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 subhansh-dev/agent-maxxing --skill 00-fine-tunegit 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/00-fine-tune)<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.
<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>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 | $0.00757 |
| Opus 5 | $0.00016 | $0.00378 |
| Sonnet 5 | $0.00007 | $0.00151 |
| Haiku 4.5 | $0.00003 | $0.00076 |
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.
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 |
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 · 68 lines · 33 tokens per session scan A 2f1123504742
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.
Other skills, from other repositories
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
writing
A writing guide for turning verified facts and calculations into finished text for a specific audience. It follows the requested language, structure, and length.
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.
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…