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 ralfyishere/rules-with-receipts --skill prompt-engineeringgit clone --depth 1 https://github.com/ralfyishere/rules-with-receiptsWrote 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/ralfyishere/rules-with-receipts/prompt-engineering)<a href="https://agentmods.dev/skills/ralfyishere/rules-with-receipts/prompt-engineering"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/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/ralfyishere/rules-with-receipts/prompt-engineering"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/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 | $0.00097 | $0.01642 |
| Opus 5 | $0.00048 | $0.00821 |
| Sonnet 5 | $0.00019 | $0.00328 |
| Haiku 4.5 | $0.00010 | $0.00164 |
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 9d 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.
Prompt Engineering
Purpose
A prompt is a program whose runtime is a model: it has specifiable behavior, test cases, regressions, and bugs. Most prompt "improvement" is vibe-editing — adding emphasis and adjectives without a single concrete failing example in hand, then declaring the result better without running it. This skill imposes the engineering loop: specify behavior → diagnose the actual failure → make one precise change → test against cases → keep versions.
When to use this skill
- Improving an existing prompt, especially "the model keeps doing X" complaints.
- Writing new system prompts, agent instructions, or reusable templates where behavior matters and the prompt will run many times.
- Reviewing a prompt that has accreted patches ("ALWAYS do A. NEVER do B. IMPORTANT: remember A...").
When NOT to use this skill
- One-off conversational asks — just ask well; the loop's overhead needs reuse to pay off.
- When the problem is the task, not the prompt: if the model lacks the information or capability, no wording fixes it — restructure the task (provide the context, split the steps, add tools) instead of engineering the incantation.
Operating procedure
1 — Specify behavior with test cases first. Before touching the prompt, write 3–5 concrete cases: input → desired output (or desired property of output). Include: the reported failing case, a normal case that currently works (your regression guard), and one edge case (empty/hostile/ambiguous input). No test cases = no way to know the edit helped.
2 — Diagnose from actual failures, not descriptions of them. Get the real failing outputs (live-state-truth: run the prompt if you can). Classify the failure:
| Failure class | Signature | Fix direction |
|---|---|---|
| Ambiguity | Model does a reasonable other thing | Define the term; add the disambiguating example |
| Missing context | Model invents what it wasn't given | Provide the facts/data in the prompt, don't demand the model "be accurate" |
| Conflicting instructions | Behavior flips between runs; late instructions ignored | Find and resolve the conflict — don't add a third instruction to arbitrate two |
| Underspecified format | Content right, shape wrong/inconsistent | Show the format: a literal example output beats three sentences describing it |
| Buried instruction | Long prompt; the violated rule is in the middle | Restructure: critical constraints near the top, grouped, deduplicated |
| Capability gap | Fails all wordings of the same demand | Restructure the task (steps, tools, context) — see "When NOT" |
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.
- 9d ago First seen · 82 lines · 0 tokens per session scan A 364fa25c0e32
Prompt Engineering is a skill published in the GitHub repository ralfyishere/rules-with-receipts (2 stars, last pushed 2mo ago), licensed MIT. It adds 97 tokens to every session and 1,642 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 2026-08-31.
Other skills, from other repositories
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.
outlines
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library.
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
create-simple-prompt
This skill should be used when the user asks to "create a new prompt sample", "add a new prompt sample", "scaffold a new prompt sample", "create a prompt contribution", "add a prompt", or needs to create a new prompt sample with proper folder structure, README, and sample.json metadata. Do NOT use this skill for agent…
prompt-context-engineer
Transform any rough prompt, request, or idea into a well-structured, context-engineered prompt using Andrej Karpathy's context engineering principles. Use this skill whenever the user asks to improve, rewrite, restructure, optimize, or "engineer" a prompt; mentions prompt engineering or context engineering; pastes a…