rlhf-book: Skill for Claude Code

.claude/skills/run-rlhf-code-experiment/SKILL.md

run-rlhf-code-experiment is a skill for Claude Code from natolambert/rlhf-book. It costs 22 tokens per session (732 once invoked), scanned A, original, no licence file.

A tool for planning, running, and reporting a small experiment involving reinforcement learning from human feedback. RLHF is a method of improving AI systems using people’s preferences or evaluations.

In plain words
What is it for?
It helps test code or ideas for the RLHF Book and produce a report of what was tried and what happened.
Why use it?
It organizes the experiment from setup through results, so the work is easier to repeat and explain.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is natolambert/rlhf-book's own configuration. It tells Claude Code how to work on rlhf-book 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 rlhf-book configures →

Reuse

Borrowing it

Nothing to install: this file belongs to natolambert/rlhf-book. 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/natolambert/rlhf-book/main/.claude/skills/run-rlhf-code-experiment/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/natolambert/rlhf-book

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 run-rlhf-code-experiment

README.md
[![agentmods](https://agentmods.dev/badge/skills/natolambert/rlhf-book/run-rlhf-code-experiment.svg)](https://agentmods.dev/skills/natolambert/rlhf-book/run-rlhf-code-experiment)
Your own site
<a href="https://agentmods.dev/skills/natolambert/rlhf-book/run-rlhf-code-experiment"><img src="https://agentmods.dev/badge/skills/natolambert/rlhf-book/run-rlhf-code-experiment.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 732 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00022 $0.00732
Opus 5 $0.00011 $0.00366
Sonnet 5 $0.00004 $0.00146
Haiku 4.5 $0.00002 $0.00073

Measured 2d ago against content hash 69ab548e00b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

run-rlhf-code-experiment 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.

.claude/skills/run-rlhf-code-experiment/SKILL.md · 56 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

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. 2d ago Changed · +2 lines 69ab548e00b0
  2. 6d ago First seen · 54 lines · 22 tokens per session scan A ff07a8346518

Subscribe to this mod's changes

run-rlhf-code-experiment is a skill published in the GitHub repository natolambert/rlhf-book (2,368 stars, last pushed yesterday), with no licence file. It adds 22 tokens to every session and 732 once invoked, about $0.0001 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 skills, from other repositories

meta-eval

Use when the user wants to build an evaluation system for an LLM/agent application but doesn't know where to start — they have traces, prompts, RAG pipelines, or nothing at all. Also use when the user mentions evaluation, eval, benchmarking, testing LLM quality, measuring agent performance, assessing RAG accuracy, or…

agentscope-ai/OpenJudge · 101 tokens

rag-eval

Use when the user has a RAG (Retrieval-Augmented Generation) system and wants to evaluate its quality — separating retrieval issues from generation issues. Also use when the user mentions RAG evaluation, faithfulness checking, hallucination detection in RAG, retrieval quality, chunking optimization, or "is my RAG…

agentscope-ai/OpenJudge · 86 tokens

prompt-regression

Use when the user has changed a prompt (system prompt, RAG template, agent instruction, etc.) and wants to know whether the candidate is better or worse than the baseline. Also use when the user mentions prompt A/B testing, prompt comparison, prompt optimization validation, "did my prompt change help," or prompt…

agentscope-ai/OpenJudge · 86 tokens

paper-review

Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files and LaTeX source packages (.tar.gz/.zip). Covers 10 disciplines: cs, medicine, physics, chemistry, biology, economics, psychology, environmentalscience, mathematics, socialsciences. Use when the user…

agentscope-ai/OpenJudge · 94 tokens

ref-hallucination-arena

Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate, per-field accuracy (title/author/year/DOI), discipline breakdown, and year constraint compliance. Supports tool-augmented (ReAct + web search) mode. Use when the…

agentscope-ai/OpenJudge · 100 tokens

rl-reward

Build RL reward signals using the OpenJudge framework. Covers choosing between pointwise and pairwise reward strategies based on RL algorithm, task type, and cost; aggregating multi-dimensional pointwise scores into a scalar reward; pairwise tournament reward for GRPO on subjective tasks (net win rate across group…

agentscope-ai/OpenJudge · 116 tokens