What is yoyo AGENTS.md?

Project instructions for yoyo, a tool with a core code-analysis layer and separate command-line and MCP interfaces. MCP is a standard way for AI tools to access software capabilities.

Working on yoyo’s engine, CLI, MCP interface, documentation, tests, and release version updates.

They give coding agents consistent rules for architecture, documentation, version changes, and deciding whether work belongs in the core or presentation layer.

How avirajkhare00/yoyo configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to avirajkhare00/yoyo. 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/avirajkhare00/yoyo/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/avirajkhare00/yoyo

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/avirajkhare00/yoyo/agents-md/github.svg)](https://agentmods.dev/instructions/avirajkhare00/yoyo/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/avirajkhare00/yoyo/agents-md"><img src="https://agentmods.dev/badge/instructions/avirajkhare00/yoyo/agents-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/avirajkhare00/yoyo/agents-md"><img src="https://agentmods.dev/badge/instructions/avirajkhare00/yoyo/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,222 This file is loaded in full into every session.

When invoked 1,222 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	$0.01222	$0.01222
Opus 5.5	$0.00489	$0.00489
Sonnet 5.5	$0.00244	$0.00244
Haiku 4.5	$0.00122	$0.00122

Measured 2mo ago against content hash a3b9280a5b37, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

yoyo 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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

yoyo CLAUDE.md — 98% identical, 2 lines differ

AGENTS.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

yoyo — Instructions for Codex

Operator

Read AVIRAJ.md once per session when context is fresh. It defines the operator's standards, pace, and communication style.

Core stance

Dogfood yoyo in every yoyo session. Pain felt while using it is product input; file an issue when it matters.
Build feedback loops, not just features. Every change should have a way to measure whether it helped.
Prefer durable design over extra instructions. If a rule keeps appearing, push it into the product.

Architecture

yoyo has two layers:

Engine: src/engine/, src/lang/. Stable core: AST parsing, indexing, analysis, graph operations.
Presentation: src/mcp.rs, src/cli.rs. MCP schemas, CLI commands, formatting.

Work bottom-up. Fix engine problems in the engine, not with presentation-layer workarounds.

MCP vs CLI

MCP is the curated surface. Every exposed tool costs tokens; keep only tools that earn their slot.
CLI is the full human surface. Do not remove CLI commands just because the MCP surface was simplified.

If the boundary is unclear, read docs/architecture.md.

Documentation ownership

Every fact should have one home:

Language support and project metrics: METRICS.md
Competitive landscape: COMPETITORS.md
Version history: CHANGELOG.md
Architecture and working rules: CLAUDE.md
Tool and API docs: docs/README.md

README.md is a front door, not a database. Summarize there and link outward. Delete duplicated facts on sight.

Language ground truth

Before generating code in a systems language, read the relevant playbook when one exists.

Zig 0.15.x: playbook/zig-0.15.md

When integrating a new language or library, read the source first. For tree-sitter grammars, inspect:

src/node-types.json
grammar.js
queries/highlights.scm

Docs and memory drift; source is ground truth.

Language policy

Use systems languages only:

Rust for core product code
Go for tooling, automation, eval harnesses, CI helpers
Zig when it is the right low-level fit

Read the full file on GitHub · 146 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 · 146 lines · 1,222 tokens per session scan A a3b9280a5b37

Subscribe to this mod's changes

yoyo AGENTS.md is an instructions file published in the GitHub repository avirajkhare00/yoyo (25 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 1,222 tokens to every session, about $0.0049 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.

ast tree-sitter-parser

yoyo AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
yoyo AGENTS.mdavirajkhare00/yoyo	Instructions file	25	7mo ago	Apache-2.0	A	1,222	Codex, OpenCode
weld copilot-instructions.mdconfigflux/weld	Instructions file	6	2mo ago	Apache-2.0	A	19	GitHub Copilot
vibecop copilot-instructions.mdbhvbhushan/vibecop	Instructions file	57	7mo ago	MIT	A	32	GitHub Copilot
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

yoyo: Instructions file for Codex