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.
npx agentmods add instructions/sublayerapp/sublayer/claude-mdgit clone --depth 1 https://github.com/sublayerapp/sublayerWhat 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 | $0.00759 | $0.00759 |
| Opus 5 | $0.00380 | $0.00380 |
| Sonnet 5 | $0.00152 | $0.00152 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
sublayer 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 83 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
Sublayer is a Ruby gem and CLI framework for building AI-powered applications. It provides base classes for Generators, Actions, Tasks, and Agents that work with multiple AI providers (OpenAI, Claude, Gemini).
Development Commands
# Setup
bin/setup # Install dependencies and configure dummy API keys
bundle install # Install gem dependencies
# Testing
rake spec # Run RSpec test suite
rake # Default task (runs specs)
# Building and releasing
rake build # Build gem package
rake install # Install gem locally
rake release # Release to RubyGems
# CLI usage (after install)
sublayer new PROJECT_NAME --template=[CLI|GithubAction|QuickScript] --provider=[OpenAI|Claude|Gemini]
sublayer generate:generator # Generate new Generator class
sublayer generate:agent # Generate new Agent class
sublayer generate:action # Generate new Action class
Architecture
The framework is built around four core concepts:
- Generators (
lib/sublayer/generators/base.rb) - Generate specific outputs based on input data - Actions (
lib/sublayer/actions/base.rb) - Perform operations to get inputs or use generated outputs - Agents (
lib/sublayer/agents/base.rb) - Autonomous entities with triggers and goal conditions - Tasks (
lib/sublayer/tasks/base.rb) - Task management components
AI Provider System: The framework supports multiple AI providers through a unified interface:
- OpenAI (default: gpt-4o) -
lib/sublayer/providers/open_ai.rb - Claude (Anthropic) -
lib/sublayer/providers/claude.rb - Gemini (Google, beta) -
lib/sublayer/providers/gemini.rb
Provider configuration is done via:
Sublayer.configuration.ai_provider = Sublayer::Providers::Claude
Sublayer.configuration.ai_model = "claude-3-5-sonnet-20240620"
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.
- 2d ago First seen · 83 lines · 759 tokens per session scan A cdb5f390002d
sublayer CLAUDE.md is an instructions file published in the GitHub repository sublayerapp/sublayer (205 stars, last pushed 1y ago), licensed MIT. It adds 759 tokens to every session, about $0.0038 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 2026-08-30.
Other instructions, from other repositories
AutoAgents AGENTS.md
Instructions for liquidos-ai/AutoAgents, covering autoagents repository guidelines, project structure & module organization, code quality, naming conventions and error handling.
timbal CLAUDE.md
Instructions for timbal-ai/timbal, covering claude.md, commands, development and testing, benchmarks and repository layout.
langium-ai CLAUDE.md
Instructions for eclipse-langium/langium-ai, covering claude.md, project overview, commands, build & test (all workspaces) and lint & format.
typedai AGENTS.md
Instructions for TrafficGuard/typedai, covering general code standards, clean code style guidelines, example, original code and analysis.
AutoAgents CLAUDE.md
Instructions for liquidos-ai/AutoAgents, a project described as: A multi-agent framework written in Rust that enables you to build, deploy, and coordinate multiple intelligent agents.
scout_apm_mcp.rb AGENTS.md
Instructions for amkisko/scout_apm_mcp.rb, covering agent context, shared instructions, shared prayers, minimal implementation and finite state machines.