Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/svngoku/coding-agents-skillsnpx agentmods add skills/svngoku/coding-agents-skills/prime-rlWrote 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/svngoku/coding-agents-skills/prime-rl)<a href="https://agentmods.dev/skills/svngoku/coding-agents-skills/prime-rl"><img src="https://agentmods.dev/badge/skills/svngoku/coding-agents-skills/prime-rl/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/svngoku/coding-agents-skills/prime-rl"><img src="https://agentmods.dev/badge/skills/svngoku/coding-agents-skills/prime-rl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00129 | $0.04198 |
| Opus 5.5 | $0.00052 | $0.01679 |
| Sonnet 5.5 | $0.00026 | $0.00840 |
| Haiku 4.5 | $0.00013 | $0.00420 |
Grade C, and why
prime-rl scanned grade C with 2 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 5d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -sSL https://raw.githubusercontent.com/PrimeIntellect-ai/prime-rl/main/scripts/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sSL https://raw.githubusercontent.com/PrimeIntellect-ai/prime-rl/main/scripts/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prime-rl Post-Training
prime-rl is Prime Intellect's framework for
asynchronous RL and SFT post-training at scale. One launch (uv run rl) starts a vLLM inference
server, a CPU-only orchestrator that collects rollouts from
verifiers environments, and an FSDP trainer that
pushes new weights back to inference. This skill teaches how to install it, write configs, choose
an algorithm, launch and monitor runs, evaluate checkpoints, and export weights.
Facts are checked against upstream commit dd72f0f (2026-10-13, v0.9.0). When the docs and the
code disagree, this skill follows the code (see Doc Drift).
Quick Reference
| Topic | Reference | When to read |
|---|---|---|
| Install, uv sync, extras, env packages | references/install.md | Fresh machine, missing env package, DeepEP/kernels |
| Config system (TOML + CLI) | references/configs.md | Writing or overriding any config, config errors |
| Algorithms, losses, advantages, curricula, renderers | references/algorithms.md | Choosing GRPO vs OPD vs SFT-distill, tuning the loss |
rl / sft / inference, run dirs, checkpoints, resume, export |
references/training-runs.md | Launching, resuming, exporting to HF |
| Logs, metrics, dashboard, check-in runbook | references/monitoring.md | Checking on or debugging a live run |
uv run eval, task selection |
references/eval.md | Benchmarking a model or checkpoint |
| Multi-GPU, multi-node, SLURM, LoRA, MoE, inference serving | references/scaling.md | Anything beyond one node with defaults |
Core Workflow
-
Install on a Linux box with NVIDIA GPUs (the smoke run needs 2):
curl -sSL https://raw.githubusercontent.com/PrimeIntellect-ai/prime-rl/main/scripts/install.sh | bash cd prime-rl && uv sync --all-extras
What ships with it
13 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.
- eval.yaml 971 B
- graders/check.py 8.9 KB runs code
- instructions/reverse-text-grpo-run.md 1.6 KB
- references/algorithms.md 9.6 KB
- references/configs.md 6.7 KB
- references/eval.md 4.5 KB
- references/install.md 4.7 KB
- references/monitoring.md 7.3 KB
- references/scaling.md 8.3 KB
- references/training-runs.md 8.7 KB
- rubrics/quality.md 2.0 KB
- solutions/reference-reverse-text-grpo-run/rl.toml 967 B
- solutions/reference-reverse-text-grpo-run/run.sh 643 B runs code
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.
- 5d ago First seen · 320 lines · 129 tokens per session scan C df5c8b61238f
prime-rl is a skill published in the GitHub repository svngoku/coding-agents-skills (12 stars, last pushed yesterday), licensed MIT. It adds 129 tokens to every session and 4,198 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-14.
Other skills, from other repositories
iflytek-image-understanding
An image-analysis tool that describes pictures and answers questions about what they contain. It uses an AI vision service, which interprets visual content rather than only reading text files.
ai-llm-integration-expert
Expert guide for integrating Large Language Models (LLMs), Model Context Protocol (MCP v1.x), hybrid reasoning models, RAG architecture, vector databases, and AI agents / Panduan ahli untuk integrasi LLM, Model Context Protocol (MCP), model hybrid reasoning, arsitektur RAG, vector database, dan agen AI.
multi-agent-orchestration
Expert guide for designing and orchestrating multi-agent systems, agent swarms, 2026 Anthropic agentic design patterns, graph-based workflows (LangGraph, OpenAI Agents SDK, Google ADK, Mastra.ai), shared state memory, and human-in-the-loop guardrails in English and Indonesian.
llm-finops-router
Expert guide for AI FinOps, dynamic model routing (LiteLLM, Portkey, RouteLLM), cost optimization, budget enforcement, semantic caching, and latency-based fallback architectures / Panduan ahli untuk AI FinOps, routing model dinamis, optimasi biaya, penegakan anggaran, semantic caching, dan arsitektur fallback berbasis…
vercel-ai-sdk-expert
Expert guide for Vercel AI SDK (Core, UI, RSC), streaming structured data, multi-provider model switching, tool calling loops, and React 19/Next.js 15 AI engineering / Panduan ahli Vercel AI SDK, streaming data terstruktur, dan integrasi AI pada React 19/Next.js 15.
adaptive-model-cascade
Expert guide for intelligent model cascading and routing — complexity-scored task routing from Flash/Haiku to Sonnet/Opus/Astra, dynamic escalation with quality gates, 40-60% token cost reduction while maintaining output quality / Panduan ahli untuk kaskade dan routing model cerdas — routing tugas berbasis skor…