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/docs-writer/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/docs-writer)<a href="https://agentmods.dev/skills/maximhq/bifrost/docs-writer"><img src="https://agentmods.dev/badge/skills/maximhq/bifrost/docs-writer/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/docs-writer"><img src="https://agentmods.dev/badge/skills/maximhq/bifrost/docs-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Tool Misuse · line 217 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
- medium Data Exfiltration · line 347 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00083 | $0.07984 |
| Opus 5.5 | $0.00033 | $0.03194 |
| Sonnet 5.5 | $0.00017 | $0.01597 |
| Haiku 4.5 | $0.00008 | $0.00798 |
Grade A, and why
docs-writer 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 2mo 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.
- API examples with curl commands How it starts
The opening of the file, as written. The whole thing — 861 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bifrost Documentation Writer
Write, update, and review Mintlify MDX documentation for Bifrost features. Performs thorough codebase research across both the React UI and Go backend, validates config.json examples against the schema, and follows established documentation conventions.
Usage
/docs-writer <feature-name> # Write new docs for a feature
/docs-writer update <doc-path> # Update an existing doc page
/docs-writer review <doc-path> # Review a doc for accuracy and completeness
Workflow Overview
- Understand the request -- Determine which feature needs documentation
- Research the codebase -- Explore UI pages, Go handlers, config schema, and existing docs
- Research external context -- Use Context7 and WebSearch for additional information
- Ask clarifying questions -- Confirm scope, audience, and edge cases with the user
- Present doc outline -- Show a structured outline and wait for approval
- Write the documentation -- Create the MDX file following Mintlify conventions
- Update navigation -- Add the new page to docs.json
- Present for review -- Show the complete doc and incorporate feedback
Step 1: Understand the Request
For new docs (/docs-writer <feature-name>)
Parse the feature name and map it to codebase areas. Common feature-to-directory mappings:
| Feature Name | UI Directory | Handler File | Config Schema Section | Existing Docs |
|---|---|---|---|---|
| virtual-keys | ui/app/workspace/virtual-keys/ |
handlers/governance.go |
governance.virtual_keys |
docs/features/governance/virtual-keys.mdx |
| routing | ui/app/workspace/routing-rules/ |
handlers/governance.go |
governance.routing_rules |
docs/features/governance/routing.mdx |
| providers | ui/app/workspace/providers/ |
handlers/providers.go |
providers |
docs/providers/ |
| mcp | ui/app/workspace/mcp-registry/ |
handlers/mcp.go |
mcp |
docs/mcp/ |
| plugins | ui/app/workspace/plugins/ |
handlers/plugins.go |
plugins |
docs/features/plugins/ |
| logs / observability | ui/app/workspace/logs/ |
handlers/logging.go |
client.enable_logging |
docs/features/observability/ |
| semantic-caching | ui/app/workspace/config/caching/ |
handlers/cache.go |
plugins.semantic_cache + vector_store |
docs/features/semantic-caching.mdx |
| guardrails | ui/app/workspace/guardrails/ |
Enterprise | guardrails_config |
docs/enterprise/guardrails.mdx |
| clustering | ui/app/workspace/cluster/ |
Enterprise | cluster_config |
docs/enterprise/clustering.mdx |
| load-balancing | ui/app/workspace/adaptive-routing/ |
Enterprise | load_balancer_config |
docs/enterprise/adaptive-load-balancing.mdx |
| audit-logs | ui/app/workspace/audit-logs/ |
Enterprise | audit_logs |
docs/enterprise/audit-logs.mdx |
| rbac | ui/app/workspace/rbac/ |
Enterprise | auth_config |
docs/enterprise/rbac.mdx |
| config | ui/app/workspace/config/ |
handlers/config.go |
client |
docs/quickstart/ |
| budget-and-limits | ui/app/workspace/virtual-keys/ |
handlers/governance.go |
governance.budgets, governance.rate_limits |
docs/features/governance/budget-and-limits.mdx |
| mcp-tools | ui/app/workspace/mcp-tool-groups/ |
handlers/governance.go |
governance.virtual_keys[].mcp_configs |
docs/features/governance/mcp-tools.mdx |
| fallbacks | N/A (request-level) | handlers/inference.go |
N/A | docs/features/fallbacks.mdx |
| telemetry | ui/app/workspace/observability/ |
handlers/plugins.go |
plugins.prometheus, plugins.otel |
docs/features/telemetry.mdx |
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.
- 2mo ago First seen · 861 lines · 83 tokens per session scan A 1d9d08c32907
docs-writer is a skill published in the GitHub repository maximhq/bifrost (9,185 stars, last pushed today), licensed Apache-2.0. It adds 83 tokens to every session and 7,984 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
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.
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.
cli-eval
Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.
omni-mcp
Connect to the OmniRoute MCP server (110 tools, 3 transports: SSE/stdio/HTTP). Covers routing, cache, compression, memory, skills, providers, and audit tools across 33 permission scopes.