What is opendivination AGENTS.md?

A repository guide for OpenDivination, a Python software project for drawing tarot and I Ching readings through a command-line program and software library.

It helps set up the project, run tarot or I Ching draws, inspect available sources, and run tests, linting, and type checks.

It tells coding agents which files to read, which interfaces are official, and which commands and checks to use when working on the project.

How amenti-labs/opendivination configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to amenti-labs/opendivination. 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/amenti-labs/opendivination/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/amenti-labs/opendivination

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/amenti-labs/opendivination/agents-md.svg)](https://agentmods.dev/instructions/amenti-labs/opendivination/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/amenti-labs/opendivination/agents-md"><img src="https://agentmods.dev/badge/instructions/amenti-labs/opendivination/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 600 This file is loaded in full into every session.

When invoked 600 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.

Model	Per session	Once invoked
Fable 5.1	$0.00600	$0.00600
Opus 5	$0.00300	$0.00300
Sonnet 5	$0.00120	$0.00120
Haiku 4.5	$0.00060	$0.00060

Measured 6d ago against content hash bea556cef11d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

opendivination 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 · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenDivination Agent Guide

Canonical Agent Surfaces

Python SDK in src/opendivination/
CLI via opendivination ...
Portable skill bundles in skills/
Repository-level instructions in AGENTS.md

The MCP server was intentionally removed. Do not reintroduce MCP as the primary integration surface unless there is an explicit product decision to do so.

Read These First

README.md
skills/AGENTS.md
skills/divination-setup/SKILL.md
skills/divination/SKILL.md
src/opendivination/types.py
src/opendivination/cli/main.py
tests/test_cli.py

Core Commands

Development setup:

pip install -e ".[dev]"

Quality checks:

pytest
ruff check src tests skills/divination/scripts skills/divination-setup/scripts
mypy src

Canonical agent commands:

opendivination setup --json
opendivination draw tarot --json
opendivination draw tarot --question "What should I focus on?" --embed-provider local --json
opendivination draw iching --method yarrow --json
opendivination draw iching --question "How do I proceed?" --embed-provider local --json
opendivination sources --json

Source defaults:

csprng is the default source unless the user has explicitly changed it with setup
openentropy is not a default; treat it as an opt-in local hardware path
prefer qcicada over the aggregate openentropy source when the user wants the strongest explicit quantum path

Skill helper:

python3 skills/divination-setup/scripts/run_opendivination.py --check
python3 skills/divination/scripts/run_opendivination.py --check

Result Handling Rules

Prefer JSON CLI output when an agent needs structured data.
When the user asks about randomness, provenance, or trust, always include provenance.source_id and provenance.is_quantum.
Never imply quantum entropy when the actual source is csprng.
Keep interpretation separate from entropy/provenance facts.
If you change output structure, update the README, the skill bundle, and tests together.

Read the full file on GitHub · 80 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.

6d ago First seen · 80 lines · 600 tokens per session scan A bea556cef11d

Subscribe to this mod's changes

opendivination AGENTS.md is an instructions file published in the GitHub repository amenti-labs/opendivination (1 stars, last pushed 5mo ago), licensed MIT. It adds 600 tokens to every session, about $0.0030 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.

Claude Code claude-skills divination entropy iching oracle

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

opendivination: Instructions file for Codex