What is openyoko CLAUDE.md?

Repository instructions for OpenYoko, a personal life-management system built around a file-based vault. They tell the coding agent how to find the vault and work with its projects, notes, and templates.

Use them when working on the OpenYoko repository, especially when reading the vault configuration, managing personal data, or changing skills and templates.

They give the agent a consistent starting point and prevent it from using the wrong vault location.

How ThoBustos/openyoko configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ThoBustos/openyoko. 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/ThoBustos/openyoko/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ThoBustos/openyoko

Made for: Claude Code.

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/thobustos/openyoko/claude-md/github.svg)](https://agentmods.dev/instructions/thobustos/openyoko/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/thobustos/openyoko/claude-md"><img src="https://agentmods.dev/badge/instructions/thobustos/openyoko/claude-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/thobustos/openyoko/claude-md"><img src="https://agentmods.dev/badge/instructions/thobustos/openyoko/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,336 This file is loaded in full into every session.

When invoked 4,336 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	$0.04336	$0.04336
Opus 5.5	$0.01734	$0.01734
Sonnet 5.5	$0.00867	$0.00867
Haiku 4.5	$0.00434	$0.00434

Measured 2mo ago against content hash e6e673f64821, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

openyoko CLAUDE.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 2mo 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.

CLAUDE.md · 499 lines

How it starts

The opening of the file, as written. The whole thing — 499 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Personal Agent OS - Claude Instructions

This is the core operating system for a personal life management vault. Claude should behave as an intelligent assistant that understands the vault structure, maintains information freshness, and helps the user live intentionally.

CRITICAL: First Action on Every Session

Before doing ANYTHING else, read the vault path:

Read: config/vault.json

This file contains the absolute path to the user's vault. ALL vault operations use this path.

If config/vault.json exists → use the vault_path value
If missing → fall back to ../my-vault/ relative to this repo
NEVER hardcode vault paths in skills or instructions

This is the foundation of OpenYoko - the vault is where all personal data lives.

Repository Overview

This repo (personal-agent-os/) is the framework and templates. The user's actual vault lives at ../my-vault/ as a sibling directory.

Key directories:

.claude/skills/ - Skill definitions (SKILL.md files) that define workflows
templates/ - Markdown templates for vault entries
docs/ - User documentation
example-vault/ - Reference vault structure
config/mcp/ - MCP server configuration (credentials stored outside repo)

Philosophy

Structure before automation. Clarity before tools.

Personal Agent OS organizes life around:

Identity - Who you are becoming (LIFE_VISION.md)
Pillars - What must never be neglected (PILLARS.md)
Projects - What you're building (03_PROJECTS/)
Relationships - Who matters (04_PEOPLE/)
Reflection - How you course-correct (02_JOURNAL/)

The vault is the single source of truth. Claude's job is to:

Keep the vault accurate and fresh
Surface relevant context when helping
Capture new information in the right place
Maintain the integrity of the system

Information Architecture

Read the full file on GitHub · 499 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.

2mo ago First seen · 499 lines · 4,336 tokens per session scan A e6e673f64821

Subscribe to this mod's changes

openyoko CLAUDE.md is an instructions file published in the GitHub repository ThoBustos/openyoko (9 stars, last pushed 2mo ago), licensed MIT. It adds 4,336 tokens to every session, about $0.0173 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 2026-08-31.

openyoko CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
openyoko CLAUDE.mdThoBustos/openyoko	Instructions file	9	2mo ago	MIT	A	4,336	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

openyoko: Instructions file for Claude Code