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.
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 agentmods add skills/maximhq/bifrost/helm-updatenpx skills add maximhq/bifrost --skill helm-updategit 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/helm-update)<a href="https://agentmods.dev/skills/maximhq/bifrost/helm-update"><img src="https://agentmods.dev/badge/skills/maximhq/bifrost/helm-update.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 | $0.00097 | $0.02090 |
| Opus 5 | $0.00048 | $0.01045 |
| Sonnet 5 | $0.00019 | $0.00418 |
| Haiku 4.5 | $0.00010 | $0.00209 |
Grade A, and why
helm-update scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Helm Update
Apply changes to the Bifrost Helm chart, keep it in sync with config.schema.json, and update all changelogs.
Key File Paths
| File | Path |
|---|---|
| Config schema | transports/config.schema.json |
| Chart metadata | helm-charts/bifrost/Chart.yaml |
| Values | helm-charts/bifrost/values.yaml |
| Values schema | helm-charts/bifrost/values.schema.json |
| Helpers template | helm-charts/bifrost/templates/_helpers.tpl |
| Helm README | helm-charts/bifrost/README.md |
| Docs changelogs | docs/changelogs/helm-v<version>.mdx |
| Docs navigation | docs/docs.json |
Workflow
Step 1: Gather Current State
Read the current helm chart version and identify the last helm release commit:
# Current helm chart version
cat helm-charts/bifrost/Chart.yaml | grep '^version:'
# Latest docs helm changelog (= last released version)
ls -1t docs/changelogs/helm-v*.mdx | head -1
# Find the commit that added the latest helm changelog
LAST_HELM_MDX=$(ls -1t docs/changelogs/helm-v*.mdx | head -1)
git log --oneline -- "$LAST_HELM_MDX" | head -1
Save the last-release commit SHA — you'll need it to scope the config.schema.json diff.
Step 2: Check config.schema.json Changes Since Last Helm Release
LAST_COMMIT=$(git log --oneline -- "$(ls -1t docs/changelogs/helm-v*.mdx | head -1)" | awk '{print $1}')
# What changed in config.schema.json since then?
git diff ${LAST_COMMIT}..HEAD -- transports/config.schema.json
Identify any fields added, removed, or changed in config.schema.json that are not yet reflected in the helm chart. These are gaps that must be closed — even if the user did not explicitly ask for them. Note each gap; you will apply them alongside the user's requested changes.
Step 3: Apply User-Requested Changes + Fill Gaps
For every change (user-requested AND schema gaps detected in Step 2):
values.yaml
Add new fields as commented-out blocks with a realistic sample value. Place new sections near related existing fields. Keep existing uncommented defaults intact.
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.
- 6d ago First seen · 230 lines · 97 tokens per session scan A e1b9cfd6e283
helm-update is a skill published in the GitHub repository maximhq/bifrost (7,809 stars, last pushed today), licensed Apache-2.0. It adds 97 tokens to every session and 2,090 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
portainer-mcp-hygiene
How to drive the Portainer MCP server's tools correctly — both reading and mutating. Reading: project responses with select (JMESPath), where the heavy fields live (snapshots, status blocks, managed fields), how to handle non-JSON Docker/K8s proxy endpoints (container and pod logs, stats, exec), and how to interpret…
portainer-mcp-release
How to cut a portainer-mcp release that bumps the embedded Portainer OpenAPI spec to a new Portainer minor (e.g. 2.41.x → 2.42.x). Walks through finding the upstream patch target, regenerating the spec, recounting ops/tags per profile, refreshing the orphan-tag inventory, bumping version pins across the README and…
documentation-lookup
This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.
Sandbox Isolation
Run untrusted or risky commands in Docker-based sandbox with resource limits and network isolation.
devcontainer-dev
Spin up and interact with ToolHive Studio's containerized dev environment (Xvfb + noVNC + DinD). Use when running, testing, or debugging the app in isolation — locally, in a git worktree, or in GitHub Codespaces; when touching .devcontainer/, scripts/devcontainer-.sh, or the devContainer:dev npm script; or when…
docker
Docker container management.