Bifrost is an AI gateway that gives applications one OpenAI-compatible API for accessing models from more than 23 providers. It is used to route model requests, handle provider failover and load balancing, and apply features such as caching, guardrails, and MCP gateway support.
Borrowing it
Nothing to install: this file belongs to maximhq/bifrost. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/maximhq/bifrost/dev/.claude/skills/add-pricing-field/SKILL.mdgit clone --depth 1 https://github.com/maximhq/bifrostWrote 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/maximhq/bifrost/add-pricing-field)<a href="https://agentmods.dev/skills/maximhq/bifrost/add-pricing-field"><img src="https://agentmods.dev/badge/skills/maximhq/bifrost/add-pricing-field/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/maximhq/bifrost/add-pricing-field"><img src="https://agentmods.dev/badge/skills/maximhq/bifrost/add-pricing-field.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00123 | $0.03981 |
| Opus 5.5 | $0.00049 | $0.01592 |
| Sonnet 5.5 | $0.00025 | $0.00796 |
| Haiku 4.5 | $0.00012 | $0.00398 |
Grade A, and why
add-pricing-field 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 18d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Pricing Field
Add a new per-model pricing field to Bifrost's cost engine so it is parsed from the upstream datasheet, persisted, billed correctly, overridable, and documented — with no silent gap.
The pricing engine has one source-of-truth shape (Options in framework/modelcatalog/datasheet/types.go)
that gets mechanically mirrored into ~8 other places. Missing any one of them produces a field that
looks wired (compiles, shows up in one API) but silently doesn't bill, doesn't survive the 24h
datasheet resync, or can't be overridden — so treat every step below as mandatory, not optional.
Before You Start
Ask (or infer from context) three things about the new field:
- Field name — the exact upstream datasheet JSON key (e.g.
cost_per_request,output_cost_per_image_above_8_and_8_pixels). This becomes the Go field name (PascalCase) and the DB column name (as-is, snake_case). - Semantics — what usage quantity does it multiply, and is it additive on top of another
cost (like a flat per-request surcharge) or does it replace/tier an existing rate (like a
pixel-threshold override)? This determines where in
cost.goit plugs in — read the existingcompute*Costfunctions for the closest analog before writing new logic. - Which request type(s) it applies to — drives which
compute*Costfunction to touch and the UI'srequestTypeGroupstagging. At the Go level this includescontainer(schemas. ContainerCreateRequest), but the override UI'sREQUEST_TYPE_GROUPSonly has 7 groups (chat/ text/responses, embedding, rerank, audio, image, video, ocr) — there is no dedicatedcontainergroup. A container-priced field (e.g.code_interpreter_cost_per_session) still needs arequestTypeGroupsentry in Step 9, so tag it onto the existing group it's conceptually closest to (that field uses"chat") rather than inventing an unsupported"container"value.
If any of these is unclear from the user's message, ask before writing code — silently guessing the billing semantics of a money field is the one mistake in this skill that isn't easily caught by tests.
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.
- 18d ago Changed 49bd7c721189
- 2mo ago First seen · 246 lines · 123 tokens per session scan A bf2cf0cc9efb
add-pricing-field is a skill published in the GitHub repository maximhq/bifrost (9,185 stars, last pushed today), licensed Apache-2.0. It adds 123 tokens to every session and 3,981 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
x402-job-budgets
Put an agent's x402 payments under a per-job budget with bounded shares for sub-agents. Use when an agent or its sub-agents pay for APIs, data or other agents with x402 (@x402/fetch, @x402/axios, @x402/core), share one wallet or payment client, run paid calls concurrently, or need each task or child agent capped…
inferrail-job-safe-search
Search the web through Inferrail with upfront x402 USDC payment, durable request IDs, job budgets, safe retry instructions, and a machine-readable receipt.
omni-budget
Configure spending limits, token quotas, and rate-limit policies per API key or globally. Inspect current consumption and enforce cost controls across providers.
unrelated-tools
Search, inspect, and call tools exposed through an Unrelated MCP Gateway profile using the unrelated CLI. Use when a task may be handled by an authorized Gateway tool, when the exact tool name or input schema is unknown, or when a compact client-side alternative to loading a full MCP catalog is desired.
unified-ai-gateway
Operate and evaluate Unified AI System through fifteen governed MCP tools, including provider-free prompt enhancement, while preserving fake-provider, authorization, and evidence boundaries.
gateway-usage
Check Cornell AI Gateway (LiteLLM) key spend and remaining budget from live response headers. Use when asked about API usage, gateway spend, cost, or remaining budget.