What is bifrost-onboard?

A setup guide for connecting Claude Code to a Bifrost MCP gateway, which is a shared gateway for accessing MCP servers. It covers the gateway address, personal key, installation, environment variables, and connection checks.

Use it when installing Bifrost in Claude Code, registering the gateway, saving its environment variables, restarting the client, and confirming that memory and skill discovery work.

It turns the first-time connection process into a defined sequence and explains which settings must persist between sessions. This reduces setup errors caused by missing credentials or an unconfigured client.

bifrost-onboard — Skill for Claude Code by neXenio

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add neXenio/bifrost-plugin

Claude Code

/plugin install bifrost-plugin

Made for: Claude Code.

Or install bifrost-plugin, the plugin that ships this one along with the rest of its 5 skills, 5 commands, 5 hooks, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nexenio/bifrost-plugin/bifrost-onboard/github.svg)](https://agentmods.dev/skills/nexenio/bifrost-plugin/bifrost-onboard)

Your own site

<a href="https://agentmods.dev/skills/nexenio/bifrost-plugin/bifrost-onboard"><img src="https://agentmods.dev/badge/skills/nexenio/bifrost-plugin/bifrost-onboard/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nexenio/bifrost-plugin/bifrost-onboard"><img src="https://agentmods.dev/badge/skills/nexenio/bifrost-plugin/bifrost-onboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,212 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 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.

Model	Per session	Once invoked
Fable 5.1	$0.00073	$0.01212
Opus 5	$0.00036	$0.00606
Sonnet 5	$0.00015	$0.00242
Haiku 4.5	$0.00007	$0.00121

Measured 8d ago against content hash 6d2140bc41fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

bifrost-onboard scanned grade B 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 8d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

grep -q "## Skill Discovery" ~/.claude/CLAUDE.md \

skills/bifrost-onboard/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bifrost Onboarding

Walk through full Bifrost setup in Claude Code (steps 1–5), then optionally Claude Desktop (step 6).

Step 1 — Get your gateway URL and virtual key

Ask your gateway operator for two values:

The gateway /mcp endpoint URL → BIFROST_URL
Your personal virtual key (vk_…) → BIFROST_VK

Step 2 — Run the installer

From the plugin root (or use the slash command — see below):

export BIFROST_URL=https://<your-gateway-host>/mcp
node "${CLAUDE_PLUGIN_ROOT}/bin/install.js" --key vk_<your-key>

The installer:

Registers the bifrost MCP server via claude mcp add --scope user (idempotent — re-running replaces the same entry; it never edits config files directly).
Without --key, stores the ${BIFROST_VK} runtime template. It does NOT modify your shell profile — you must add export BIFROST_VK=… to ~/.zshrc (or ~/.bashrc) yourself for the key to persist across sessions.

Or run the slash command from inside Claude Code (same installer):

/bifrost-setup

Step 3 — Persist the env vars, then restart Claude Code

Add the export lines to your shell profile so they survive new shells:

echo 'export BIFROST_URL=https://<your-gateway-host>/mcp' >> ~/.zshrc   # or ~/.bashrc
echo 'export BIFROST_VK=vk_<your-key>' >> ~/.zshrc
source ~/.zshrc

Then restart CC so the MCP server and hooks are loaded.

macOS note: Claude Code launched from the Dock or Spotlight does NOT inherit ~/.zshrc exports. Launch CC from a terminal (open from a shell, or run the claude CLI), or set the env vars via a launchd plist, otherwise the gateway sees no key.

Step 4 — Smoke check

Run these checks to confirm everything is live:

MCP loaded: type /mcp — bifrost should appear in the server list.
Skill search works: if your gateway exposes a skill server, call mcp__bifrost__<skills-server>-skill_search with "test connection" — should return results.
Memory tools: if your gateway exposes a memory server, call its search tool (mcp__bifrost__<memory-server>-search) with a short query — should return results or an empty list.
Session context: open a new session — the bifrost context block should appear at the top.

Read the full file on GitHub · 108 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.

8d ago First seen · 108 lines · 73 tokens per session scan B 6d2140bc41fe

Subscribe to this mod's changes

bifrost-onboard is a skill published in the GitHub repository neXenio/bifrost-plugin (2 stars, last pushed 20d ago), licensed MIT. It adds 73 tokens to every session and 1,212 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Claude Code ai-gateway anthropic bifrost claude claude-code-plugin

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.

devcsde/oatda-skills · 50 tokens

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.

devcsde/oatda-skills · 52 tokens

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…

devcsde/oatda-skills · 107 tokens

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.

devcsde/oatda-skills · 53 tokens

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.

devcsde/oatda-skills · 84 tokens

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".

devcsde/oatda-skills · 64 tokens

bifrost-onboard