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 TokonoMix/tokonomix-council-mcp --skill tokonomix-gatewaygit clone --depth 1 https://github.com/TokonoMix/tokonomix-council-mcpWrote 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/tokonomix/tokonomix-council-mcp/tokonomix-gateway)<a href="https://agentmods.dev/skills/tokonomix/tokonomix-council-mcp/tokonomix-gateway"><img src="https://agentmods.dev/badge/skills/tokonomix/tokonomix-council-mcp/tokonomix-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/tokonomix/tokonomix-council-mcp/tokonomix-gateway"><img src="https://agentmods.dev/badge/skills/tokonomix/tokonomix-council-mcp/tokonomix-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 | $0.00098 | $0.04803 |
| Opus 5 | $0.00049 | $0.02402 |
| Sonnet 5 | $0.00020 | $0.00961 |
| Haiku 4.5 | $0.00010 | $0.00480 |
Grade B, and why
tokonomix-gateway scanned grade B with 2 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 12d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
r = requests.post( "https://tokonomix.ai/api/v1/images/edits", Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
r = requests.post( How it starts
The opening of the file, as written. The whole thing — 610 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tokonomix Gateway — Direct HTTP
One key. All providers. Every modality.
The Tokonomix gateway is an OpenAI-compatible (and Anthropic-compatible) AI
gateway that routes to Anthropic, OpenAI, Google, Mistral, xAI, Azure EU, and
open-weight models through a single tok_live_... API key. It also adds
multi-model consensus, EU data-residency routing, and live spend tracking on top
of the standard API surface.
When to use this skill vs the MCP
| Situation | Recommended approach |
|---|---|
| Building an app / agent framework / CI pipeline | This skill — direct HTTP |
| Using Claude Code, Cursor, Cline, or any MCP host | tokonomix-council-mcp (MCP tools) |
| Running an unattended backlog of tickets overnight | agents-never-sleep |
| Migrating an existing OpenAI app to multi-vendor | This skill — drop-in base_url swap |
| You need tool-calling + streaming simultaneously | /api/anthropic/v1/messages endpoint (below) |
Authentication
Every endpoint (except health probes) requires a Bearer token:
Authorization: Bearer tok_live_...
Get a key:
- Visit
https://tokonomix.ai/dashboard/keys(login or sign up first). - Or use the keyless onboarding via the MCP tools (
tokonomix_onboard).
Keys carry per-key settings: a default council, monthly spend cap, and optional restrictions on models/modes/regions. Set guardrails once on the key; they apply to every call.
Credentials are saved to ~/.tokonomix/credentials.json (mode 0600) by the MCP
onboarding flow. When both a file and TOKONOMIX_API_KEY env var are present, the
env var takes precedence.
OpenAI drop-in
Swap base_url in the OpenAI SDK. No other changes needed:
Python:
from openai import OpenAI
client = OpenAI(
base_url="https://tokonomix.ai/api/v1",
api_key="tok_live_...",
)
response = client.chat.completions.create(
model="claude-sonnet-4-6",
messages=[{"role": "user", "content": "Explain zero-knowledge proofs in 3 sentences."}],
)
print(response.choices[0].message.content)
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.
- 12d ago First seen · 610 lines · 98 tokens per session scan B eb7f91e746d9
tokonomix-gateway is a skill published in the GitHub repository TokonoMix/tokonomix-council-mcp (1 stars, last pushed 6d ago), licensed MIT. It adds 98 tokens to every session and 4,803 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
omni-compression
Configure RTK (command output), Caveman (prose), and stacked compression modes. Manage language packs, custom rules, and test prompt compression reducing tokens by 60–90%.
cli-compression
Configure and test prompt compression from the CLI. Manage RTK filters, Caveman rules, stacked compression modes, and preview compression output with real prompts.
9router-chat
Chat / code generation via 9Router 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 9Router.
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.
9router-stt
Speech-to-text via 9Router /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models. Use when the user wants to transcribe audio, convert speech to text, or get subtitles from audio files.
9router
Entry point for 9Router — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions 9Router, NINEROUTERURL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant capability…