AReaL: Skill for Claude Code

.agents/skills/add-archon-model/SKILL.md

add-archon-model is a skill for Claude Code, Codex from areal-project/AReaL. It costs 38 tokens per session (4,859 once invoked), scanned A, original, Apache-2.0.

A guide for adding support for a new Hugging Face model architecture to the Archon training engine. Hugging Face is a platform and library ecosystem that provides downloadable machine-learning models and their configurations.

In plain words
What is it for?
Use it when adding support for a decoder-only Transformer model, such as a new Llama, Mistral, or DeepSeek architecture.
Why use it?
It explains how to inspect a model's configuration and source code so Archon can recognize and run that model family correctly.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions Claude Code; installed under .agents/ (shared by several agents).

This is areal-project/AReaL's own configuration. It tells Claude Code and Codex how to work on AReaL 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 AReaL configures →

About the project

AReaL is an infrastructure system for training large language models with reinforcement learning, connecting model training to applications built around AI agents. Researchers and developers use it to train reasoning and agentic models through asynchronous workflows, and the catalogue add-ons support working with AReaL.

areal-project/AReaL · 5,739 stars · on GitHub · areal-ai.io

Reuse

Borrowing it

Nothing to install: this file belongs to areal-project/AReaL. 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/areal-project/AReaL/main/.agents/skills/add-archon-model/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/areal-project/AReaL

Made for: Claude Code, Codex.

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 add-archon-model

README.md
[![agentmods](https://agentmods.dev/badge/skills/areal-project/areal/add-archon-model/github.svg)](https://agentmods.dev/skills/areal-project/areal/add-archon-model)
Your own site
<a href="https://agentmods.dev/skills/areal-project/areal/add-archon-model"><img src="https://agentmods.dev/badge/skills/areal-project/areal/add-archon-model/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 add-archon-model

Your own site · 80×15
<a href="https://agentmods.dev/skills/areal-project/areal/add-archon-model"><img src="https://agentmods.dev/badge/skills/areal-project/areal/add-archon-model.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,859 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Prompt Injection · line 464
    Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
    Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
  • medium Agent Snooping · line 469
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 470
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00038 $0.04859
Opus 5 $0.00019 $0.02429
Sonnet 5 $0.00008 $0.00972
Haiku 4.5 $0.00004 $0.00486

Measured 10d ago against content hash 24b53b005b0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

add-archon-model 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.

.agents/skills/add-archon-model/SKILL.md · 510 lines

How it starts

The opening of the file, as written. The whole thing — 510 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add Archon Model

Add support for a new HuggingFace model architecture in the Archon training engine.

When to Use

This skill is triggered when:

  • User asks "how do I add a model to Archon?"
  • User wants to support a new model family (e.g., Llama, Mistral, DeepSeek) in ArchonEngine
  • User mentions adding a new ModelSpec or model type for Archon

Prerequisites

Before starting, ensure:

  • The target model is available on HuggingFace (has config.json with model_type)
  • You know the HuggingFace model ID (e.g., meta-llama/Llama-3-8B)
  • The model uses a standard transformer architecture (decoder-only)

Step-by-Step Guide

Step 1: Analyze the Target Model Architecture

Read the HuggingFace model's source code to extract key architecture information.

Action: Fetch and analyze the model's HuggingFace configuration and modeling files.

  1. Read the model's config.json (via AutoConfig.from_pretrained) to identify:

    • model_type string (this is the key used for registry lookup)
    • All architecture hyperparameters (hidden_size, num_layers, etc.)
    • Any model-specific fields (e.g., qk_norm, attention_bias, MoE fields)
  2. Read the HuggingFace modeling_*.py source to identify:

    • Attention variant: Does it have Q/K norm? Attention bias? Sliding window? Multi-latent attention?
    • FFN variant: SwiGLU (gate_proj + up_proj + down_proj)? GeGLU? Standard MLP?
    • MoE support: Does it have MoE layers? What router type? Shared experts?
    • RoPE variant: Standard RoPE? YaRN? NTK-aware scaling? What is the inv_freq formula?
    • Normalization: RMSNorm or LayerNorm? Pre-norm or post-norm? Elementwise affine?
    • Weight tying: Does tie_word_embeddings appear in config?
    • State dict key names: What are the HF weight key naming conventions?
  3. Summarize findings in a checklist like:

Target model: <name>
HF model_type: "<model_type>" (and variants like "<model_type>_moe" if applicable)
Attention: [standard GQA / with QK norm / with bias / sliding window / ...]
FFN: [SwiGLU / GeGLU / standard MLP / ...]
MoE: [no / yes - num_experts, top_k, shared_experts]
RoPE: [standard / YaRN / NTK-aware / ...]
Norm: [RMSNorm / LayerNorm] with [pre-norm / post-norm]
Weight tying: [yes / no]

Read the full file on GitHub · 510 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 · 510 lines · 38 tokens per session scan A 24b53b005b0a

Subscribe to this mod's changes

add-archon-model is a skill published in the GitHub repository areal-project/AReaL (5,739 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 4,859 once invoked, about $0.0002 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.