New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Model Fallback

by majiayu000 in majiayu000/claude-skill-registry

模型自动降级与故障切换。当主模型请求失败、超时、达到速率限制或配额耗尽时，自动切换到备用模型，确保服务连续性。支持多供应商、多优先级的智能模型选择，提供健康监控、自动重试和错误恢复机制。

MITAuto-check: notesBackend & APIs

Install Model Fallback

skills CLI
$ npx skills add majiayu000/claude-skill-registry --skill model-fallback -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install majiayu000/claude-skill-registry model-fallback --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/majiayu000/claude-skill-registry.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ai-llm/model-fallback .claude/skills/model-fallback && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
model-fallback
GitHub stars
666
Used in
2 other repos
Token cost
~2.3k tokens
SKILL.md length
217 words
Files
2
Skills in repo
1,273
Repo updated
First seen
Licence
MIT

At a glance

模型自动降级与故障切换。当主模型请求失败、超时、达到速率限制或配额耗尽时，自动切换到备用模型，确保服务连续性。支持多供应商、多优先级的智能模型选择，提供健康监控、自动重试和错误恢复机制。

  • Works in 12 steps: 智能模型选择 → 故障检测与处理 → 重试机制 → …
  • Backend & APIs work in your project
  • SKILL.md covers 概述, 核心功能, 快速开始 and 工作流程, plus 5 more sections
  • Calls python3

What it does

Model Fallback is an agent skill from majiayu000/claude-skill-registry. 模型自动降级与故障切换。当主模型请求失败、超时、达到速率限制或配额耗尽时，自动切换到备用模型，确保服务连续性。支持多供应商、多优先级的智能模型选择，提供健康监控、自动重试和错误恢复机制。

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `metadata.json`).

It sits in Backend & APIs. The repository describes itself as: Searchable Claude Code skills catalog with source-linked guides and generated registry artifacts. The licence is MIT.

When your agent uses it

  • Backend & APIs work in your project

Example prompts

  • “/model-fallback”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): Bash, Read, Write, Edit, Exec

Workflow steps

12 steps, taken from the step headings in SKILL.md.

  1. 智能模型选择
  2. 故障检测与处理
  3. 重试机制
  4. 健康监控
  5. 配置模型降级
  6. 启动监控
  7. 手动触发切换
  8. 超时错误 (Timeout)
  9. 速率限制 (Rate Limit)
  10. 配额耗尽 (Quota Exceeded)
  11. 认证错误 (Authentication)
  12. 定期检查

What it can do on your machine

Read from SKILL.md and the folder at commit 2d14a69. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Write
    • Edit
    • Exec

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Model Fallback loads about 2.3k tokens when it runs. Until then it costs about 27 tokens; SKILL.md has 217 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~27
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Write, Edit, Exec

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from majiayu000/claude-skill-registry at commit 2d14a69, republished under its MIT licence (© majiayu000). 217 words, ~2,304 tokens.

Download SKILL.mdSave it as .claude/skills/model-fallback/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
model-fallback
description
模型自动降级与故障切换。当主模型请求失败、超时、达到速率限制或配额耗尽时，自动切换到备用模型，确保服务连续性。支持多供应商、多优先级的智能模型选择，提供健康监控、自动重试和错误恢复机制。
allowed-tools
Bash, Read, Write, Edit, Exec

模型自动降级与故障切换

概述

本技能提供完整的模型自动降级和故障切换解决方案，确保在主模型不可用时自动切换到备用模型，维持 AI 助手的持续服务能力。

核心功能

1. 智能模型选择

根据任务类型和模型状态智能选择最合适的模型：

yaml
优先级顺序:
  1. anapi/opus-4.5         # 最强能力，最高优先级
  2. zai/glm-4.7            # 中文优化，性价比高
  3. openrouter-vip/gpt-5.2-codex  # 编码专用
  4. github-copilot/claude-sonnet-4-5  # 免费备用
2. 故障检测与处理

自动检测以下故障并触发切换：

  • 超时错误 (timeout): 请求超过设定时间
  • 速率限制 (rate_limit): API 调用频率超限
  • 配额耗尽 (quota_exceeded): token 配额用尽
  • 认证错误 (authentication): API 密钥失效
  • 服务不可用 (service_unavailable): 供应商服务故障
  • 网络错误 (network_error): 连接失败
3. 重试机制

智能重试策略：

yaml
重试配置:
  最大重试次数: 3
  初始延迟: 1000ms
  最大延迟: 10000ms
  退避倍数: 2.0
  使用备用模型: true

重试时间线：

第1次失败 → 等待 1s → 重试
第2次失败 → 等待 2s → 重试
第3次失败 → 等待 4s → 切换模型
4. 健康监控

持续监控所有模型供应商的健康状态：

bash
# 每5分钟检查一次
检查项目:
  - API 端点连通性
  - 响应时间
  - 错误率
  - 配额使用情况

快速开始

1. 配置模型降级

配置文件：~/.openclaw/agents/main/agent/agent.json

json
{
  "model": "anapi/opus-4.5",
  "modelFallback": [
    "zai/glm-4.7",
    "openrouter-vip/gpt-5.2-codex",
    "github-copilot/claude-sonnet-4-5"
  ],
  "retry": {
    "maxAttempts": 3,
    "initialDelayMs": 1000,
    "maxDelayMs": 10000,
    "backoffMultiplier": 2.0,
    "useFallbackOnFailure": true
  }
}
2. 启动监控
bash
# 启动后台监控
~/.openclaw/scripts/monitor-models.sh start

# 查看监控状态
~/.openclaw/scripts/monitor-models.sh status

# 停止监控
~/.openclaw/scripts/monitor-models.sh stop
3. 手动触发切换
bash
# 运行降级检查脚本
~/.openclaw/scripts/model-fallback.sh

工作流程

正常请求流程
用户请求
    ↓
选择主模型 (anapi/opus-4.5)
    ↓
发送请求到 API
    ↓
成功 → 返回结果
故障切换流程
用户请求
    ↓
选择当前模型
    ↓
发送请求 → 失败/超时
    ↓
重试 (最多3次)
    ↓
仍然失败?
    ↓
切换到备用模型 (zai/glm-4.7)
    ↓
发送请求
    ↓
成功 → 返回结果并记录
监控流程
监控守护进程 (每5分钟)
    ↓
检查所有模型健康状态
    ↓
├─ 主模型健康 → 保持当前
└─ 主模型不健康 → 切换到最佳可用模型
    ↓
更新状态文件
    ↓
记录日志

错误处理策略

1. 超时错误 (Timeout)
json
{
  "timeout": {
    "switchModel": true,
    "retryCount": 2,
    "timeoutMs": 60000,
    "fallbackTo": "zai/glm-4.7"
  }
}

行为：

  • 超过 60 秒视为超时
  • 重试 2 次后仍超时则切换模型
2. 速率限制 (Rate Limit)
json
{
  "rateLimit": {
    "switchModel": true,
    "cooldownMs": 60000,
    "alert": true,
    "fallbackTo": "zai/glm-4.7"
  }
}

行为：

  • 收到 429 错误码
  • 冷却 60 秒后尝试恢复
  • 立即切换到备用模型
3. 配额耗尽 (Quota Exceeded)
json
{
  "quotaExceeded": {
    "switchModel": true,
    "alert": true,
    "fallbackTo": "zai/glm-4.7",
    "checkInterval": 3600000
  }
}

行为：

  • 配额用尽时切换模型
  • 每小时检查一次主模型是否恢复
  • 发送告警通知
4. 认证错误 (Authentication)
json
{
  "authenticationError": {
    "switchModel": true,
    "alert": true,
    "disableModel": true
  }
}

行为：

  • API 密钥失效时立即切换
  • 禁用故障模型（不自动恢复）
  • 发送紧急告警

智能路由规则

根据任务类型自动选择最合适的模型：

json
{
  "routing": {
    "strategy": "priority-fallback",
    "rules": [
      {
        "name": "coding-task",
        "match": {
          "contentContains": ["代码", "code", "编程", "函数"]
        },
        "preferModels": [
          "openrouter-vip/gpt-5.2-codex",
          "anapi/opus-4.5"
        ]
      },
      {
        "name": "chinese-task",
        "match": {
          "language": "zh"
        },
        "preferModels": [
          "zai/glm-4.7",
          "anapi/opus-4.5"
        ]
      },
      {
        "name": "vision-task",
        "match": {
          "hasImage": true
        },
        "preferModels": [
          "anapi/opus-4.5"
        ]
      }
    ]
  }
}

监控与日志

日志文件位置
bash
~/.openclaw/logs/model-fallback.log    # 切换日志
~/.openclaw/logs/model-monitor.log     # 监控日志
~/.openclaw/logs/model-status.json     # 状态报告
查看实时日志
bash
# 查看切换日志
tail -f ~/.openclaw/logs/model-fallback.log

