prompt-engineer

prompt-engineer is a skill for Claude Code, Codex from OpenCoven/coven. It costs 168 tokens per session (1,049 once invoked), scanned A, original, MIT.

A guide for designing, improving, testing, and evaluating prompts: the instructions given to a large language model. It covers prompt structure, examples, cost, speed, and safety.

In plain words
What is it for?
Use it to write or refine system prompts, user prompts, templates, few-shot examples, evaluation plans, and safeguards against unsafe or manipulated input.
Why use it?
It helps make model behavior more reliable and makes trade-offs between quality, token usage, latency, and cost easier to assess.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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.

agentmods
npx agentmods add skills/opencoven/coven/prompt-engineer
Any agent
npx skills add OpenCoven/coven --skill prompt-engineer
Clone the repo
git clone --depth 1 https://github.com/OpenCoven/coven

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 prompt-engineer

README.md
[![agentmods](https://agentmods.dev/badge/skills/opencoven/coven/prompt-engineer.svg)](https://agentmods.dev/skills/opencoven/coven/prompt-engineer)
Your own site
<a href="https://agentmods.dev/skills/opencoven/coven/prompt-engineer"><img src="https://agentmods.dev/badge/skills/opencoven/coven/prompt-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 168 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,049 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00168 $0.01049
Opus 5 $0.00084 $0.00524
Sonnet 5 $0.00034 $0.00210
Haiku 4.5 $0.00017 $0.00105

Measured 6d ago against content hash d9448b6c6c55, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

prompt-engineer 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 6d 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.

skills/prompt-engineer/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Engineer

Craft and optimize LLM prompts for maximum effectiveness, consistency, and cost efficiency.

Core Workflow

1. Requirements Analysis

Before writing or editing any prompt:

  1. Identify the use case — what task the prompt must accomplish
  2. Define success criteria — accuracy target, format requirements, tone
  3. Understand constraints — token budget, latency ceiling, cost limit, model choice
  4. Review existing prompts and their failure modes (if any)
  5. Determine safety requirements — input validation, output filtering, injection defense

2. Prompt Design

Select the appropriate pattern based on task complexity. See references/patterns.md for detailed guidance on each.

Complexity Pattern When to Use
Simple Zero-shot Clear task, model already knows the domain
Medium Few-shot Specific format or style needed
Complex Chain-of-thought Multi-step reasoning required
Branching Tree-of-thought Multiple valid approaches to explore
Agentic ReAct Tool use + reasoning interleaved
Safety Constitutional AI Output must pass ethical/policy filters

Design principles:

  • Instruction clarity — state the task, constraints, and output format explicitly
  • Minimal tokens — every token must earn its place; compress without losing meaning
  • Modular structure — separate system prompt, context, instructions, and examples
  • Variable placeholders — use {{variable}} for dynamic content injection
  • Error recovery — include fallback instructions for ambiguous or invalid input

3. Optimization

Iterate on prompts to reduce cost and improve quality:

  • Token reduction — remove redundant phrasing, compress examples, use abbreviations the model understands
  • Context compression — summarize long context; only include what the model needs for the current step
  • Output constraints — specify format (JSON, markdown, list) to reduce parsing overhead
  • Caching — identify static prompt sections that can be cached across calls
  • Batch processing — group similar requests when possible

Read the full file on GitHub · 110 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 110 lines · 168 tokens per session scan A d9448b6c6c55

Subscribe to this mod's changes

prompt-engineer is a skill published in the GitHub repository OpenCoven/coven (46 stars, last pushed yesterday), licensed MIT. It adds 168 tokens to every session and 1,049 once invoked, about $0.0008 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.