agentmods.dev

copilot-proxy: Instructions file for Codex

AGENTS.md

copilot-proxy AGENTS.md is an instructions file for Codex, OpenCode from Jer-y/copilot-proxy. It costs 2,757 tokens per session, scanned A, original, MIT.

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

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions AGENTS.md; mentions Codex.

This is Jer-y/copilot-proxy's own configuration. It tells Codex and OpenCode how to work on copilot-proxy 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 copilot-proxy configures →

not rated 45repo +1 changed 1mo ago A scan 2,757 tokens original MIT
View source ↗ Jer-y/copilot-proxy jer-y.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to Jer-y/copilot-proxy. 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/Jer-y/copilot-proxy/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Jer-y/copilot-proxy

Made for: Codex, OpenCode.

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 copilot-proxy AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jer-y/copilot-proxy/agents-md/github.svg)](https://agentmods.dev/instructions/jer-y/copilot-proxy/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jer-y/copilot-proxy/agents-md"><img src="https://agentmods.dev/badge/instructions/jer-y/copilot-proxy/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.

agentmods 80×15 button for copilot-proxy AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jer-y/copilot-proxy/agents-md"><img src="https://agentmods.dev/badge/instructions/jer-y/copilot-proxy/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,757 This file is loaded in full into every session.
When invoked 2,757 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.02757 $0.02757
Opus 5.5 $0.01103 $0.01103
Sonnet 5.5 $0.00551 $0.00551
Haiku 4.5 $0.00276 $0.00276

Measured 1mo ago against content hash c47762ff7c15, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 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.

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-utils.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. 1mo ago Changed · -3 tokens per session c47762ff7c15
  2. 1mo ago Changed · +1 lines · +69 tokens per session c8137a3e1899
  3. 1mo ago Changed · -1 lines · -114 tokens per session 4bcded72d43f
  4. 1mo 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 (45 stars, last pushed 1mo ago), licensed MIT. It adds 2,757 tokens to every session, about $0.0110 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.

Claude Codeanthropic-apianthropic-compatibleapi-proxycodexcodex-cli
Related

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,461 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,731 tokens

vscode model-prompts.instructions.md

Model-specific prompt authoring and registry guidelines.

microsoft/vscode · 2,022 tokens