# 查看监控日志
tail -f ~/.openclaw/logs/model-monitor.log

# 查看所有日志
tail -f ~/.openclaw/logs/*.log
状态报告
bash
# 查看当前状态
~/.openclaw/scripts/monitor-models.sh status

# JSON 格式状态
cat ~/.openclaw/logs/model-status.json | python3 -m json.tool

脚本说明

model-fallback.sh

模型降级切换脚本，负责：

  • 测试所有配置的模型
  • 选择最佳可用模型
  • 执行模型切换
  • 记录切换日志

用法：

bash
~/.openclaw/scripts/model-fallback.sh
monitor-models.sh

健康监控守护进程，负责：

  • 定期检查模型健康状态
  • 自动触发故障切换
  • 生成状态报告
  • 管理 PID 文件

用法：

bash
~/.openclaw/scripts/monitor-models.sh {start|stop|restart|status|check}
test-model-fallback.sh

测试脚本，用于：

  • 验证配置正确性
  • 测试切换逻辑
  • 模拟故障场景
  • 生成测试报告

用法：

bash
~/clawd/scripts/test-model-fallback.sh

配置文件详解

agent.json 完整配置
json
{
  "model": "anapi/opus-4.5",
  "modelFallback": [
    "zai/glm-4.7",
    "openrouter-vip/gpt-5.2-codex",
    "github-copilot/claude-sonnet-4-5"
  ],
  "retry": {
    "maxAttempts": 3,
    "initialDelayMs": 1000,
    "maxDelayMs": 10000,
    "backoffMultiplier": 2.0,
    "useFallbackOnFailure": true
  },
  "errorHandling": {
    "rateLimit": {
      "switchModel": true,
      "cooldownMs": 60000,
      "alert": true
    },
    "timeout": {
      "switchModel": true,
      "retryCount": 2,
      "timeoutMs": 60000
    },
    "quotaExceeded": {
      "switchModel": true,
      "alert": true,
      "fallbackTo": "zai/glm-4.7"
    },
    "authenticationError": {
      "switchModel": true,
      "alert": true,
      "disableModel": true
    }
  },
  "models": {
    "anapi/opus-4.5": {
      "provider": "anapi",
      "alias": "opus45",
      "maxTokens": 200000,
      "timeoutMs": 60000,
      "priority": 1,
      "supports": ["vision", "tools", "long-context"],
      "costFactor": "high"
    },
    "zai/glm-4.7": {
      "provider": "zai",
      "alias": "zai47",
      "maxTokens": 200000,
      "timeoutMs": 60000,
      "priority": 2,
      "supports": ["tools", "long-context"],
      "costFactor": "medium",
      "bestFor": ["chinese", "general-purpose"]
    },
    "openrouter-vip/gpt-5.2-codex": {
      "provider": "openrouter-vip",
      "alias": "codex52",
      "maxTokens": 100000,
      "timeoutMs": 30000,
      "priority": 3,
      "supports": ["coding"],
      "costFactor": "low",
      "bestFor": ["coding", "code-generation"]
    },
    "github-copilot/claude-sonnet-4-5": {
      "provider": "github-copilot",
      "alias": "sonnet",
      "maxTokens": 200000,
      "timeoutMs": 60000,
      "priority": 4,
      "supports": ["tools", "long-context"],
      "costFactor": "free",
      "bestFor": ["fallback", "general-purpose"]
    }
  },
  "monitoring": {
    "enabled": true,
    "checkIntervalMs": 300000,
    "logFile": "$HOME/.openclaw/logs/model-fallback.log",
    "alertOnFailure": true
  }
}

故障排查

问题 1: 模型未自动切换

检查：

bash
# 查看配置文件
cat ~/.openclaw/agents/main/agent/agent.json | grep modelFallback

# 查看日志
tail -20 ~/.openclaw/logs/model-fallback.log

# 手动运行切换脚本
~/.openclaw/scripts/model-fallback.sh
问题 2: 监控未运行

检查：

bash
# 查看进程
ps aux | grep monitor-models

# 查看PID文件
cat ~/.openclaw/logs/model-monitor.pid

# 重启监控
~/.openclaw/scripts/monitor-models.sh restart
问题 3: 所有模型都不可用

检查：

bash
# 查看状态报告
~/.openclaw/scripts/monitor-models.sh status

# 检查 API 密钥
cat ~/.openclaw/agents/main/agent/auth-profiles.json

# 测试网络连接
ping -c 3 anapi.9w7.cn
ping -c 3 open.bigmodel.cn

性能优化

减少切换频率
json
{
  "retry": {
    "maxAttempts": 5,        // 增加重试次数
    "initialDelayMs": 2000   // 增加初始延迟
  }
}
优化响应时间

为不同任务选择最快的模型：

json
{
  "routing": {
    "rules": [
      {
        "name": "quick-response",
        "match": {
          "priority": "speed"
        },
        "preferModels": [
          "github-copilot/claude-sonnet-4-5",  // 通常响应最快
          "zai/glm-4.7"
        ]
      }
    ]
  }
}

集成到 OpenClaw

配置完成后，模型降级功能会自动集成到 OpenClaw Gateway：

  1. 自动重启 Gateway:
bash
openclaw gateway restart
  1. 验证配置:
bash
openclaw status | grep Model
  1. 查看日志:
bash
journalctl -u openclaw-gateway -f | grep model

最佳实践

1. 定期检查

每周运行一次全面检查：

bash
~/clawd/scripts/test-model-fallback.sh
2. 监控日志

每天查看切换日志：

bash
grep "切换模型" ~/.openclaw/logs/model-fallback.log | tail -10
3. 更新配置

当添加新模型时，更新 agent.json：

json
{
  "modelFallback": [
    "anapi/opus-4.5",
    "zai/glm-4.7",
    "new-model-here",  // 新模型
    "github-copilot/claude-sonnet-4-5"
  ]
}
4. 备份配置

定期备份配置文件：

bash
cp ~/.openclaw/agents/main/agent/agent.json \
   ~/.openclaw/agents/main/agent/agent.json.backup

相关文件

  • ~/.openclaw/agents/main/agent/agent.json - 主配置文件
  • ~/.openclaw/agents/main/agent/auth-profiles.json - API 密钥
  • ~/.openclaw/scripts/model-fallback.sh - 切换脚本
  • ~/.openclaw/scripts/monitor-models.sh - 监控脚本
  • ~/clawd/scripts/test-model-fallback.sh - 测试脚本
  • ~/clawd/docs/model-fallback-strategy.md - 技术文档

支持的模型

当前配置的模型及其特性：

模型供应商优先级最大Token特长
opus-4.5anapi1200k最强能力，视觉
glm-4.7zai2200k中文优化
gpt-5.2-codexopenrouter-vip3100k编码专用
sonnet-4.5github-copilot4200k免费备用

TODO

  • 添加更多供应商
  • 实现基于成本的模型选择
  • 添加模型性能指标收集
  • 实现预测性模型切换
  • 集成告警通知（Telegram/邮件）
  • 添加 WebUI 监控面板

© majiayu000, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/ai-llm/model-fallback of majiayu000/claude-skill-registry.

  • SKILL.md
  • metadata.json

Open the folder on GitHubat commit 2d14a69

Used in 2 other repositories

We found 4 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in majiayu000/claude-skill-registry, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Model Fallback next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Model Fallback compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Model Fallback this skillmajiayu000/claude-skill-registry6662 repos~2.3kAutomated safety check: NotesMIT
Configuring Horizoncoollabsio/coolify63k4 repos~898Automated safety check: PassMIT
Nestjs Best Practicesrolling-scopes/rsschool-app10k6 repos~1.2kAutomated safety check: PassMIT
Sub2API AdminWei-Shaw/sub2api43k1 repos~717Automated safety check: PassLGPL-3.0
Firecrawl Build Onboardingfirecrawl/firecrawl190k1 repos~1.4kAutomated safety check: NotesISC
Obsidian BasesAtmosphere/atmosphere3.8k22 repos~3.2kAutomated safety check: PassApache-2.0

Similar skills

  • Configuring Horizon

    coollabsio/coolify

    A skill your agent uses whenever the user mentions Horizon by name in a Laravel context.

    63k GitHub starsUsed in 4 repos~898 tokens
    Backend & APIsAuto-check passed

  • Nestjs Best Practices

    rolling-scopes/rsschool-app

    NestJS best practices and architecture patterns for building production-ready applications.

    10k GitHub starsUsed in 6 repos~1.2k tokens
    Backend & APIsAuto-check passed

  • Sub2API Admin

    Wei-Shaw/sub2api

    Manages a Sub2API deployment from the command line: accounts, redeem and invitation codes, groups, proxies, imports, exports and raw admin API calls.

