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 mahmoud20138/Tradecraft --skill few-shot-quality-promptinggit clone --depth 1 https://github.com/mahmoud20138/TradecraftWrote 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/mahmoud20138/tradecraft/few-shot-quality-prompting)<a href="https://agentmods.dev/skills/mahmoud20138/tradecraft/few-shot-quality-prompting"><img src="https://agentmods.dev/badge/skills/mahmoud20138/tradecraft/few-shot-quality-prompting/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/mahmoud20138/tradecraft/few-shot-quality-prompting"><img src="https://agentmods.dev/badge/skills/mahmoud20138/tradecraft/few-shot-quality-prompting.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 | $0.00102 | $0.03511 |
| Opus 5 | $0.00051 | $0.01755 |
| Sonnet 5 | $0.00020 | $0.00702 |
| Haiku 4.5 | $0.00010 | $0.00351 |
Grade A, and why
few-shot-quality-prompting 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 12d 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 — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Few-Shot Quality Prompting Skill — Engineering AI Output Excellence
Identity
You are a prompt engineering specialist who knows that the difference between mediocre and exceptional AI output is 90% prompt design and 10% model capability. You design prompts as carefully as you design code — with structure, testing, and iteration.
CORE INSIGHT
The model is a mirror. It reflects the quality level you demonstrate in your prompt.
Show it amateur code → get amateur code. Show it senior-engineer code → get senior-engineer code. Show it nothing → get generic defaults.
SYSTEM PROMPT ARCHITECTURE
The 7-Layer System Prompt
┌─────────────────────────────────────┐
│ LAYER 1: IDENTITY │ Who is the AI? (role, expertise level)
├─────────────────────────────────────┤
│ LAYER 2: CONTEXT │ What's the project? (stack, constraints)
├─────────────────────────────────────┤
│ LAYER 3: SKILLS │ Domain knowledge (loaded dynamically)
├─────────────────────────────────────┤
│ LAYER 4: GOLDEN EXAMPLES │ 2-3 examples of perfect output
├─────────────────────────────────────┤
│ LAYER 5: ANTI-PATTERNS │ Explicit "NEVER do this" list
├─────────────────────────────────────┤
│ LAYER 6: OUTPUT FORMAT │ Exact structure of response
├─────────────────────────────────────┤
│ LAYER 7: QUALITY GATES │ Self-check before responding
└─────────────────────────────────────┘
Layer-by-Layer Construction
Layer 1: Identity
WEAK: "You are a helpful coding assistant."
STRONG: "You are a senior frontend engineer at a design-focused studio
with 10 years of experience shipping production React applications.
You have strong opinions about clean architecture and refuse to
write code you wouldn't approve in a code review."
The identity sets the quality floor. "Senior engineer at Stripe" produces better code than "helpful assistant" because the model activates different knowledge distributions.
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.
- 12d ago First seen · 464 lines · 102 tokens per session scan A 672a2660b041
few-shot-quality-prompting is a skill published in the GitHub repository mahmoud20138/Tradecraft (15 stars, last pushed 4mo ago), licensed MIT. It adds 102 tokens to every session and 3,511 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.
Other skills, from other repositories
prompt-engineering
Use when writing or improving prompts for a language model. Covers instruction structure, examples, reasoning elicitation, output formatting, and systematically diagnosing why a prompt fails.
structured-output
Use when an LLM must return machine-readable data. Covers schema design for models, native structured-output modes, validation and repair, and extraction that survives contact with messy input.
prompt-engineer
Expert prompt engineering for AI systems. Use when the user wants to write or review prompts for AI, create instructions for AI systems, build system prompts, review or improve existing prompts, optimize AI instructions, or create any form of written communication intended for AI consumption (Claude, GPT, or other…
Prompt Refiner
Improves AI prompts to be clearer, more specific, and produce more consistent outputs.
huashu-prompt-save
Automatically identifies the prompt type and saves it to the appropriate category (Technical / Content / Teaching / Product / General). Use when the user mentions "save prompt", "record prompt", or "organise prompts".
agent-orchestration-improve-agent
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.