Borrowing it
Nothing to install: this file belongs to quangdang46/openproxy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/quangdang46/openproxy/main/.agents/skills/openproxy-embeddings/SKILL.mdgit clone --depth 1 https://github.com/quangdang46/openproxyWrote 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/quangdang46/openproxy/openproxy-embeddings)<a href="https://agentmods.dev/skills/quangdang46/openproxy/openproxy-embeddings"><img src="https://agentmods.dev/badge/skills/quangdang46/openproxy/openproxy-embeddings/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/quangdang46/openproxy/openproxy-embeddings"><img src="https://agentmods.dev/badge/skills/quangdang46/openproxy/openproxy-embeddings.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 | $0.00128 | $0.05578 |
| Opus 5.5 | $0.00051 | $0.02231 |
| Sonnet 5.5 | $0.00026 | $0.01116 |
| Haiku 4.5 | $0.00013 | $0.00558 |
Grade A, and why
openproxy-embeddings scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 29d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS http://127.0.0.1:4623/health | jq '.status' How it starts
The opening of the file, as written. The whole thing — 450 lines — stays where its author put it; the contents beside it link to each section on GitHub.
openproxy-embeddings — vectors through /v1/embeddings
OpenProxy proxies embedding calls through one
OpenAI-shaped route, POST http://127.0.0.1:4623/v1/embeddings. The request is resolved to a
provider from the model field, checked against the embedding-adapter registry, and fanned
out with credential rotation on 401/403/429.
This skill covers:
- The request contract (
model,input,dimensions,encoding_format) - Which providers can serve embeddings, and their upstream URLs
- Registering a
custom-embeddingprovider node for a self-hosted / OpenAI-compatible server - Verifying an embedding provider is wired, end to end
Everything here is non-interactive and safe to run unattended.
0 · Preflight
Confirm the server is up and a key is available before touching anything:
curl -sS http://127.0.0.1:4623/health | jq '.status'
# → "ok"
export OPENPROXY_API_KEY="$(cat "$HOME/.openproxy/admin.key")"
# or mint a scoped one:
openproxy key add rag-embedder --auto
If the server is not running: openproxy server start --detach --no-open.
1 · The request contract
curl -sS http://127.0.0.1:4623/v1/embeddings \
-H "Authorization: Bearer $OPENPROXY_API_KEY" \
-H 'content-type: application/json' \
-d '{
"model": "openai/text-embedding-3-small",
"input": "the quick brown fox"
}' | jq '{object, n: (.data|length), dims: (.data[0].embedding|length), usage}'
Response shape is always OpenAI's, regardless of upstream:
{
"object": "list",
"data": [{ "object": "embedding", "index": 0, "embedding": [0.0023, -0.0119, …] }],
"model": "text-embedding-3-small",
"usage": { "prompt_tokens": 4, "total_tokens": 4 }
}
| Field | Required | Notes |
|---|---|---|
model |
yes | <provider>/<model-id>, or <node-prefix>/<model-id> for a custom node, or a registered alias. This field alone picks the provider — a provider field in the body is ignored by the handler. |
input |
yes | A string, an array of strings, an array of token-id arrays, or an array of token arrays. An empty array is valid and reaches the provider. |
dimensions |
no | Output vector width. See §2. |
encoding_format |
no | Defaults to float. An empty string is coerced to float. |
user |
no | Forwarded only to upstreams whose adapter keeps the caller body. |
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.
- 29d ago First seen · 450 lines · 128 tokens per session scan A c7b1e44b3949
openproxy-embeddings is a skill published in the GitHub repository quangdang46/openproxy (29 stars, last pushed 5d ago), licensed MIT. It adds 128 tokens to every session and 5,578 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-29.
Other skills, from other repositories
keirouter-embeddings
Generate vector embeddings via KeiRouter /v1/embeddings using OpenAI / Mistral / Cohere / Voyage / NVIDIA / AWS Bedrock and other embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
aio-rag-kit
Set up vector database collections, index content, and run semantic search via RAG pipelines using Qdrant and rag-kit (auto-installs if missing). Use for retrieval-augmented generation, similarity search over a knowledge base, or embedding content for meaning-based retrieval.
10router-embeddings
Generate vector embeddings via 10Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.