    43k GitHub starsUsed in 1 repo~717 tokens
    Backend & APIsAuto-check passed

  • Firecrawl Build Onboarding

    firecrawl/firecrawl

    Gets Firecrawl working in a project: signs you in through the browser, saves FIRECRAWL_API_KEY to .env and picks the first SDK or REST path.

    190k GitHub starsUsed in 1 repo~1.4k tokens
    Backend & APIsAuto-check: notes

  • Obsidian Bases

    Atmosphere/atmosphere

    Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries.

    3.8k GitHub starsUsed in 22 repos~3.2k tokens
    Backend & APIsAuto-check passed

  • Fortify Development

    coollabsio/coolify

    ACTIVATE when the user works on authentication in Laravel. An agent skill from coollabsio/coolify.

    63k GitHub starsUsed in 4 repos~1.9k tokens
    Backend & APIsAuto-check passed

More from majiayu000/claude-skill-registry

All 1,273 skills in this repo

  • Deep Research

    majiayu000/claude-skill-registry

    Multi-source deep research using firecrawl and exa MCPs. An agent skill from majiayu000/claude-skill-registry.

    666 GitHub starsUsed in 6 repos~1.1k tokens
    Auto-check passed

  • Exa Search

    majiayu000/claude-skill-registry

    Neural search via Exa MCP for web, code, and company research.

    666 GitHub starsUsed in 5 repos~856 tokens
    Auto-check passed

  • Fal AI Media

    majiayu000/claude-skill-registry

    Unified media generation via fal.ai MCP — image, video, and audio.

    666 GitHub starsUsed in 5 repos~1.7k tokens
    Auto-check passed

  • Pyzotero

    majiayu000/claude-skill-registry

    Interact with Zotero reference management libraries using the pyzotero Python client.

    666 GitHub starsUsed in 5 repos~1.6k tokens
    Auto-check: notes

  • Bgpt Paper Search

    majiayu000/claude-skill-registry

    Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server.

    666 GitHub starsUsed in 4 repos~619 tokens
    Auto-check: notes

  • Bio Alignment Pairwise

    majiayu000/claude-skill-registry

    Perform pairwise sequence alignment using Biopython Bio.Align.PairwiseAligner.

    666 GitHub starsUsed in 4 repos~1.7k tokens
    Auto-check passed

Categories

Questions about Model Fallback

What does Model Fallback do?

模型自动降级与故障切换。当主模型请求失败、超时、达到速率限制或配额耗尽时，自动切换到备用模型，确保服务连续性。支持多供应商、多优先级的智能模型选择，提供健康监控、自动重试和错误恢复机制。. Model Fallback is an agent skill from majiayu000/claude-skill-registry.

When should I use Model Fallback?

Model Fallback fits situations like: backend & APIs work in your project.

How do I install Model Fallback in Claude Code?

Run `npx skills add majiayu000/claude-skill-registry --skill model-fallback -a claude-code`. Or copy the skill folder (skills/ai-llm/model-fallback in majiayu000/claude-skill-registry) into .claude/skills/model-fallback in your project. Claude Code loads it when a task matches its description.

How do I install Model Fallback in Codex?

Run `npx skills add majiayu000/claude-skill-registry --skill model-fallback -a codex`. Or copy the skill folder (skills/ai-llm/model-fallback in majiayu000/claude-skill-registry) into .agents/skills/model-fallback in your project. Codex loads it when a task matches its description.

Can I use Model Fallback in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add majiayu000/claude-skill-registry --skill model-fallback -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/model-fallback, .gemini/skills/model-fallback, .github/skills/model-fallback and .opencode/skills/model-fallback in your project.

What does Model Fallback need to run?

Going by SKILL.md and its folder, Model Fallback needs the command-line tools its instructions call (python3). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Bash, Read, Write, Edit, Exec.

Does Model Fallback access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Model Fallback safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Model Fallback use?

Model Fallback is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Model Fallback use?

About 2.3k tokens (SKILL.md is roughly 9.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Model Fallback?

Skills that share tags, products or a category with Model Fallback: Configuring Horizon (coollabsio/coolify, 63k stars), Nestjs Best Practices (rolling-scopes/rsschool-app, 10k stars), Sub2API Admin (Wei-Shaw/sub2api, 43k stars) and Firecrawl Build Onboarding (firecrawl/firecrawl, 190k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Model Fallback?

majiayu000 (a GitHub user) maintains it in majiayu000/claude-skill-registry, which has 666 GitHub stars. The repository holds 1,273 skills in this directory. The repository was last updated on October 7, 2026.

Source: majiayu000/claude-skill-registry on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.