agents CLAUDE.md

agents CLAUDE.md is an instructions file for coding agents from mtnyilmaz/agents. It costs 580 tokens per session, scanned A, original, MIT.

A central set of instructions for a layered system of AI-agent rules used across different code editors and project types. It explains how shared rules are organized and installed into another repository.

In plain words
What is it for?
Use it to install rules for projects such as React, Vue, Next.js, Go, Django, FastAPI, Laravel, or full-stack applications, then sync them with supported editor tools.
Why use it?
It provides a single source for common, language-specific, framework-specific, and project-specific rules instead of maintaining separate copies.

Instructions file

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/mtnyilmaz/agents/claude-md
Clone the repo
git clone --depth 1 https://github.com/mtnyilmaz/agents

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 agents CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mtnyilmaz/agents/claude-md.svg)](https://agentmods.dev/instructions/mtnyilmaz/agents/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mtnyilmaz/agents/claude-md"><img src="https://agentmods.dev/badge/instructions/mtnyilmaz/agents/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 580 This file is loaded in full into every session.
When invoked 580 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 $0.00580 $0.00580
Opus 5 $0.00290 $0.00290
Sonnet 5 $0.00116 $0.00116
Haiku 4.5 $0.00058 $0.00058

Measured 4d ago against content hash 3fee608c68da, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agents 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 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.

CLAUDE.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Instructions

This is a centralized agent rules registry. See README.md for the complete system overview.

What This Repo Is

A layered, multi-IDE AI agent rule system. Rules are organized in .agents/layers/ by scope (universal → language → framework → concern → project), assembled per-repo via install.sh, and synced to IDE tools via sync-rules.sh.

How to Work With This Repo

  1. Read README.md for the full system overview
  2. Rules source of truth: .agents/layers/
  3. Skills: .agents/skills/
  4. Workflows: .agents/workflows/
  5. Scripts: .agents/scripts/install.sh and sync-rules.sh

Installing Rules Into a Target Repo

bash .agents/scripts/install.sh --type <type> --target /path/to/repo
bash .agents/scripts/sync-rules.sh   # run inside target repo

Supported --type values: nextjs, nuxt, vue, react, tanstack, fastify, express, go, django, fastapi, laravel, expo, email-*, fullstack

Layer Order

universal → language → framework → concern → project

Each layer narrows scope. universal applies to every repo. project applies only to one specific repo.

Critical Rules (apply everywhere)

  • Never commit without explicit user permission
  • Conventional Commits: feat(scope): description
  • Adapter pattern for all third-party integrations
  • Soft delete everywhere — never hard delete records
  • No console.log in production code — use structured logger
  • Route → Service → Database — never skip service layer
  • User-facing copy (any app name in the repo): always from that package’s i18n — default en, standard second tr; no hardcoded client-visible literals (dummy/fixture/seed/test data excepted)

Version Policy (MANDATORY)

ALWAYS use @latest when installing any dependency. Never rely on your training data for version numbers — they are outdated. Never copy version numbers from rule/skill/layer files.

# RIGHT — always @latest
npx create-next-app@latest
npx create-expo-app@latest
pnpm add next@latest fastify@latest expo@latest zod@latest

# WRONG — never hardcode versions
npx create-next-app@15    # ❌
pnpm add fastify@5        # ❌
pnpm add expo@54          # ❌

Read the full file on GitHub · 61 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 · 61 lines · 580 tokens per session scan A 3fee608c68da

Subscribe to this mod's changes

agents CLAUDE.md is an instructions file published in the GitHub repository mtnyilmaz/agents (6 stars, last pushed 3mo ago), licensed MIT. It adds 580 tokens to every session, about $0.0029 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.

Related

Other instructions, from other repositories

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

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

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens