Home / xingjian-bai / opal · GitHub

train-with-agent SKILL.md skillA

train-with-agent from xingjian-bai/opal is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add xingjian-bai/opal/train-with-agent@git:20261023.123ec04

Pins git:20261023.123ec04 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
xingjian-bai/opal
Path
skills/train-with-agent/SKILL.md
Versions recorded
6
Latest version
git:20261023.123ec04, committed Oct 23, 2026
First version recorded
Oct 21, 2026
Size
7,379 bytes
Repository stars
355
License
MIT

Put the OPAL agent into this repository's PyTorch training script, so that a coding agent can rewrite the optimizer while the model trains. Use when the user asks to "train with an agent", "add OPAL", or similar.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Add OPAL to a training script

Goal: the user's training run, unchanged except that its optimizer is wrapped by `opal.wrap(...)`. Work in small
steps and show the user the diff before running anything that costs GPU time.

**Do not edit any file inside the OPAL repository** (its prompt, starting programs or code): configure everything
through `opal.wrap` arguments (`prompt=`, `program=`, `task_facts=`, ...). An edited install changes every run without
a word, and its results no longer match the blog's; OPAL warns when it finds one.

The agent's programs run inside your training process with its permissions and are not sandboxed; eval_integrity detects some evaluation-time parameter moves and boundary flags some file I/O and introspection, but neither prevents a program from reading what your process can read.
Keep test data and labels out of the training process, evaluate the final checkpoint in a separate process, and review boundary flags in report.html and events.jsonl (see docs/GUIDE.md, "What OPAL does not protect against").

1. **Find the loop.** Locate the training script and the place where the optimizer and LR scheduler are built and
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add xingjian-bai/opal/train-with-agent@sha256:ad36e7b0250acbc9

The line at the top of this page pins the label git:20261023.123ec04, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

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

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 6 versions of this file, between Oct 21, 2026 and Oct 23, 2026, more than one a day.

versioncommittedcommitsizeaudit
git:20261023.123ec04 latest2026-10-23 123ec04 7,379 BA view · diff
git:20261023.3e969d22026-10-23 3e969d2 7,293 BA view · diff
git:20261023.195a95f2026-10-23 195a95f 7,320 BA view · diff
git:20261022.de0475a2026-10-22 de0475a 7,234 BA view · diff
git:20261022.ab118d72026-10-22 ab118d7 6,929 BA view · diff
git:20261021.2e178b92026-10-21 2e178b9 6,445 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the 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 (7379 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

xingjian-bai/opal · 355 stars · license MIT · pushed 2026-11-03 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_muvubcaulefutlpc
GET https://markdownregistry.com/api/v1/resolve?ref=xingjian-bai/opal/train-with-agent
GET https://markdownregistry.com/api/v1/blob/ad36e7b0250acbc953158a0b00745107e4eca1ea93ec078c299077a8301e287a

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

Browse by kind, by grade A, or by owner.