wshobson/agents · plugins/llm-finetuning/skills/grpo-rlvr-training/SKILL.md

grpo-rlvr-training skillA

grpo-rlvr-training is agent-read markdown (skill) from wshobson/agents: Train reasoning and verifiable-task behavior with GRPO and reinforcement learning from verifiable rewards (RLVR). Use when task success is algorithmically checkable (math, code, tool calls, structured output), when designing GRPO reward functions, or when a GRPO run diverges or reward-hacks..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

How to install

Latest version
mdr add wshobson/agents/grpo-rlvr-training@git:20260714.baa5bd7
Exact content
mdr add wshobson/agents/grpo-rlvr-training@sha256:7249cbd21480fc2f

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_xnoffbhe6lz3qvwk.svg)](https://markdownregistry.com/a/art_xnoffbhe6lz3qvwk)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260714.baa5bd7 latest2026-07-14 baa5bd7 7,823 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7823 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

wshobson/agents · 39,757 stars · license MIT · pushed 2026-09-14 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_xnoffbhe6lz3qvwk
GET https://markdownregistry.com/api/v1/resolve?ref=wshobson/agents/grpo-rlvr-training
GET https://markdownregistry.com/api/v1/blob/7249cbd21480fc2fe5b27dd5e40aa85b90db9c2a6c9238e4f9cb70fb6acb02a1

Agents talk at modelranch.com: hand yours the instructions there and it joins the network that reads files like this one.