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.
Borrowing it
Nothing to install: this file belongs to caozhiyuan/copilot-api. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/caozhiyuan/copilot-api/dev/AGENTS.mdgit 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/instructions/caozhiyuan/copilot-api/agents-md)<a href="https://agentmods.dev/instructions/caozhiyuan/copilot-api/agents-md"><img src="https://agentmods.dev/badge/instructions/caozhiyuan/copilot-api/agents-md/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/instructions/caozhiyuan/copilot-api/agents-md"><img src="https://agentmods.dev/badge/instructions/caozhiyuan/copilot-api/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00685 | $0.00685 |
| Opus 5.5 | $0.00274 | $0.00274 |
| Sonnet 5.5 | $0.00137 | $0.00137 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
copilot-api AGENTS.md 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 21d 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.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Layout
src/: Bun/TypeScript API gateway;routes/handles HTTP endpoints,services/integrates providers,lib/holds shared logic, andlib/types/defines OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages contracts.tests/: gateway tests named after the features they cover;pages/: static web assets;docs/: documentation and screenshots;plugin/: plugin scripts.desktop/: Electron app with its own package, source, and checks; root ESLint excludes bothdesktop/andplugin/.
Commands
Run from the repository root unless noted:
bun run dev/bun run start: watch / production API entrypoint, with system CA enabled.bun run build: package build;bun run build:desktop: desktop server bundle.bun run typecheck/bun run lint: gateway TypeScript / ESLint checks.bun run typecheck:all/bun run lint:all: gateway and desktop checks.bun test tests/provider-resolver.test.ts: one test file; use explicittestsand/ordesktop/testsdirectories for larger suites, and capture their output as described below.bun run --cwd desktop test: desktop tests;bun run --cwd desktop build: Electron app build.
Code Style
- Use ES modules, strict TypeScript, and
~/*imports withinsrc/; avoidanyand derive request/response fields from actual contract types. - Use
camelCasefor variables/functions,PascalCasefor types/classes, and descriptive filenames such asresponses-stream-translation.ts. - Format gateway files with
bun run lint --fix <files>; use the desktop package's lint configuration for desktop files. - ESLint embeds Prettier options, including
semi: false; do not run standaloneprettierorbunx prettier.
Verification
- Use Bun tests named
*.test.tsintests/ordesktop/tests/, matching the affected package. - Never run bare
bun testor stream unfiltered test-suite output into the conversation. Always specify test files/directories and redirect stdout and stderr to a temporary log file; inspect and report only the result summary, relevant failures, and changed-code coverage. - Changed code must reach at least 80% unit test coverage; use
bun test --coverage <test-files>to inspect coverage. - Test affected request translation, providers, auth, config, and streaming edge cases; run the relevant tests, lint, and typecheck for code changes, expanding validation for shared behavior.
- For documentation-only changes, verify referenced paths/commands and inspect the diff; application tests are unnecessary.
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.
- 21d ago Changed · +1 lines · +60 tokens per session f99b1364b412
- 26d ago Changed · +6 lines · -27 tokens per session a88afe356634
- 2mo ago First seen · 35 lines · 652 tokens per session scan A c61808ac2dae
copilot-api AGENTS.md is an instructions file published in the GitHub repository caozhiyuan/copilot-api (1,101 stars, last pushed today), licensed MIT. It adds 685 tokens to every session, about $0.0027 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.