cubepi: Instructions file for Codex

AGENTS.md

cubepi AGENTS.md is an instructions file for Codex, OpenCode from cubeplexai/cubepi. It costs 1,300 tokens per session, scanned A, original, MIT.

Repository instructions for cubepi, an async Python framework for building agents—programs that use language models and tools to perform tasks. They describe its modules, commands, tests, and code standards.

In plain words
What is it for?
They are for installing dependencies, running tests and coverage, checking formatting and types, and working on providers, agents, tools, storage, MCP, and tracing.
Why use it?
They give contributors the project’s required development workflow and checks, helping changes fit the existing design.

Instructions file for CodexOpenCode

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

This is cubeplexai/cubepi's own configuration. It tells Codex and OpenCode how to work on cubepi 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 cubepi configures →

Reuse

Borrowing it

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

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 cubepi AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cubeplexai/cubepi/agents-md.svg)](https://agentmods.dev/instructions/cubeplexai/cubepi/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/cubeplexai/cubepi/agents-md"><img src="https://agentmods.dev/badge/instructions/cubeplexai/cubepi/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,300 This file is loaded in full into every session.
When invoked 1,300 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 5.1 $0.01300 $0.01300
Opus 5 $0.00650 $0.00650
Sonnet 5 $0.00260 $0.00260
Haiku 4.5 $0.00130 $0.00130

Measured 6d ago against content hash 8d5dd673e53f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cubepi 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 6d 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 · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cubepi

Pythonic async-native agent framework (an alternative to langgraph). Async-first, strongly typed, deliberately few dependencies.

Commands (always via uv)

uv sync --all-extras --dev               # install everything
uv run pytest tests/                      # run tests (asyncio_mode=auto)
uv run pytest tests/path/test.py::test -v # single test
uv run ruff check cubepi/ tests/
uv run ruff format --check cubepi/ tests/ # CI checks formatting, doesn't fix
uv run mypy cubepi

CI runs pytest + ruff + mypy. Tests run on Python 3.11–3.14 (3.14 is continue-on-error); local default is 3.13 (.python-version).

Architecture

cubepi/ modules: providers/ (LLM abstraction — Provider protocol returning MessageStream; anthropic / openai / openai_responses / faux), agent/ (agent.py stateful class, loop.py stateless core algorithm, tools.py execution engine), middleware/, checkpointer/ (memory / sqlite / postgres), mcp/, tracing/ (OTel, optional), cli/ (cubepi trace). See the README "Architecture" section for the full annotated tree.

Conventions & gotchas

  • Lean deps: core deps are anthropic, openai, pydantic only. Everything else (sqlite, postgres, mcp, tracing, trace-cli) is an optional extra in pyproject.toml. Don't add a hard dependency without strong reason.
  • cubepi.tracing is lazily importable (PEP 562 __getattr__): schema constants import without the opentelemetry SDK, so the trace CLI works on a cubepi[trace-cli]-only install. Don't add eager OTel imports to its __init__.py.
  • Tests use FauxProvider for deterministic, no-API-call runs with realistic streaming. Prefer it over mocking providers.
  • cubepi/cli/** is excluded from codecov (codecov.yml ignore).
  • Packaged data: cubepi/providers/catalog/data/*.yaml ships in the wheel.

Development workflow

This project follows a deliberate spec → plan → code pipeline. Honor it for any non-trivial work.

1. Set up an isolated worktree first. When a new requirement comes in, before doing any work create a date-prefixed worktree on a date-prefixed branch (e.g. .worktrees/YYYY-MM-DD-<topic> on branch YYYY-MM-DD-<topic>). Never work directly on main. Subagents that write code must also use isolation: "worktree".

Read the full file on GitHub · 102 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. 6d ago First seen · 102 lines · 1,300 tokens per session scan A 8d5dd673e53f

Subscribe to this mod's changes

cubepi AGENTS.md is an instructions file published in the GitHub repository cubeplexai/cubepi (48 stars, last pushed yesterday), licensed MIT. It adds 1,300 tokens to every session, about $0.0065 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.

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 · 5,182 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