agentmods.dev

copilot-proxy AGENTS.md

Project instructions for copilot-proxy, including its build, lint, type-checking, testing, and code-style rules. A monorepo-style setup may contain several related parts that are checked with different commands.

In plain words
What is it for?
Use them when modifying copilot-proxy or reviewing a change. They help you choose the right build, lint, type-check, audit, and test commands.
Why use it?
They give contributors the expected engineering principle and the commands used to verify changes. They also reduce guesswork about how this project should be built and tested.

Instructions file for CodexOpenCode

37 8d ago A scan 2,805 tokens original MIT
View the source file Jer-y/copilot-proxy
Install

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.

agentmods
npx agentmods add instructions/jer-y/copilot-proxy/agents-md
Clone the repo
git clone --depth 1 https://github.com/Jer-y/copilot-proxy

Made for: Codex, OpenCode.

Per session 2,805 This file is loaded in full into every session.
When invoked 2,805 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.02805 $0.02805
Opus 5 $0.01403 $0.01403
Sonnet 5 $0.00561 $0.00561
Haiku 4.5 $0.00281 $0.00281

Measured 2d ago against content hash b5df9db1d34b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

copilot-proxy 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 2d 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.

AGENTS.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Top-Level Engineering Principle

  • Avoid over-engineering. Choose the simplest complete solution that satisfies the current confirmed requirement and preserves the existing product contract.
  • Complexity must be earned by a concrete current need, observed evidence, or a real second use case. Hypothetical future flexibility, practically unreachable edge cases, and architectural elegance alone are not sufficient justification.
  • This principle governs architecture, implementation, debugging, testing, review, documentation, and operations. Unless correctness, security, an external protocol contract, or an explicit user requirement demands otherwise, prefer narrower scope, fewer moving parts, and reversible changes over broader or more generic designs.

Build, Lint, and Test Commands

  • Core: bun run build, bun run dev, bun run start, bun run lint, bun run lint --fix, bun run typecheck, bun run knip, and bun run audit.
  • Tests: bun test, bun run test:coverage, or bun test <test-file>.
  • Common targeted tests: tests/create-responses.test.ts, tests/messages-routing.test.ts, tests/model-config.test.ts, tests/copilot-auth-recovery.test.ts, tests/auth-recovery-routes.test.ts, tests/concurrency-limiter.test.ts, and tests/request-signal-regression.test.ts.
  • Protocol and live gates: use bun run test:node:http, bun run test:live:copilot, bun run test:live:responses-item-replay, and bun run test:live:codex as applicable. Exact environment variables, route matrices, and acceptance criteria live in the capability validation guide.
  • Native service: bun run ./src/main.ts enable; use stop, restart, status, and logs for lifecycle control. Linux boot-before-login requires systemd user lingering. The removed start -d path must continue to direct users to enable.
  • Other CLI subcommands: setup, models, doctor, auth, check-usage, and debug.
  • Codex setup policy: Before authentication, inspect the installed Codex version and bundled catalog. Require Codex 0.134.0 or newer, and apply the same usable bundled-metadata gate to interactive choices and explicit --model. Keep live route-probe evidence separate from evidence that the generated profile was saved and executed with real Codex; setup does not provide the latter.

Read the full file on GitHub · 79 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. 2d ago First seen · 79 lines · 2,805 tokens per session scan A b5df9db1d34b

Subscribe to this mod's changes

copilot-proxy AGENTS.md is an instructions file published in the GitHub repository Jer-y/copilot-proxy (37 stars, last pushed 8d ago), licensed MIT. It adds 2,805 tokens to every session, about $0.0140 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.

Backend and APIsCode reviewTestinganthropic-apianthropic-compatibleapi-proxyclaude-codecodexcodex-cli
Related

Other instructions, from other repositories

copilot-proxy-api CLAUDE.md

Instructions for voidsteed/copilot-proxy-api, covering claude.md, project overview, common commands, architecture and entry points & cli structure.

voidsteed/copilot-proxy-api · 3,899 tokens

airelay CLAUDE.md

Claude Code instructions for ligj1706/airelay, covering claude.md, 项目概述, 产品定位, 设计原则 and 产品演进方向.

ligj1706/airelay · 1,752 tokens

ccNexus AGENTS.md

AGENTS.md instructions for jackychanisnotme/ccNexus, covering agents.md, 项目概述, 当前产品阶段与最高优先级, 存量客户兼容性规则 and 未来服务器运营功能设计边界.

jackychanisnotme/ccNexus · 3,463 tokens

ccNexus CLAUDE.md

Claude Code instructions for jackychanisnotme/ccNexus, covering claude.md, 项目概述, 常用开发命令, 开发与构建 and 桌面应用开发模式（支持热重载）.

jackychanisnotme/ccNexus · 1,602 tokens

copilot-proxy-api AGENTS.md

Instructions for voidsteed/copilot-proxy-api, covering agents.md, build, lint, and test commands and code style guidelines.

voidsteed/copilot-proxy-api · 441 tokens

apm python.instructions.md

Python development guidelines.

microsoft/apm · 78 tokens