cortex-training-rl SKILL.md skillA
cortex-training-rl from openhands/extensions is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add openhands/extensions/cortex-training-rl@git:20261101.21c88f5Pins git:20261101.21c88f5 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- openhands/extensions
- Path
skills/cortex-training-rl/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261101.21c88f5, committed Nov 1, 2026
- First version recorded
- Oct 27, 2026
- Size
- 10,777 bytes
- Repository stars
- 179
- License
- MIT
Run reinforcement-learning post-training of a model inside the OpenHands agent harness on Snowflake Cortex Training for any Harbor training and eval task directories or SWE-smith code localization, and generate the reward convergence graph. Use when asked to launch, monitor, debug, stop, or plot an OpenHands or Harbor RL run on Cortex Training.
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
# OpenHands RL post-training on Cortex Training The trainer and the sampler run on Cortex Training GPUs (`4 training + 4 sampling H200s`). Your machine runs a CPU-only driver that executes OpenHands rollouts against a local OpenAI-compatible proxy (`ChatCompletionsProxy`) and sends the exact sampled token IDs (`loss_mask = 1` on assistant turns, `0` on prompts and tool outputs) plus verifier rewards back to Cortex for a GSPO/GRPO update. Two recipes ship in [Arctic Platform](https://github.com/Snowflake-AI-Research/Arctic-Platform): 1. **Harbor RL (`recipes/rl/harbor` + `arctic_platform/integrations/harbor`, [PR #294](https://github.com/Snowflake-AI-Research/Arctic-Platform/pull/294)):** Takes any Harbor training and eval task directories (`TRAIN_HARBOR_TASKS` and `EVAL_HARBOR_TASKS`, each task containing `instruction.md`, `environment/`, and `tests/test.sh`) and any target OpenHands agent (`HARBOR_SKILL`, `OPENHANDS_TOOLS`, `OPENHANDS_SYSTEM_PROMPT_FILE`, or `HARBOR_AGENT`). Each rollout is orchestrated by Harbor's `Trial` and scored by Harbor's `Verifier` (`tests/test.sh` $\to$ `/logs/verifier/reward.txt` or `reward.json`). …
Read the whole file at its exact version.
How to install
mdr add openhands/extensions/cortex-training-rl@sha256:a429239bb79453a5The line at the top of this page pins the label git:20261101.21c88f5, 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.
[](https://markdownregistry.com/a/art_mglhh2u7ay4ol2cr)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Oct 27, 2026 and Nov 1, 2026, about one every 5 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261101.21c88f5 latest | 2026-11-01 | 21c88f5 | 10,777 B | A | view · diff |
| git:20261027.f7b18a5 | 2026-10-27 | f7b18a5 | 7,702 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (10777 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
openhands/extensions · 179 stars · license MIT · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_mglhh2u7ay4ol2cr GET https://markdownregistry.com/api/v1/resolve?ref=openhands/extensions/cortex-training-rl GET https://markdownregistry.com/api/v1/blob/a429239bb79453a519a4d5fd4186f569c5dc889f96ae9847008fd1514917cef0
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.