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 neXenio/bifrost-plugin --skill bifrost-gateway-essentialsgit clone --depth 1 https://github.com/neXenio/bifrost-pluginWrote 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/nexenio/bifrost-plugin/bifrost-gateway-essentials)<a href="https://agentmods.dev/skills/nexenio/bifrost-plugin/bifrost-gateway-essentials"><img src="https://agentmods.dev/badge/skills/nexenio/bifrost-plugin/bifrost-gateway-essentials.svg" alt="Measured on agentmods" 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 | $0.00956 |
| Opus 5 | $0.00064 | $0.00478 |
| Sonnet 5 | $0.00026 | $0.00191 |
| Haiku 4.5 | $0.00013 | $0.00096 |
Grade A, and why
bifrost-gateway-essentials scanned grade A with 0 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 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bifrost gateway essentials
This skill carries the operating rules for a Bifrost gateway in a form that does not depend on hooks. The plugin's SessionStart hook normally injects a richer, gateway-specific version of this at the top of every session — but hooks only run in the Claude Code CLI and in Claude Desktop's Code and Cowork tabs. On Desktop's Chat tab and on claude.ai web, nothing is injected, so this skill is the fallback. Its description is loaded on every surface whether or not the skill is invoked.
If you did get an injected bifrost context block this session, prefer it: it was generated from your actual gateway and names real servers, whereas this skill can only describe the shape.
The one thing that trips everyone up
Run /mcp to see what loaded. A gateway exposes upstream servers in two modes,
and the same gateway usually mixes both:
-
Flat tools — callable directly, namespaced
mcp__bifrost__<server>-<tool>(for examplemcp__bifrost__skills-skill_search). -
Code mode — most servers are not flat tools and never appear in your tool list. They are reached through the meta-tool
executeToolCode, which runs a short Starlark snippet:result = <server>.<tool>(param="value")
So a tool that does not exist in your tool list is weak evidence that the gateway
lacks the capability, and strong evidence that the capability is in code mode.
Discover what is there with listToolFiles(), then getToolDocs() / readToolFile()
for signatures. Confirm server names from that listing rather than guessing them.
/bifrost-code-mode covers this path in full.
Before non-trivial work
skill_search(query="<the task>", k=5), thenget_skill(name=...)to load a match. The gateway's skill library is the point of the gateway; searching it is cheap and skipping it is how work gets redone.memory_search(query="...", limit=6)for prior decisions and constraints.
After significant work
Store durable, privacy-safe facts only: memory_store(subject="...", text="..."),
with anything longer than a fact in body as markdown, and items=[...] to save
several at once.
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 · 77 lines · 128 tokens per session scan A a902abcca65c
bifrost-gateway-essentials is a skill published in the GitHub repository neXenio/bifrost-plugin (2 stars, last pushed 20d ago), licensed MIT. It adds 128 tokens to every session and 956 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
oatda-list-models
Use when the user wants to list available AI models from OATDA's 10+ providers. Filter by type (chat, image, video, audio) or by provider name, including speech, transcription, and translation models.
oatda-compare-models
Use when the user wants to compare outputs from multiple LLM models side-by-side in a single request. Sends one prompt to multiple providers (OpenAI, Anthropic, Google, DeepSeek, etc.) in parallel via OATDA's /api/v1/compare endpoint and returns each model's response. Triggers on "compare models", "which model is…
oatda-generate-image
Use when the user wants to generate images using AI models through OATDA's unified API. Supports DALL-E 3, GPT-Image-1, Google Imagen, MiniMax, Qwen, and xAI image models.
oatda-generate-speech
Use when the user wants to generate speech/audio from text using OATDA's unified audio API. MCP generatespeech returns a short-lived signed AUDIOURL (download with curl, no login). HTTP /api/v1/llm/speech returns a file via curl --output. Supports OpenAI TTS, xAI grok-tts, voiceovers, and accessibility audio.
oatda-generate-video
Use when the user wants to generate videos using AI models through OATDA's unified API. Supports MiniMax, Google Veo, Alibaba Wan, ZAI, and OpenAI Sora. Video generation is asynchronous.
oatda-video-ad-creator
Create a branded video ad for the user's own product using OATDA APIs (TTS voiceover + AI video hook clip), Remotion, and ffmpeg. Triggers on "create video", "make ad", "Werbevideo", "promo video", "video ad".