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 vignesh2027/AI-AGENT-SKILLS --skill prompt-engineeringgit clone --depth 1 https://github.com/vignesh2027/AI-AGENT-SKILLSWrote 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/vignesh2027/ai-agent-skills/prompt-engineering)<a href="https://agentmods.dev/skills/vignesh2027/ai-agent-skills/prompt-engineering"><img src="https://agentmods.dev/badge/skills/vignesh2027/ai-agent-skills/prompt-engineering/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/vignesh2027/ai-agent-skills/prompt-engineering"><img src="https://agentmods.dev/badge/skills/vignesh2027/ai-agent-skills/prompt-engineering.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 | $0.00018 | $0.00737 |
| Opus 5 | $0.00009 | $0.00368 |
| Sonnet 5 | $0.00004 | $0.00147 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade A, and why
prompt-engineering 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Prompts are code. They have bugs, regressions, and security vulnerabilities. This skill applies software engineering discipline to prompt development: version control, testing, structured output validation, and safety evaluation.
When to Use
- Before integrating any LLM into a product feature
- When a prompt is behaving inconsistently
- Before shipping a prompt to production
- When iterating on prompt quality
Process
Step 1: Define the task precisely
Write the exact input → output contract for the prompt. What is the input format? What is the output format? What constitutes a correct output? What constitutes a failure?
Step 2: Collect a golden dataset
Gather 20–50 representative inputs with verified correct outputs. This is your test suite. Without it, you are guessing.
Step 3: Write the initial prompt
Start with the simplest possible prompt. State: role, task, constraints, output format. Be explicit about what the model should NOT do.
Step 4: Add examples (few-shot)
Provide 3–5 representative examples that demonstrate the correct behavior. Examples are more reliable than instructions for complex formatting tasks.
Step 5: Specify the output format
For structured outputs: require JSON or XML with a schema. Validate all outputs against the schema. Reject non-conforming outputs rather than guessing.
Step 6: Evaluate on the golden dataset
Run your prompt against all test cases. Score: accuracy, format compliance, latency, cost. Document the baseline.
Step 7: Iterate and track changes
Every change to a prompt is a code change. Version it. Track which version produced which score. Never overwrite a working prompt without knowing the delta.
Step 8: Safety and guardrails
Test for:
- Prompt injection (user input that overwrites your instructions)
- Jailbreaks (attempts to bypass role restrictions)
- Harmful outputs (toxicity, bias, PII)
- Hallucination (false factual claims)
Add a system prompt safety layer. Add output filtering. Document what is out of scope.
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 · 82 lines · 18 tokens per session scan A 47d3228081df
prompt-engineering is a skill published in the GitHub repository vignesh2027/AI-AGENT-SKILLS (1 stars, last pushed 14d ago), licensed MIT. It adds 18 tokens to every session and 737 once invoked, about $0.0001 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
context-engineering-advisor
Diagnose context stuffing vs. context engineering. Use when an AI workflow feels bloated, brittle, or hard to steer reliably.
ai-evaluation-engineering
An AI evaluation engineering specialist for testing models and prompts. The description does not provide enough detail to state which concrete operations it performs.
cursor-langchain
Cursor IDE rules for langchain.
create-pi-prompt
Como criar prompt templates para pi. Use quando o usuário quiser criar atalhos /comando que expandem em prompts completos.
mdc-openai
This guide provides definitive, actionable best practices for developing with the OpenAI API, covering prompt engineering, robust client usage, agent design, and testing.
mdc-llm-prompt-engineering
Dedicates a module or files for managing Prompt templates with version control for LLM applications.