llamero: Instructions file for Claude Code

CLAUDE.md

llamero CLAUDE.md is an instructions file for Claude Code from crimson-knight/llamero. It costs 1,267 tokens per session, scanned A, original, MIT.

Repository instructions for llamero, a Crystal library for building AI applications with cloud model providers or local models running on Apple Silicon Macs.

In plain words
What is it for?
Use them when adding AI features in Crystal, selecting a provider, enabling retries and failover, running models locally, streaming responses, or training and switching adapters.
Why use it?
They help an agent choose between cloud chat, local inference, typed JSON responses, and LoRA or QLoRA adapters, which are small trained add-ons for adapting a model.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is crimson-knight/llamero's own configuration. It tells Claude Code how to work on llamero 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 llamero configures →

Reuse

Borrowing it

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

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 llamero CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/crimson-knight/llamero/claude-md"><img src="https://agentmods.dev/badge/instructions/crimson-knight/llamero/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,267 This file is loaded in full into every session.
When invoked 1,267 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 $0.01267 $0.01267
Opus 5 $0.00633 $0.00633
Sonnet 5 $0.00253 $0.00253
Haiku 4.5 $0.00127 $0.00127

Measured 10d ago against content hash 4a23185bd333, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

llamero 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 10d 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 · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

llamero — guide for AI coding agents

llamero is a Crystal library for building AI applications. It has two independent tracks that share the same Message and BaseGrammar types:

  1. Cloud providers (Llamero::Client + provider clients): OpenAI, Anthropic, Groq, OpenRouter with automatic retry/failover, streaming, and structured JSON output parsed into Crystal classes.
  2. Native local inference (Llamero::Native): runs MLX models locally on Apple Silicon through a Swift bridge — resident model, token streaming, structured output, LoRA/QLoRA adapter hot-swap, and in-process adapter training. No Python, no llama.cpp.

Which API do I need?

Task Use Detailed skill
Call OpenAI/Claude/Groq/OpenRouter, failover, retries Subclass Llamero::Client cloud-providers
Run a model locally on a Mac, no API key Llamero::Native::MLXRuntime local-inference
Typed JSON output from any model chat_structured + a Llamero::BaseGrammar subclass both skills
Teach a local model new facts/documents; LoRA/QLoRA session.train_adapter adapter-training
Toggle learned knowledge on/off at runtime session.activate_adapters / deactivate_adapters local-inference

Minimal rules that prevent most mistakes:

  • require "llamero" is the only require.
  • Llamero::Client is abstract — subclass it; never Llamero::Client.new.
  • Native chat lives on a session: runtime.start_session, then session.load_model (required), then session.chat(...).
  • Response text is always .content; structured results are .parsed.
  • BaseGrammar schema properties all need default values.
  • Native track on a machine without the built Swift bridge silently uses a deterministic mock. Gate real-inference code on runtime.real_bridge?.

Storage root

Default storage is ~/.llamero. Apps that own their AI data directory must set the root at boot before creating runtimes:

Llamero.storage_root = Path.home.join(".scribe")

Read the full file on GitHub · 98 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. 10d ago First seen · 98 lines · 1,267 tokens per session scan A 4a23185bd333

Subscribe to this mod's changes

llamero CLAUDE.md is an instructions file published in the GitHub repository crimson-knight/llamero (22 stars, last pushed 17d ago), licensed MIT. It adds 1,267 tokens to every session, about $0.0063 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

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

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 · 5,153 tokens

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

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

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 · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens