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 agents/smallmain/vscode-unify-chat-provider/update-cli-clientsgit clone --depth 1 https://github.com/smallmain/vscode-unify-chat-providerWrote 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/agents/smallmain/vscode-unify-chat-provider/update-cli-clients)<a href="https://agentmods.dev/agents/smallmain/vscode-unify-chat-provider/update-cli-clients"><img src="https://agentmods.dev/badge/agents/smallmain/vscode-unify-chat-provider/update-cli-clients.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 | $0.00010 | $0.00740 |
| Opus 5 | $0.00005 | $0.00370 |
| Sonnet 5 | $0.00002 | $0.00148 |
| Haiku 4.5 | $0.00001 | $0.00074 |
Grade A, and why
Update Cli Clients 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 4d 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.
What it actually says
目标
以下列出的客户端需要定期维护和更新，因为它们是通过模拟授权和请求实现的，官方可能会更改其授权或请求方式，导致客户端失效。
维护的方式是参考指定的参考项目的源码。
客户端列表
- Claude Code Client：参考 CLIProxyAPI 项目，本地路径：
/Users/smallmain/Documents/Work/CLIProxyAPI - Github Copilot Client：参考 CLIProxyAPI 项目，本地路径：
/Users/smallmain/Documents/Work/CLIProxyAPI - Open AI Codex Client：参考 CLIProxyAPI 项目，本地路径：
/Users/smallmain/Documents/Work/CLIProxyAPI - Antigravity / Gemini CLI Client：参考 CLIProxyAPI 项目，本地路径：
/Users/smallmain/Documents/Work/CLIProxyAPI
如果用户明确指定了客户端，那么只维护指定的客户端；否则，维护所有列出的客户端。
你的职责
你负责运行 subAgent，让每个子代理分别负责一个客户端的维护。
对于每个子代理，它们需要：
- 如果用户明确提到需要完整地检查一遍，那么拉取参考项目的最新代码进行检查。
- 如果用户没有明确提到，那么只检查参考项目当前提交与最新提交之间的代码改动即可。
- 了解项目中客户端的授权、请求的实现，重点在于模拟请求。
- 参考指定的参考项目的源码，检查客户端是否需要更新。
- 同步客户端支持的模型列表。
- 如果需要更新，那么修改相应的代码。
- 最后，将参考项目同步到最新提交（注意如果多个客户端共用一个参考项目，那么需都完成之后再同步到最新提交）。
模型 ID 同步规则（重要）
- 本项目的请求模型 ID 以“本项目的模型配置”作为输入，不直接照搬参考项目的前缀模型 ID 或复杂 alias 解析（例如
antigravity-*）。 - 允许的改动仅限“协议必需转换”：例如 Gemini 3 Pro 的 tier 后缀、Claude 的
-thinking、Gemini CLI 的-preview/-preview-customtools处理。 - 同步模型列表时，先核对本项目
getAvailableModels与本项目已有配置/命名，再决定是否增删；不要把参考项目的内部路由 ID 当作本项目配置 ID 直接写入。 - 以参考项目的模型列表为准，删除本项目中在参考项目中没有的模型，并添加参考项目中有但本项目没有的模型，确保最终列表与参考项目保持一致。
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.
- 4d ago First seen · 71 lines · 10 tokens per session scan A f532ab5c170b
Update Cli Clients is an agent published in the GitHub repository smallmain/vscode-unify-chat-provider (707 stars, last pushed 8d ago), licensed MIT. It adds 10 tokens to every session and 740 once invoked, about $0.0001 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 agents, from other repositories
challenger
I handle: Fact-checking, counter-hypothesis testing, verification, constructive challenge I do not handle: Implementation, code writing, architecture design — I review, not build On rejection: Specific items needing correction + verification methods provided.
01-Orchestrator
Master orchestrator for the multi-step Azure platform engineering workflow. Coordinates Requirements, Architect, Design, IaC Plan, IaC Code, Deploy agents with mandatory human approval gates. Routes Bicep or Terraform tracks via decisions.iactool.
03-Architect
Expert Architect providing guidance using Azure Well-Architected Framework principles and Microsoft best practices. Evaluates decisions against WAF pillars and generates ARM MCP-verified cost estimates.
04g-Governance
Azure governance discovery agent. Queries Azure Policy assignments via REST API (incl. management-group-inherited policies), classifies effects, produces governance constraint artifacts, and runs adversarial review. Step 3.5: after Architecture, before IaC Planning.
02-Requirements
Researches and captures Azure platform engineering project requirements.
06b-Bicep CodeGen
Expert Azure Bicep IaC specialist that creates near-production-ready Bicep templates following Azure Verified Modules (AVM) standards. Validates, tests, and ensures code quality.