caozhiyuan/copilot-api is a local AI gateway that exposes OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages interfaces for multiple providers. It lets clients such as Claude Code, OpenCode, and Codex connect through one endpoint to GitHub Copilot, the built-in Codex provider, and other configured services.
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.
git clone --depth 1 https://github.com/caozhiyuan/copilot-apiWrote 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/plugins/caozhiyuan/copilot-api/agent-inject)<a href="https://agentmods.dev/plugins/caozhiyuan/copilot-api/agent-inject"><img src="https://agentmods.dev/badge/plugins/caozhiyuan/copilot-api/agent-inject/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.
<a href="https://agentmods.dev/plugins/caozhiyuan/copilot-api/agent-inject"><img src="https://agentmods.dev/badge/plugins/caozhiyuan/copilot-api/agent-inject.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agent-inject 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.
What it actually says
{
"name": "agent-inject",
"description": "Inject copilot-api rules and SubagentStart agent context",
"version": "1.5.1",
"author": {
"name": "copilot-api maintainers"
}
}
What it installs
The manifest is a name and a version. 3 hooks travel with it, and installing the plugin installs all of them. Each is measured on its own page, and each can be installed alone.
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.
- 1mo ago First seen · 9 lines scan A 6c5f906ea5b3
agent-inject is a plugin published in the GitHub repository caozhiyuan/copilot-api (1,083 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
reporting-and-database-access
Database Toolbox, MATLAB Report Generator, Parallel Computing Toolbox, and Simulink Report Generator.
deeplaw-knowledge-os
Explicit-use, read-only access to the local Markdown-native Knowledge OS and bounded Context Capsules.
agent-evolutions
Genetic exploration of solution spaces for AI coding agents — gather a verifiable objective, evolve variants, apply the winner.
sharp-edges
Identify error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes.
unknowns
Skills for discovering and closing knowledge gaps across the dev lifecycle, from Thariq's 'Know Your Unknowns'.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.