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.
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.
curl -O https://raw.githubusercontent.com/areal-project/AReaL/main/.agents/skills/upgrade-deps/SKILL.mdgit clone --depth 1 https://github.com/areal-project/AReaLWrote 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.
[](https://agentmods.dev/skills/areal-project/areal/upgrade-deps)<a href="https://agentmods.dev/skills/areal-project/areal/upgrade-deps"><img src="https://agentmods.dev/badge/skills/areal-project/areal/upgrade-deps/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.
<a href="https://agentmods.dev/skills/areal-project/areal/upgrade-deps"><img src="https://agentmods.dev/badge/skills/areal-project/areal/upgrade-deps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 Tool Misuse · line 463 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Prompt Injection · line 540 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.05589 |
| Opus 5 | $0.00026 | $0.02795 |
| Sonnet 5 | $0.00010 | $0.01118 |
| Haiku 4.5 | $0.00005 | $0.00559 |
Grade C, and why
upgrade-deps scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "${REPO_ROOT}/<package>-src" How it starts
The opening of the file, as written. The whole thing — 550 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Usage
/upgrade-deps <package==version> [<package==version> ...]
Arguments: One or more pinned package versions, e.g.,
/upgrade-deps megatron-core==0.17.0 sglang==0.5.10 vllm==0.18.0 transformers==4.58.0.
If a package is omitted, its current version can be preserved or upgraded, depending on
the resolution of uv lock.
Architecture
Dual-Manifest Model
AReaL maintains two pyproject files because SGLang and vLLM pin
mutually-incompatible torch / torchao versions:
| File | Inference backend | Lock file |
|---|---|---|
pyproject.toml |
SGLang (default) | uv.lock |
pyproject.vllm.toml |
vLLM | uv.vllm.lock |
Both share the same core dependencies, megatron extras, and dev group. They diverge only
in inference backend extras and torch/torchao version constraints.
The Dockerfile builds both variants from a single file using ARG VARIANT (sglang
or vllm). The base image, torch install, and flash-attn wheels are all
variant-specific.
Focused Packages
The following packages are focused — their API usage in AReaL is cataloged, and any version change triggers the API compatibility audit (Step 6):
| Package | Import path |
|---|---|
megatron-core |
megatron.core |
megatron-bridge |
megatron.bridge |
mbridge |
mbridge |
transformers |
transformers |
sglang |
sglang |
vllm |
vllm |
peft |
peft |
torchao |
torchao |
torch is tracked in the Package Impact Matrix below for scope and Docker awareness,
but is not a focused package — it does not receive API auditing.
Package Impact Matrix
Every entry below has a variant scope that determines which files to edit, which
lock files to regenerate, and whether the Dockerfile needs review. All focused packages
plus torch (tracked for Docker impact only, not API-audited) are listed.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 550 lines · 52 tokens per session scan C a1912969c875
upgrade-deps is a skill published in the GitHub repository areal-project/AReaL (5,739 stars, last pushed today), licensed Apache-2.0. It adds 52 tokens to every session and 5,589 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agent-lightning
Provides the action space, tradeoffs, and evaluation context for improving an editable AI agent against a benchmark while preserving its deployment contract. Use when optimizing agent accuracy, cost, latency, or reliability.
slime-rl-training
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
duckduckgo-search
Free keyless web, news, and image search via ddgs.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.