ccx: Skill for Claude Code

.claude/skills/model-update/SKILL.md

model-update is a skill for Claude Code from BenedictKing/ccx. It costs 43 tokens per session (2,673 once invoked), scanned A, original, MIT.

A procedure for adding or updating the list of AI models that a project can recognize and route requests to.

In plain words
What is it for?
Use it to register a new model family or add a dated model alias, update routing rules and capability records, and check dependent benchmarks or generated files.
Why use it?
It prevents model names, aliases, provider routes, capability data, and related tests from becoming inconsistent after a model release.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is BenedictKing/ccx's own configuration. It tells Claude Code how to work on ccx itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ccx configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/generate-model-registry.mjs.

About the project

BenedictKing/ccx is an AI API proxy and protocol-translation gateway that provides one entry point for Claude, OpenAI, Codex Responses, Gemini, and other listed APIs. It is used to manage provider channels, keys, routing, monitoring, and failover, and the catalogue entries provide skills and instructions for operating it.

BenedictKing/ccx · 3,983 stars · on GitHub · benedictking.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to BenedictKing/ccx. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/BenedictKing/ccx/main/.claude/skills/model-update/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/BenedictKing/ccx

Made for: Claude Code.

Wrote 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.

agentmods badge for model-update

README.md
[![agentmods](https://agentmods.dev/badge/skills/benedictking/ccx/model-update/github.svg)](https://agentmods.dev/skills/benedictking/ccx/model-update)
Your own site
<a href="https://agentmods.dev/skills/benedictking/ccx/model-update"><img src="https://agentmods.dev/badge/skills/benedictking/ccx/model-update/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.

agentmods 80×15 button for model-update

Your own site · 80×15
<a href="https://agentmods.dev/skills/benedictking/ccx/model-update"><img src="https://agentmods.dev/badge/skills/benedictking/ccx/model-update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,673 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.02673
Opus 5.5 $0.00017 $0.01069
Sonnet 5.5 $0.00009 $0.00535
Haiku 4.5 $0.00004 $0.00267

Measured 1mo ago against content hash 91a8f927f76c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

model-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 1mo 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.

.claude/skills/model-update/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CCX 模型注册更新技能

当用户输入包含以下关键词时触发:

  • "新模型"、"添加模型"、"model registry"、"模型注册"、"模型版本更新"、"model update"

适用范围

适用于三类场景:

  1. 新增独立模型(默认情形):仓库中还没有该 canonical model,需要补完整能力定义与必要映射。一般添加模型都是新的独立模型——带新主次版本号的模型(如 claude-fable-5 → claude-fable-5-1、claude-mythos-5 → claude-mythos-5-1)一律默认独立注册,不要归并进前代。归并会把 benchmark 证据混进前代 profile,图表张冠李戴、选型画像互相污染,事后拆分成本远高于一次独立注册。
  2. 已有模型的 dated suffix / 快照别名:如 DeepSeek-V4-Pro-0813、claude-haiku-4-5-20251001,通常只需要放宽 pattern、补测试,并检查特定 route 白名单是否也要同步放开。
  3. 错误归并的别名拆分为独立模型:发现既有归并搞错了(别名次代其实是独立模型),按"别名拆分检查清单"执行。

执行流程

0. 先判定属于哪一类变更

先回答这 4 个问题:

  1. 仓库里是否已经存在 canonical model(如 deepseek-v4-pro)?
  2. 新上线的是全新 canonical model,还是已有模型的日期后缀/快照别名?默认假设是独立模型;只有纯日期后缀(-20260902 / -0813)或官方明确的快照别名才按别名处理。拿不准时按独立模型处理或向用户确认,不要默认归并。
  3. 是否有 provider route 对该模型做了 SupportedModels 白名单限制?
  4. 是否有 benchmark / preset / builtin manifest 依赖生成产物自动同步?

如果只是 dated suffix 更新,优先最小化修改,避免误改优先级和 alias。

1. 收集模型信息

优先从官方文档、项目上下文或现有同族模型推断以下字段:

字段 示例
canonical model deepseek-v4-pro
新上线别名 DeepSeek-V4-Pro-0813
provider deepseek / anthropic / openai
是否已有同族条目 是 / 否
是否只是日期后缀 是 / 否
是否影响 bare alias 如 sonnet / opus / deepseek-chat
是否影响特定协议路由白名单 如 Responses route

2. 更新 single source of truth

核心文件: shared/model-registry/ccx_model_registry.json

2.1 如果是新增 canonical model

在 upstreamCapabilities 中新增完整条目,按家族就近放置。

2.2 如果是 dated suffix / 快照别名更新

优先修改已有 patterns,不要重复新增能力条目。注意此分支仅适用于纯日期后缀/快照别名;次代版本模型走 2.1 新增独立条目。

典型规则:

  • 仅支持 -YYYY-MM-DD 与 -YYMMDD / -YYYYMMDD 时,pattern 常是 -\\d{6,8}
  • 若 DeepSeek 新版本使用 -MMDD,需放宽到 -\\d{4,8}

例如:

"(?:^|[-/])deepseek-v4-pro(?:-\\d{4}-\\d{2}-\\d{2}|-\\d{4,8})?(?=$|@)"

3. 检查是否需要改 route 白名单

重点文件: backend-go/internal/config/provider_templates.go

检查:

  • SupportedModels
  • provider 描述文案
  • route 描述文案
  • 对应测试 backend-go/internal/config/provider_templates_test.go

典型场景:

  • 上游某协议端点此前只支持 flash
  • 新版本上线后 pro 也支持该端点
  • 此时不仅要放宽注册表 pattern,还要把 route 白名单从 []string{"deepseek-v4-flash"} 扩成 []string{"deepseek-v4-flash", "deepseek-v4-pro"}

Read the full file on GitHub · 188 lines

Changes

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.

  1. 1mo ago Changed · -1 lines 91a8f927f76c
  2. 2mo ago Changed · +16 lines 9e791b719782
  3. 2mo ago First seen · 173 lines · 43 tokens per session scan A 75c4a1cde4bb

Subscribe to this mod's changes

model-update is a skill published in the GitHub repository BenedictKing/ccx (3,983 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 2,673 once invoked, about $0.0002 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.

Related

model-update compared with skills from other repositories

model-update next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
model-updateBenedictKing/ccxSkill4.0k3d agoMITA43Claude Code
developmentfengshao1227/ccg-workflowSkill6.0k4d agoMITA41Claude Code
bionic-decision-enginewinstonkoh87/Athena-PublicSkill620yesterdayMITA41Claude Code, Codex
trading-risk-gatewinstonkoh87/Athena-PublicSkill620yesterdayMITA53Claude Code
macos-toolssonichi/sutandoSkill404todayMITA52Claude Code, Codex
cmux-architecturemanaflow-ai/cmuxSkill29kyesterdaynoneA63Codex
video-perceptionjordanrendric/claude-video-visionSkill1.5k23d agoMITA51Claude Code