openproxy: Skill for Claude Code

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

openproxy-stt is a skill for Claude Code, Codex from quangdang46/openproxy. It costs 99 tokens per session (5,174 once invoked), scanned A, original, MIT.

A guide for transcribing audio through OpenProxy, a service that routes requests to speech-to-text providers. Speech-to-text means converting spoken audio into written text.

In plain words
What is it for?
It is for sending audio to OpenProxy's transcription API or command-line tool and receiving its written transcript.
Why use it?
It removes the need to handle different request formats, providers, and fallback credentials separately.

Skill for Claude CodeCodex

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

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-stt/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-stt

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/quangdang46/openproxy/openproxy-stt"><img src="https://agentmods.dev/badge/skills/quangdang46/openproxy/openproxy-stt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,174 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 $0.00099 $0.05174
Opus 5.5 $0.00040 $0.02070
Sonnet 5.5 $0.00020 $0.01035
Haiku 4.5 $0.00010 $0.00517

Measured 29d ago against content hash e27c5c429023, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

openproxy-stt 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
.agents/skills/openproxy-stt/SKILL.md · 393 lines

How it starts

The opening of the file, as written. The whole thing — 393 lines — stays where its author put it; the contents beside it link to each section on GitHub.

openproxy — speech-to-text

OpenProxy transcribes audio on one OpenAI-compatible endpoint and routes it to whichever credentialed STT provider owns the requested model. This skill covers:

  1. Probing the server and confirming the route exists
  2. Registering an STT provider credential
  3. Transcribing over POST /v1/audio/transcriptions (multipart and JSON shapes)
  4. Transcribing from the CLI
  5. Reading the per-provider response shapes
  6. Verifying the whole thing end to end

Everything here is non-interactive and copy-pasteable.

0 · Detect what's already running

Do this before mutating anything:

command -v openproxy && openproxy --version || echo "not installed"
openproxy --robot server status 2>/dev/null || echo "server not running"
curl -sS http://127.0.0.1:4623/health

If the server is not up, start it detached and headless:

openproxy server start --detach --no-open
curl -sS http://127.0.0.1:4623/v1 | jq .endpoints

/v1 advertises /v1/audio/transcriptions in its endpoint list. If it is not there, the binary is older than this skill — upgrade before continuing.

Capture the admin key once and reuse it. /v1/* is gated on settings.requireLogin, which defaults to on, so the bearer is required unless the user has deliberately turned it off:

openproxy key add <NAME> --auto
# Or pass your own secret positionally: openproxy key add <NAME> '<SECRET>'
# If no key exists yet, capture the one-shot admin key from:
openproxy --robot server init | jq -r '.data.admin_key.key'
# Or recover the dashboard password for a running server:
openproxy auth reset-password --show

The bearer may be the admin key from server init or any proxy key minted with openproxy key add. Both work on /v1/audio/transcriptions.

1 · Register an STT provider

STT providers are provider connections tagged with mediaType: "stt". Add one through the media-providers API, which encrypts the key on the way into the database:

curl -sS -X POST http://127.0.0.1:4623/api/media-providers \
  -H "Authorization: Bearer $OPENPROXY_API_KEY" \
  -H 'content-type: application/json' \
  -d '{
        "name": "openai-stt",
        "provider": "openai",
        "apiKey": "sk-...",
        "mediaType": "stt"
      }'

Read the full file on GitHub · 393 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 · 393 lines · 99 tokens per session scan A e27c5c429023

Subscribe to this mod's changes

openproxy-stt is a skill published in the GitHub repository quangdang46/openproxy (29 stars, last pushed 5d ago), licensed MIT. It adds 99 tokens to every session and 5,174 once invoked, about $0.0004 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