agentmods.dev

oraclebone copilot-instructions.md

oraclebone copilot-instructions.md is an instructions file for GitHub Copilot from sapuyou45-bit/oraclebone. It costs 503 tokens per session, scanned A, original, MIT.

Repository instructions for oraclebone, a Python command-line tool that produces I Ching divination readings. They cover the project layout, skill files, security rules, and how readings must be generated by audited code.

In plain words
What is it for?
Use them when changing oraclebone, its skills, reading scripts, schemas, references, or shared safety policies.
Why use it?
They prevent unsafe shortcuts such as letting an AI model invent results, using hidden network calls, or mishandling randomness and sensitive data.

Instructions file for GitHub Copilot

not rated 4 3d ago A scan 503 tokens original MIT
View the source file sapuyou45-bit/oraclebone
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/sapuyou45-bit/oraclebone/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/sapuyou45-bit/oraclebone

Made for: GitHub Copilot.

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 oraclebone copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sapuyou45-bit/oraclebone/copilot-instructions.svg)](https://agentmods.dev/instructions/sapuyou45-bit/oraclebone/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/sapuyou45-bit/oraclebone/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/sapuyou45-bit/oraclebone/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 503 This file is loaded in full into every session.
When invoked 503 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 $0.00503 $0.00503
Opus 5 $0.00251 $0.00251
Sonnet 5 $0.00101 $0.00101
Haiku 4.5 $0.00050 $0.00050

Measured 4d ago against content hash a278b72d7586, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

oraclebone copilot-instructions.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 4d 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.

.github/copilot-instructions.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot / AI assistant instructions for this repository

Read AGENTS.md first, then this file.

Project shape

  • Python package oraclebone exposes the CLI oraclebone.
  • Per-skill skill folders live under skills/<skill>/ and each ships:
    • SKILL.md (trigger description + workflow)
    • agents/openai.yaml, agents/claude.yaml, agents/gemini.yaml, agents/cursor.mdc
    • scripts/ (delegates to the package; standalone fallback when copied as a folder)
    • references/ (sources, interpretation template, cards/hexagrams reference)
  • Shared cross-skill policies live in shared/.
  • JSON output schemas live in schemas/.

Non-negotiable rules when writing code

  1. Never let the model generate the divination result. Every code path that produces a draw / hexagram / position must go through the audited script. Adapters re-export the CLI; they do not call out to a model.
  2. Randomness uses system entropy by default. Seeded mode is reserved for tests and reproducible demos and must be documented as such in any new surface.
  3. No hidden network calls, no shelling out, no telemetry, no secret handling. Per SECURITY.md.
  4. Safety boundaries: refuse medical / legal / financial / emergency / crisis advice. See shared/safety-policy.md.
  5. JSON outputs need a matching schema in schemas/ and a unit test.
  6. Python 3.9–3.12 compatibility (use from __future__ import annotations for new modules).

Workflow expectations

  • Tests must pass: python3 -m unittest discover -s tests (49 tests today, all four CI matrix versions).
  • New behaviour must come with tests under tests/.
  • Update CHANGELOG.md [Unreleased] for every user-facing change.
  • Update RELEASE_NOTES.md once during the release-cutting PR.
  • PRs use the checklist in .github/PULL_REQUEST_TEMPLATE.md.

Releasing

Maintainer-only. See docs/maintainer/release-and-pypi.md. Tag vX.Y.Z → release workflow attaches sdist+wheel, and publishes to PyPI when PYPI_API_TOKEN secret is set.

Read the full file on GitHub · 36 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. 4d ago First seen · 36 lines · 503 tokens per session scan A a278b72d7586

Subscribe to this mod's changes

oraclebone copilot-instructions.md is an instructions file published in the GitHub repository sapuyou45-bit/oraclebone (4 stars, last pushed 3d ago), licensed MIT. It adds 503 tokens to every session, about $0.0025 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.

ai-agentsai-skillscodexdivinationichingopenai
Related

Other instructions, from other repositories

opendivination AGENTS.md

AGENTS.md instructions for amenti-labs/opendivination, covering opendivination agent guide, canonical agent surfaces, read these first, core commands and result handling rules.

amenti-labs/opendivination · 600 tokens

AstrBot copilot-instructions.md

Copilot instructions for AstrBotDevs/AstrBot, covering astrbot development instructions, working effectively, bootstrap and install dependencies, running the application and dashboard build (vue.js/node.js).

AstrBotDevs/AstrBot · 736 tokens

ai AGENTS.md

AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.

vercel/ai · 2,900 tokens

dario CLAUDE.md

Claude Code instructions for askalf/dario, covering dario — notes for claude code (and other llm coding agents), commits and prs, style, scope and when in doubt, ask.

askalf/dario · 407 tokens

a-i--skills 03-development-workflow.instructions.md

Instructions for organvm-iv-taxis/a-i--skills, covering development workflow instructions, no repo-wide build system, common development commands, after adding/modifying skills and validation before committing.

organvm-iv-taxis/a-i--skills · 892 tokens

ZipAgent AGENTS.md

Instructions for JiayuXu0/ZipAgent, covering repository guidelines, project structure & module organization, build, test & development commands, coding style & naming conventions and testing guidelines.

JiayuXu0/ZipAgent · 504 tokens