fine-tune

fine-tune is a skill for Claude Code, Codex from subhansh-dev/agent-maxxing. It costs 33 tokens per session (757 once invoked), scanned A, original, MIT.

A collection of instructions for changing an AI coding agent’s personality, reasoning, coding habits, and communication style. It can be added to the agent’s permanent instructions or loaded for specific tasks.

In plain words
What is it for?
Use it to tune how an agent writes code, plans work, designs interfaces, uses tools, coordinates other agents, and communicates.
Why use it?
It gives the agent consistent guidance instead of relying on its default behaviour for every session.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Good fit Use it to tune how an agent writes code, plans work, designs interfaces, uses tools, coordinates other agents, and communicates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/subhansh-dev/agent-maxxing/00-fine-tune
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.

Any agent
npx skills add subhansh-dev/agent-maxxing --skill 00-fine-tune
Clone the repo
git clone --depth 1 https://github.com/subhansh-dev/agent-maxxing

Made for: Claude Code, Codex.

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 fine-tune

README.md
[![agentmods](https://agentmods.dev/badge/skills/subhansh-dev/agent-maxxing/00-fine-tune/github.svg)](https://agentmods.dev/skills/subhansh-dev/agent-maxxing/00-fine-tune)
Your own site
<a href="https://agentmods.dev/skills/subhansh-dev/agent-maxxing/00-fine-tune"><img src="https://agentmods.dev/badge/skills/subhansh-dev/agent-maxxing/00-fine-tune/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.

agentmods 80×15 button for fine-tune

Your own site · 80×15
<a href="https://agentmods.dev/skills/subhansh-dev/agent-maxxing/00-fine-tune"><img src="https://agentmods.dev/badge/skills/subhansh-dev/agent-maxxing/00-fine-tune.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 757 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00033 $0.00757
Opus 5 $0.00016 $0.00378
Sonnet 5 $0.00007 $0.00151
Haiku 4.5 $0.00003 $0.00076

Measured 5d ago against content hash 2f1123504742, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

fine-tune 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.

system-prompts/00-FINE-TUNE/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Fine-Tune System

This folder contains carefully extracted patterns from leaked system prompts of the world's most advanced AI agents — Claude Fable 5, GPT-5.5 Codex, Gemini CLI, Claude Code, and more. Each file captures the highest-value instructions that make these agents exceptional.

How to Use

Option 1: Permanent Integration (Recommended)

Add this to your agent's system prompt or CLAUDE.md / AGENTS.md:

## Agent Fine-Tune

Read and apply the instructions in these files on every session:
1. `system-prompts/01-agent-core-personality.md` — Core personality, memory, and communication
2. `system-prompts/02-coding-excellence.md` — Engineering judgment and code quality
3. `system-prompts/03-reasoning-planning.md` — Thinking, planning, and decision-making
4. `system-prompts/04-frontend-mastery.md` — UI/UX design rules
5. `system-prompts/05-agent-orchestration.md` — Multi-agent and tool usage
6. `system-prompts/06-tone-communication.md` — How to talk and present

These override default behaviors. Follow them precisely.

Option 2: Load on Demand

When working on a specific task, load the relevant file:

  • Writing code → 02-coding-excellence.md
  • Planning/architecture → 03-reasoning-planning.md
  • Building UI → 04-frontend-mastery.md
  • Using tools → 05-agent-orchestration.md
  • Just chatting → 01-agent-core-personality.md

Option 3: Copy to Agent Directory

cp -r system-prompts/* ~/.claude/skills/fine-tune/

What Each File Extracts

File Source Prompts What It Improves
01-agent-core-personality.md Claude Fable 5, Opus 4.8 Personality, memory, tone, refusal handling
02-coding-excellence.md Codex GPT-5.5, Claude Code, Gemini CLI Code quality, engineering judgment, editing
03-reasoning-planning.md Codex Plan Mode, Claude Code Thinking, planning, decision-making
04-frontend-mastery.md Codex GPT-5.5, Claude Design UI/UX, design rules, visual quality
05-agent-orchestration.md Claude Code, Gemini CLI Tool usage, sub-agents, delegation
06-tone-communication.md Claude Fable 5, Codex GPT-5.5 Communication style, formatting

Read the full file on GitHub · 68 lines

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 · 68 lines · 33 tokens per session scan A 2f1123504742

Subscribe to this mod's changes

fine-tune is a skill published in the GitHub repository subhansh-dev/agent-maxxing (2 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 757 once invoked, about $0.0002 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 2026-09-03.