frontier-models SKILL.md skillB

frontier-models from sunflowerslwtech/sunkit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add sunflowerslwtech/sunkit/frontier-models@git:20261116.c3d1e03

Pins git:20261116.c3d1e03 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
sunflowerslwtech/sunkit
Path
plugins/frontier/skills/frontier-models/SKILL.md
Versions recorded
4
Latest version
git:20261116.c3d1e03, committed Nov 16, 2026
First version recorded
Oct 25, 2026
Size
5,131 bytes
Repository stars
15
License
Apache-2.0

The models and harnesses this machine can reach beyond its own Claude seat, and how to use them. Covers the magpie gateway (llm-gateway) and its routing groups, switching a claude-gw session to GPT-6.1 Sol, Grok 4.7, Kimi, GLM, DeepSeek, Qwen or Doubao, and the subagents agy-pro, agy-trial, zen, zcode and frontier. Fires on 「用 GPT/Grok/Gemini/GLM/Kimi/DeepSeek/Qwen」「换个模型」「有哪些模型」「magpie」「网关」「路由组」「降级」「让 Antigravity/OpenCode/ZCode 做」「出图」「看视频」, "which models can I use", "ask GPT…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Frontier models and harnesses

Plain `claude` talks to Anthropic on this machine's Claude seat. Everything else goes through one of two doors.

## 1. The magpie gateway: other models inside Claude Code

`claude-gw` starts a Claude Code session on the gateway (llm-gateway, `http://100.116.218.86:3425`; this machine's key is in `~/.claude/magpie-settings.json`). The `/model` picker in a claude-gw session lists the frontier rows below; `/model <id>` takes any id `harness-run models` prints.

Routing groups (magpie `routing=order`, `stays=session`: one member per session for the prompt cache, the next member when it fails or runs out):

| id | chain |
|---|---|
| `claude-opus-5-5` (Opus row, claude-gw's default) | Opus 5.5 on the three Claude Team seats → Kiro Opus 5.5 → `claude-sonnet-5-5` |
| `claude-sonnet-5-5` | Sonnet 5.5 on the seats → Zed Sonnet 5.5 → Kiro Sonnet 5.5 → `frontier` |
| `claude-haiku-5-5` | Haiku 5.5 on the seats → Zed Haiku 5.5 → Kiro Haiku 5.5 → DeepSeek V4.1 Flash → GLM-5.3 Flash → Go Haiku |
| `claude-fable-5-1` | `claude-opus-5-5` (no Fable on the gateway) |
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_uouer3n262tr4do4/33530b646707db058cf8a2058aecdf12d169f61e0d007c53d42f729de167a6b9.json

Then /plugin install frontier-models@markdownregistry-uouer3n262tr4do4 in Claude Code. It installs git:20261116.c3d1e03, the one graded B here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add sunflowerslwtech/sunkit/frontier-models@sha256:33530b646707db05

The line at the top of this page pins the label git:20261116.c3d1e03, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_uouer3n262tr4do4.svg)](https://markdownregistry.com/a/art_uouer3n262tr4do4)

5 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in sunflowerslwtech/sunkit/frontier-models since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of frontier-models from somewhere else? Ask it: where did my frontier-models come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 4 versions of this file, between Oct 25, 2026 and Nov 16, 2026, about one every 8 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261116.c3d1e03 latest2026-11-16 c3d1e03 5,131 BB view · diff
git:20261025.38ad4c82026-10-25 38ad4c8 5,128 BB view · diff
git:20261025.e73645a2026-10-25 e73645a 4,913 BB view · diff
git:20261025.9ed5c2d2026-10-25 9ed5c2d 4,381 BB view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No link to a raw IP address (matched: http://100.116.218.86:3425)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5131 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

sunflowerslwtech/sunkit · 15 stars · license Apache-2.0 · pushed 2026-11-17 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_uouer3n262tr4do4
GET https://markdownregistry.com/api/v1/resolve?ref=sunflowerslwtech/sunkit/frontier-models
GET https://markdownregistry.com/api/v1/blob/33530b646707db058cf8a2058aecdf12d169f61e0d007c53d42f729de167a6b9

