yoagent: Instructions file for Claude Code

CLAUDE.md

yoagent CLAUDE.md is an instructions file for Claude Code from yologdev/yoagent. It costs 23,855 tokens per session, scanned A, original, MIT.

Project instructions for Yoagent, a Rust library for building AI coding agents, covering its overview, development commands, architecture, and main agent loop.

In plain words
What is it for?
Use it when developing Yoagent, running its full test suite, checking formatting, using examples, or understanding its agent, tool, and model integrations.
Why use it?
It gives an agent the repository-specific rules and commands needed to build, test, format, and lint the project correctly.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents; positional $N argument.

This is yologdev/yoagent's own configuration. It tells Claude Code how to work on yoagent 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 yoagent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to yologdev/yoagent. 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/yologdev/yoagent/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/yologdev/yoagent

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.

agentmods badge for yoagent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yologdev/yoagent/claude-md/github.svg)](https://agentmods.dev/instructions/yologdev/yoagent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/yologdev/yoagent/claude-md"><img src="https://agentmods.dev/badge/instructions/yologdev/yoagent/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.

agentmods 80×15 button for yoagent CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/yologdev/yoagent/claude-md"><img src="https://agentmods.dev/badge/instructions/yologdev/yoagent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23,855 This file is loaded in full into every session.
When invoked 23,855 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 $0.23855 $0.23855
Opus 5.5 $0.09542 $0.09542
Sonnet 5.5 $0.04771 $0.04771
Haiku 4.5 $0.02386 $0.02386

Measured yesterday against content hash 0792238e7f41, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

yoagent 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 yesterday.

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 · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 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.

Project Overview

yoagent is a Rust library (crate) for building AI coding agents. It provides a core agent loop, multi-provider LLM streaming, built-in tools, MCP integration, and context management. Published to crates.io as yoagent.

Library Principles

yoagent's motto is keep it simple but effective: a powerful, flexible, reusable base for others to build agents on. Check every change against these four lines before adding it:

  1. The loop stays as it is. New behaviour goes into tools, providers, extensions or opt-in settings, not new concepts in the agent loop.
  2. Built-in tools must be correct and safe. People use them as defaults without reading them, so a tool that silently loses data or misreports a result is a bug, not a missing feature.
  3. Small, generic knobs that any agent needs. Add a setting only when every kind of agent could want it, keep it opt-in or defaulting to today's behaviour, and keep the public API small.
  4. Opinions and heuristics belong above the library. Prompt tricks, auto-fixes, house policies and product behaviour go in extensions, in yobuild, or in the app — never baked into yoagent's defaults.

The longer reasoning is in docs/design-philosophy.md.

Build & Development Commands

cargo test --all-features            # Run all tests — what CI runs
cargo clippy --all-targets --all-features   # Lint — what CI runs (-Dwarnings)
cargo fmt                            # Auto-format code
cargo fmt -- --check                 # Check formatting (CI uses this)
RUSTDOCFLAGS="-Dwarnings" cargo doc --no-deps --all-features   # Doc links — what CI runs

cargo test <test_name>               # Run a single test by name
cargo test --test agent_test         # Run a specific test file
cargo run --example cli              # Run the interactive CLI example
cargo run --example basic            # Run the minimal example

Read the full file on GitHub · 277 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. yesterday Changed · +18 lines · +2,599 tokens per session 0792238e7f41
  2. 2d ago Changed · +172 tokens per session e8449f5e0704
  3. 3d ago Changed · +373 tokens per session 2276340bcf0f
  4. 6d ago Changed · +272 tokens per session 6de0a596c517
  5. 7d ago Changed · +946 tokens per session 8d222e3e1df7
  6. 8d ago Changed · +441 tokens per session a5341c4f2309
  7. 10d ago Changed · +615 tokens per session 3018842590ec
  8. 11d ago Changed · +704 tokens per session 0036872a4e82
  9. 15d ago Changed · +38 tokens per session 312ac395acd6
  10. 16d ago First seen · 259 lines · 17,695 tokens per session scan A adecb8bdf24c

Subscribe to this mod's changes

yoagent CLAUDE.md is an instructions file published in the GitHub repository yologdev/yoagent (369 stars, last pushed yesterday), licensed MIT. It adds 23,855 tokens to every session, about $0.0954 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 2026-08-30.

Related

yoagent CLAUDE.md compared with instructions from other repositories

yoagent CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
yoagent CLAUDE.mdyologdev/yoagentInstructions file369yesterdayMITA23,855Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode