当前配置的情况下,多一个调用本地 Gemini 的选项,并支持临时切换。
Prerequisites
- LiteLLM Vertex Proxy 已运行在
127.0.0.1:4000 - Proxy 已配置
LITELLM_MASTER_KEY - 至少一个 Gemini 模型已暴露(通过
GET /v1/models可验证) - Hermes Agent 已安装并运行在
~/.hermes/
Step 1 — Verify the LiteLLM Proxy
在配置 Hermes 之前,先验证 proxy 可用:
# 1. 检查端口监听
lsof -nP -iTCP:4000 -sTCP:LISTEN
# 2. 获取 master key(从 proxy 项目目录的 .env)
grep LITELLM_MASTER_KEY ~/GitHub-Codebase/litellm-vertex-proxy/.env
# 3. 验证 /v1/models 可访问
curl -s -H "Authorization: Bearer <LITELLM_MASTER_KEY>" http://127.0.0.1:4000/v1/models
# 4. 确认可用模型名
curl -s -H "Authorization: Bearer <LITELLM_MASTER_KEY>" http://127.0.0.1:4000/v1/models \
| python3 -c "import sys,json; d=json.load(sys.stdin); [print(m['id']) for m in d.get('data',[])]"
输出类似:
gemini-3.1-pro-preview
Step 2 — Locate Hermes Config
~/.hermes/config.yaml
Step 3 — Add the Provider and Model to config.yaml
# 备份
cp ~/.hermes/config.yaml ~/.hermes/config.yaml.bak.$(date +%Y%m%d%H%M%S)
编辑 ~/.hermes/config.yaml,替换顶部的 model: 和 providers: 块:
model:
default: gpt-5.4 # 保持原有默认不变
provider: openai-codex # 保持原有默认不变
base_url: https://chatgpt.com/backend-api/codex
providers:
local-litellm:
name: local-litellm
base_url: http://127.0.0.1:4000
api_key: <LITELLM_MASTER_KEY>
models:
- gemini-3.1-pro-preview
⚠️
<LITELLM_MASTER_KEY>替换为实际值,从~/GitHub-Codebase/litellm-vertex-proxy/.env中读取。 不要把这个 key 打印到聊天里。
Step 4 — Restart Hermes Gateway
# 方式 A:如果是 Hermes Agent 运行在终端
# 按 Ctrl+C 停止,然后重新启动
# 方式 B:如果是通过 launchd/systemd 运行
# 查找并重启对应服务
launchctl list | grep hermes
# 或
ps aux | grep hermes
Step 5 — Verify the Connection
# 在 Hermes 对话中发送:
/model local-litellm/gemini-3.1-pro-preview
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.
- 7d ago First seen · 163 lines · 70 tokens per session scan A 9d43077a3fe9
hermes-agent-litellm-vertex-gateway is a skill published in the GitHub repository davidtoby/agent-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 1,303 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
agentphone
Build AI phone agents with AgentPhone API. Use when the user wants to make phone calls, send/receive SMS, manage phone numbers, create voice agents, set up webhooks, or check usage — anything relate.
better-auth
Self-hosted auth for TypeScript/Cloudflare Workers with social auth, 2FA, passkeys, organizations, RBAC, and 15+ plugins. Requires Drizzle ORM or Kysely for D1 (no direct adapter). Self-hosted alternative to Clerk/Auth.js. Use when: self-hosting auth on D1, building OAuth provider, multi-tenant SaaS, or…
ai-sdk-core
Build backend AI with Vercel AI SDK v6 stable. Covers Output API (replaces generateObject/streamObject), speech synthesis, transcription, embeddings, MCP tools with security guidance. Includes v4→v5 migration and 15 error solutions with workarounds. Use when: implementing AI SDK v5/v6, migrating versions…
api-security-best-practices
Implement secure API design patterns including authentication, authorization, input validation, rate limiting, and protection against common API vulnerabilities.
backend-patterns
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
API Fuzzing for Bug Bounty
This skill should be used when the user asks to "test API security", "fuzz APIs", "find IDOR vulnerabilities", "test REST API", "test GraphQL", "API penetration testing", "bug bounty API testing", or needs guidance on API security assessment techniques.