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from sunflowerslwtech/sunkit

CLAUDE.md@mesh CLAUDE.md file
sunflowerslwtech/sunkit · mesh/CLAUDE.md
git:20261020.b205121 · audit A · 15 stars
brief-pdf SKILL.md skill
sunflowerslwtech/sunkit · plugins/brief-pdf/skills/brief-pdf/SKILL.md · Build a polished A4 brief PDF — company/product brief, program application, proposal, one-pager — from an HTML source…
git:20261111.6e1da0d · audit A · 15 stars
cua SKILL.md skill
sunflowerslwtech/sunkit · plugins/cua/skills/cua/SKILL.md · Single entry point for operating any GUI: desktop windows, browsers, Electron apps, dialogs, iOS/Android simulators…
git:20261111.7cff732 · audit A · 15 stars
macos-harness SKILL.md skill
sunflowerslwtech/sunkit · plugins/cua/skills/macos-harness/SKILL.md · Documentation skill for the browser-use/macos-harness CLI (MIT, v0.1.x) — whole-Mac control from one persistent…
git:20261111.7cff732 · audit B · 15 stars
phone-use SKILL.md skill
sunflowerslwtech/sunkit · plugins/cua/skills/phone-use/SKILL.md · The one manual for phones and emulators, companion detail skill of the `cua` router: Android emulator/phone via adb +…
git:20261111.7cff732 · audit B · 15 stars
loopify-requirements SKILL.md skill
sunflowerslwtech/sunkit · plugins/loopify-requirements/skills/loopify-requirements/SKILL.md · Convert prompts, vague tasks, product requirements, coding requests, research plans, monitors, reminders, and agent…
git:20260717.efb18ef · audit A · 15 stars
obsidian-wiki SKILL.md skill
sunflowerslwtech/sunkit · plugins/obsidian-wiki/skills/obsidian-wiki/SKILL.md · Use the user's Obsidian vault as the agent's long-term memory: recall what is already known BEFORE answering, write…
git:20261111.4625af9 · audit A · 15 stars
polanyi-design SKILL.md skill
sunflowerslwtech/sunkit · plugins/polanyi-design/skills/polanyi-design/SKILL.md · Frontend design cognitive system grounded in Michael Polanyi's tacit knowledge theory. Surfaces expert-level visual…
git:20260717.788a6cd · audit A · 15 stars
polanyi-enhanced SKILL.md skill
sunflowerslwtech/sunkit · plugins/polanyi-design/skills/polanyi-design/research-origin/skill/SKILL.md · Cognitive operating system for software engineering and design, based on Michael Polanyi's tacit knowledge framework…
git:20260717.788a6cd · audit A · 15 stars
search-harness SKILL.md skill
sunflowerslwtech/sunkit · plugins/search-harness/skills/search-harness/SKILL.md · Domain knowledge for designing a search harness for coding agents — search API landscape, ground-API pipeline/strategy…
git:20260717.cde2bc3 · audit A · 15 stars
anysearch SKILL.md skill
sunflowerslwtech/sunkit · plugins/search/skills/anysearch/SKILL.md · Detail doc assigned by the `search` router — AnySearch CLI: structured vertical data across 40 sub_domains (quotes…
v3.1.1 · audit A · 15 stars
exa-agent SKILL.md skill
sunflowerslwtech/sunkit · plugins/search/skills/exa-agent/SKILL.md · Detail doc assigned by the `search` router — Exa Agent (`agent_run`, usage-billed): multi-step research, list-building…
git:20261111.4625af9 · audit A · 15 stars

Every file in sunflowerslwtech/sunkit

Browse by kind, by grade B, or by owner.