BrewMe: Instructions file for Codex

AGENTS.md

BrewMe AGENTS.md is an instructions file for Codex, OpenCode from xiaojiou176-open/BrewMe. It costs 1,245 tokens per session, scanned A, original, MIT.

Repository-specific working instructions for BrewMe, a public engineering project with documented rules for code, testing, browser automation, and runtime files.

In plain words
What is it for?
Use it before editing BrewMe to find the project’s README, setup, architecture, and testing guidance and to follow its safety rules.
Why use it?
It keeps changes focused, public documentation clean, and disposable files or services from being left in the repository or on the machine.

Instructions file for CodexOpenCode

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

This is xiaojiou176-open/BrewMe's own configuration. It tells Codex and OpenCode how to work on BrewMe 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 BrewMe configures →

Reuse

Borrowing it

Nothing to install: this file belongs to xiaojiou176-open/BrewMe. 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/xiaojiou176-open/BrewMe/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/xiaojiou176-open/BrewMe

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 BrewMe AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/xiaojiou176-open/brewme/agents-md.svg)](https://agentmods.dev/instructions/xiaojiou176-open/brewme/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/xiaojiou176-open/brewme/agents-md"><img src="https://agentmods.dev/badge/instructions/xiaojiou176-open/brewme/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,245 This file is loaded in full into every session.
When invoked 1,245 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 $0.01245 $0.01245
Opus 5 $0.00622 $0.00622
Sonnet 5 $0.00249 $0.00249
Haiku 4.5 $0.00125 $0.00125

Measured 8d ago against content hash 0efabe95ae67, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

BrewMe 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 8d 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 · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Collaboration Contract

This repository is a public, source-first engineering project. The public surface MUST stay thin, truthful, and easy to navigate.

Core Rules

  1. README.md is the front door.
  2. docs/start-here.md is the quickstart and operator entrypoint.
  3. docs/architecture.md is the system map.
  4. docs/testing.md is the testing and CI contract.
  5. Runtime, cache, logs, and agent workspaces MUST stay out of the tracked public surface.
  6. Root documentation MUST stay concise and public-facing. Internal audit logs, rehearsal notes, and execution ledgers MUST NOT return.
  7. AI agents MUST read before editing, prefer surgical changes, and verify meaningful behavior with real commands.
  8. Commits, branch rewrites, and force-pushes are allowed only when explicitly authorized by the human maintainer.
  9. Browser automation MUST stay repo-scoped, state-aware, and cleanup-first: do not accumulate extra Chrome/Chromium/Safari instances, cloned profiles, or large tab sets, and do not borrow browser state opened by other repos or other L1s on the same machine.
  10. Docker and runtime residue MUST stay governed: do not leave disposable containers, caches, or duplicate runtime workspaces behind after verification when they are no longer needed.
  11. External-account writes stay opt-in only: never change GitHub profile settings, browser-signed-in account state, Resend/Google account settings, or other third-party account data unless the human maintainer explicitly authorizes that exact write.
  12. Login-state probing MUST stay bounded: if the repo-scoped real browser profile is still not logged in after one or two focused checks, record a blocker and stop escalating browser churn.
  13. Browser focus and machine-wide resource contention MUST be respected: avoid stealing desktop focus when possible, and if the machine already has more than six browser instances open, wait for other repo workflows to release resources before opening another one.
  14. Current-cycle branch, worktree, and PR residue MUST be closed out before declaring completion: merge active work into main, or evidence-close and delete branches that are already fully absorbed.
  15. Release truth and current-main truth MUST be stated separately and honestly: if the latest release lags current main, document that gap explicitly instead of implying they are the same snapshot.

Read the full file on GitHub · 78 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. 8d ago First seen · 78 lines · 1,245 tokens per session scan A 0efabe95ae67

Subscribe to this mod's changes

BrewMe AGENTS.md is an instructions file published in the GitHub repository xiaojiou176-open/BrewMe (2 stars, last pushed 3mo ago), licensed MIT. It adds 1,245 tokens to every session, about $0.0062 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 2026-08-31.

Related

Other instructions, from other repositories

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 · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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 · 6,785 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 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 · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens