finetuning

finetuning is a skill for Claude Code, Codex from evo-hq/evo. It costs 95 tokens per session (4,106 once invoked), scanned A, original, Apache-2.0.

A guide for choosing and diagnosing ways to fine-tune a machine-learning model, meaning update its weights so it behaves better for a specific task.

In plain words
What is it for?
Use it when planning or debugging SFT, LoRA, preference-based training, reinforcement learning, reward design, or model weight updates.
Why use it?
It helps match the training method to the kind of feedback available, such as examples, preferences, or testable answers. It also calls for held-out evaluation data, which is data kept separate to check whether training really worked.

Skill for Claude CodeCodex

Part of the evo plugin — 7 skills, 2 commands, 3 agents, 6 hooks shipped together

About the project

Evo is an agent plugin that turns a codebase into an automated experiment loop, discovering metrics, changing code, and testing whether those changes improve the results. It is used to optimize software through parallel subagents, tree-based exploration, shared experiment records, and optional regression or safety gates. The catalogue entries provide agent skills, hooks, commands, and other workflow components for operating Evo.

evo-hq/evo · 1,441 stars · on GitHub

Install

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.

agentmods
npx agentmods add skills/evo-hq/evo/finetuning
Any agent
npx skills add evo-hq/evo --skill finetuning
Clone the repo
git clone --depth 1 https://github.com/evo-hq/evo

Made for: Claude Code, Codex.

Or install evo, the plugin that ships this one along with the rest of its 7 skills, 2 commands, 3 agents, 6 hooks.

Wrote 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.

agentmods badge for finetuning

README.md
[![agentmods](https://agentmods.dev/badge/skills/evo-hq/evo/finetuning.svg)](https://agentmods.dev/skills/evo-hq/evo/finetuning)
Your own site
<a href="https://agentmods.dev/skills/evo-hq/evo/finetuning"><img src="https://agentmods.dev/badge/skills/evo-hq/evo/finetuning.svg" alt="Measured on agentmods" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,106 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00095 $0.04106
Opus 5 $0.00048 $0.02053
Sonnet 5 $0.00019 $0.00821
Haiku 4.5 $0.00010 $0.00411

Measured 5d ago against content hash ea19415079d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

finetuning 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 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.

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.

plugins/evo/skills/finetuning/SKILL.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Finetuning

Priors, not rules. Only firm guardrails: held-out eval you never train on, no leakage, trust evo's recorded numbers over the run's self-report. Override anything else against the gate.

Pick the technique by reward shape

Decide on the reward first, technique second. Choosing the comfortable technique over the matching one is the most common failure.

Reward shape Technique
Verifiable (exact match, unit tests, parser-decidable) RL (GRPO / RLOO / PPO) — reward includes format, so the model learns to emit verifier-acceptable shape
Preference pairs (chosen vs rejected) DPO / KTO / ORPO — cheaper than full RL, no rollouts
Demonstrations only (curated traces, chat data) SFT — install format/tone/capability the base lacks
Have a scorer + want SFT stability RFT — sample, filter by reward, SFT on survivors

"SFT-then-RL" is not a law. For a competent base model on a verifiable benchmark, RL-from-base often beats SFT-then-RL end-to-end.

Research the literature before the first commit

The decision tree above is the structural prior. The empirical answer for this model on this benchmark usually has a recent paper, blog, or HF Space recipe behind it -- and what beats baseline on a 4B base model in 2026 is not what the agent's pre-training data captures. Before picking the technique for exp_0001 (the first experiment after baseline), invoke evo:ideator with a literature brief:

Task(
    subagent_type="evo:ideator",
    prompt="brief=literature\n"
           "model_family=<e.g. Qwen3-4B-Base, Llama-3.1-8B-Base>\n"
           "benchmark=<name + URL/paper if known>\n"
           "objective=<one line: what beats baseline looks like>\n"
           "constraints=<budget, data sources allowed, gated models forbidden, etc>"
)

The ideator returns ranked proposals with references (arXiv, HF Hub, GitHub, blogs). Read them before picking from the reward-shape table. A paper showing GRPO-from-base works on <model_family> for a similar verifiable benchmark beats applying the table cold.

Read the full file on GitHub · 234 lines

Files

What ships with it

8 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.

Changes

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.

  1. 5d ago First seen · 234 lines · 95 tokens per session scan A ea19415079d8

Subscribe to this mod's changes

finetuning is a skill published in the GitHub repository evo-hq/evo (1,441 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 95 tokens to every session and 4,106 once invoked, about $0.0005 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.