Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add vasilyu1983/AI-Agents-public --skill ai-post-traininggit clone --depth 1 https://github.com/vasilyu1983/AI-Agents-publicWrote 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/vasilyu1983/ai-agents-public/ai-post-training)<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/ai-post-training"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/ai-post-training/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/vasilyu1983/ai-agents-public/ai-post-training"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/ai-post-training.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00053 | $0.04984 |
| Opus 5 | $0.00026 | $0.02492 |
| Sonnet 5 | $0.00011 | $0.00997 |
| Haiku 4.5 | $0.00005 | $0.00498 |
Grade A, and why
ai-post-training scanned grade A with 0 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 7d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Post-Training
Domain: the rung after supervised fine-tuning — turning a pretrained or SFT'd base model into an aligned, preference-tuned, or reasoning-capable model with a reward signal. This skill owns the post-training decision and pipeline: when to post-train at all, which reward signal you can produce, which algorithm family fits, and how to keep it from over-optimizing. Per-algorithm operational depth lives in ai-llm/references/post-training.md (PPO, DPO, SimPO, KTO, GRPO, GSPO, DAPO, RLVR, RULER, ORPO — catalogue + decision tree); this skill routes there.
It does not cover: pretraining (ai-pretraining), the prompt→RAG→SFT promotion ladder (ai-architecture-advisor), or serving the result (ai-llm-inference).
Quick Reference
| You have / want | Method | Deep ref |
|---|---|---|
| Labeled demonstrations of the target behavior | SFT (baseline — exhaust it first; not RL) | ai-llm |
| Pairwise preferences, want the least machinery | DPO (or DAAs: KTO / ORPO / SimPO) | methods |
| A stronger teacher model, a small student | On-policy distillation — try before GRPO | methods |
| Preferences + reward model + online RL | GRPO / RLOO (critic-free, 2026 default); PPO is the reference algorithm, now trl.experimental |
methods |
| Many samples scorable per prompt, drop the critic | GRPO (group-relative advantage) | methods |
| A real task with no mechanical checker | Rubrics as rewards (the fourth reward source) | methods |
| A multi-turn agent acting in an environment | Agentic RL (trajectory reward, rollout infra) | methods |
| A verifiable checker (math/code/tests) as the reward | RLVR (via GRPO or a GRPO-family variant — GSPO/DAPO/RLOO) — the dominant 2026 reasoning recipe | methods |
| Scale preference labels cheaply | RLAIF / Constitutional AI (model-as-judge) | data |
| A quick lift with no RL loop | Rejection sampling (best-of-N → SFT) | methods |
| Train/choose the reward model itself | Bradley-Terry RM, ORM vs PRM, generative RM | reward |
| Stop reward hacking / over-refusal | KL regularization, eval harness, over-optimization controls | over-optimization |
| Interpret a live GRPO run's metrics | Advantage mean/std, entropy, reward exhaustion, degenerate groups | diagnostics |
| Build a robust RLVR checker (not just "use a verifier") | Extract → normalize → SymPy equivalence → element-wise grading | reward |
| Compose fine-tuned checkpoints / strip an unwanted attribute | Model merging (averaging, weighted, interpolation, adapter merging) | reward |
What ships with it
7 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.
- 7d ago Changed · +55 lines d4e572870bb8
- 11d ago First seen · 228 lines · 53 tokens per session scan A 76dc0fffe93c
ai-post-training is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (87 stars, last pushed 9d ago), licensed MIT. It adds 53 tokens to every session and 4,984 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-memory-thermal-ops
Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
data-quality-frameworks
Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.
airflow-dag-patterns
Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs.
dbt-transformation-patterns
Master dbt (data build tool) for analytics engineering with model organization, testing, documentation, and incremental strategies. Use when building data transformations, creating data models, or implementing analytics engineering best practices.