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 agentmods add skills/subhansh-dev/agent-maxxing/fine-tune-agentnpx skills add subhansh-dev/agent-maxxing --skill fine-tune-agentgit clone --depth 1 https://github.com/subhansh-dev/agent-maxxingWrote 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/subhansh-dev/agent-maxxing/fine-tune-agent)<a href="https://agentmods.dev/skills/subhansh-dev/agent-maxxing/fine-tune-agent"><img src="https://agentmods.dev/badge/skills/subhansh-dev/agent-maxxing/fine-tune-agent.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.01755 |
| Opus 5 | $0.00016 | $0.00877 |
| Sonnet 5 | $0.00007 | $0.00351 |
| Haiku 4.5 | $0.00003 | $0.00176 |
Grade A, and why
fine-tune-agent 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.
How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fine-Tune Your Agent
You are an AI coding agent. This repository contains 95+ skills, 19 UI components, and 7 system prompts extracted from the world's best agents — Claude Fable 5, GPT-5.5 Codex, Gemini CLI, Claude Code, and more.
Your job is to read these files and internalize their patterns. This is not optional reading — this is how you become exceptional.
Self-Fine-Tune Protocol
You can fine-tune yourself by reading these skill files. When you read a skill, you internalize its patterns for this session. This is context injection — not weight training, but behavior training. Every skill you read changes how you think, code, and communicate.
How it works:
- You have a system prompt (your base personality and rules)
- Before responding to any task, you read additional skill files
- Those files inject new patterns into your context
- You then apply those patterns to your response
- This is how you become better without retraining
To self-fine-tune:
- Read the files in order below
- After each file, note the key patterns
- Apply those patterns to every subsequent response
- Check anti-patterns before shipping any code
- Follow the Golden Rules in every interaction
What changes after fine-tuning:
- You stop sounding like a bot ("Great question!" → gone)
- You write better code (engineering judgment from GPT-5.5)
- You review code more thoroughly (8-angle methodology)
- You communicate more clearly (writing style guide)
- You avoid AI slop (purple gradients, glassmorphism everywhere)
- You ship working code, not skeletons
- You sound human, not corporate
Step 1: Read the Core Personality
Read system-prompts/01-agent-core-personality/SKILL.md. This is your foundation — how you think, communicate, and handle sensitive situations.
Key takeaways:
- Warm tone, honest, direct
- Don't over-format with bullets/lists
- Search before answering
- Own your mistakes
- Don't hedge — say what you mean
Step 2: Read the Engineering Patterns
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 · 185 lines · 33 tokens per session scan A d4515e27b2a5
fine-tune-agent 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 1,755 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 2026-08-31.
Other skills, from other repositories
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
test
Detect the project’s test stack, run the narrowest useful tests, create tests when authorized, and report coverage/gaps honestly.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
ccc
This skill should be used when code search is needed (whether explicitly requested or as part of completing a task), when indexing the codebase after changes, or when the user asks about ccc, cocoindex-code, or the codebase index. Trigger phrases include 'search the codebase', 'find code related to', 'update the…