openproxy: Skill for Claude Code

.agents/skills/openproxy-combos/SKILL.md

openproxy-combos is a skill for Claude Code, Codex from quangdang46/openproxy. It costs 82 tokens per session (6,295 once invoked), scanned A, original, MIT.

A guide for creating and using OpenProxy combos: ordered lists of AI providers and models tried in sequence. Combos can provide fallback or distribute requests in a round-robin pattern.

In plain words
What is it for?
Use it to create, edit, test, list, delete, and dispatch combos, including using one as the model in a chat-completions request.
Why use it?
It avoids manually handling provider failures or switching models when a service returns an error. It also helps diagnose failed combo requests.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents); mentions Codex.

This is quangdang46/openproxy's own configuration. It tells Claude Code and Codex how to work on openproxy itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything openproxy configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/quangdang46/openproxy/main/.agents/skills/openproxy-combos/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/quangdang46/openproxy

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for openproxy-combos

README.md
[![agentmods](https://agentmods.dev/badge/skills/quangdang46/openproxy/openproxy-combos/github.svg)](https://agentmods.dev/skills/quangdang46/openproxy/openproxy-combos)
Your own site
<a href="https://agentmods.dev/skills/quangdang46/openproxy/openproxy-combos"><img src="https://agentmods.dev/badge/skills/quangdang46/openproxy/openproxy-combos/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.

agentmods 80×15 button for openproxy-combos

Your own site · 80×15
<a href="https://agentmods.dev/skills/quangdang46/openproxy/openproxy-combos"><img src="https://agentmods.dev/badge/skills/quangdang46/openproxy/openproxy-combos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,295 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00082 $0.06295
Opus 5.5 $0.00033 $0.02518
Sonnet 5.5 $0.00016 $0.01259
Haiku 4.5 $0.00008 $0.00630

Measured 29d ago against content hash 8be489d278a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

openproxy-combos 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.

| Declarating many combos at once | `openproxy combo apply --from-file` against a stopped server, or the REST API via curl |
.agents/skills/openproxy-combos/SKILL.md · 564 lines

How it starts

The opening of the file, as written. The whole thing — 564 lines — stays where its author put it; the contents beside it link to each section on GitHub.

openproxy-combos — build and operate fallback chains

A combo is a named, ordered list of <provider>/<model> entries that OpenProxy dispatches as a single model. It is the router's failover unit: a client sends one model name, the combo walks the list, and the first member that answers wins.

Combos are one of two core data types (alongside providers). They are stored in the data dir, edited from /dashboard/combos, and are first-class entries in GET /v1/models.

Everything below was verified against the source in this repo. Where OpenProxy deliberately diverges from the 9router reference, the divergence is called out and docs/parity-9router.md is cited.

0 · Decide CLI or REST first

This is the one decision that trips people up, so settle it before writing anything.

openproxy combo … is a local-only command. src/cli/mod.rs handles Command::Combo by calling Db::load() and handing the DB straight to combo::run — it never consults --url / --api-key. Two consequences, both confirmed by running the binary:

  • openproxy combo create --url http://127.0.0.1:4623 --api-key $KEY writes to the local data dir, not to the server. The server's /api/combos stays empty. --url is silently ignored.
  • A combo created with the CLI while a server is running is invisible to that server — absent from /api/combos and from GET /v1/models — until the server is restarted and reloads the data dir.
Situation Use
No server running, or you are about to restart one openproxy combo … CLI
A server is already running REST API (/api/combos) — the only path that goes through the live process
Declarating many combos at once openproxy combo apply --from-file against a stopped server, or the REST API via curl

If you have already used the CLI against a live server, restart it:

openproxy server stop && openproxy server start --detach --no-open

1 · What a combo record looks like

The stored record (Combo in src/types/mod.rs) is camelCase on the wire, with the extras flattened into the top level:

Read the full file on GitHub · 564 lines

Changes

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.

  1. 29d ago First seen · 564 lines · 82 tokens per session scan A 8be489d278a0

Subscribe to this mod's changes

openproxy-combos is a skill published in the GitHub repository quangdang46/openproxy (29 stars, last pushed 5d ago), licensed MIT. It adds 82 tokens to every session and 6,295 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

implementing-api-schema-validation-security

Implement API schema validation using OpenAPI specifications and JSON Schema to enforce input/output contracts and prevent injection, data exposure, and mass assignment attacks.

xalgorix/xalgorix · 35 tokens

keirouter-chat

Chat / code generation via KeiRouter using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming + auto-fallback combos. Use when the user wants to ask an LLM, generate code, summarize text, or run prompts through KeiRouter.

mydisha/keirouter · 62 tokens

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.

mydisha/keirouter · 70 tokens

10router

Entry point for 10Router — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions 10Router, TENROUTERURL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant capability…

techysy/10router · 83 tokens

post-processing

Extract, analyze, and summarize simulation output data — pull spatial fields at specific timesteps, compute time-series trends and detect steady state, extract line profiles through the domain, generate statistical summaries and distributions, calculate derived quantities (gradients, fluxes, volume fractions…

HeshamFS/materials-simulation-skills · 130 tokens

linear-solvers

Select and configure linear solvers for Ax=b systems arising in numerical simulations — choose between direct (LU, Cholesky) and iterative (CG, GMRES, BiCGSTAB, MINRES) methods, analyze sparsity patterns and matrix conditioning, recommend preconditioners (AMG, ILU, IC), apply row/column scaling, and diagnose…

HeshamFS/materials-simulation-skills · 140 tokens