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 Agent-Engineer-Master/skill-engineer --skill prompt-engineer-mastergit clone --depth 1 https://github.com/Agent-Engineer-Master/skill-engineerWrote 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/agent-engineer-master/skill-engineer/prompt-engineer-master)<a href="https://agentmods.dev/skills/agent-engineer-master/skill-engineer/prompt-engineer-master"><img src="https://agentmods.dev/badge/skills/agent-engineer-master/skill-engineer/prompt-engineer-master/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/agent-engineer-master/skill-engineer/prompt-engineer-master"><img src="https://agentmods.dev/badge/skills/agent-engineer-master/skill-engineer/prompt-engineer-master.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 | $0.00109 | $0.02079 |
| Opus 5.5 | $0.00044 | $0.00832 |
| Sonnet 5.5 | $0.00022 | $0.00416 |
| Haiku 4.5 | $0.00011 | $0.00208 |
Grade A, and why
prompt-engineer-master 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 1mo 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Engineer Master
Output contract
- Produces: a single copy-pasteable prompt block in XML or 5-section prose format, plus optional usage notes
- Does NOT produce: implementation code, prompt evaluation reports, prompt explanations, or multi-turn dialogue scaffolds
- Enables: the user or calling agent to paste the output directly into a system prompt, agent config, or project instruction file
- Consumed by: the user directly, or an agent pipeline that needs a system prompt as input
Canonical source
Read references/prompt-engineer-master.txt before generating any prompt — it contains the production patterns, XML skeleton, real-world examples, and the 10-point production checklist to adapt from.
Step 1 — Gather context (skip if sufficient detail already given)
Ask at most 3 clarifying questions. Only ask if the answer would materially change the prompt:
- What is the task and the deliverable?
- What is the audience and success criteria?
- Any constraints — tools available, tone, forbidden items, or trust level of inputs (user-typed vs server-injected vs retrieved from docs)?
If the user has given enough detail, proceed immediately to Step 2.
Step 2 — Research prior art and domain context
Skip this step if the request is for a simple single-purpose task prompt (single-source, no tools, no irreversible actions — i.e., anything that would use lightweight 5-section prose structure). Go directly to Step 3.
Read references/research-guide.md for full query specs, librarian sub-agent prompt, and synthesis format.
Run two tracks in parallel:
Track A — Prior art (inline): Search for existing prompts in this domain. Sources: Anthropic prompt library, GitHub system prompt repos, community repos, r/PromptEngineering. See research-guide.md §2 for queries.
Track B — Domain research (spawn librarian sub-agent): Read agents/librarian.md and spawn a sub-agent using those instructions. Research what makes this task domain work well — best practices, failure modes, practitioner vocabulary. Use the librarian agent prompt in research-guide.md §3.
What ships with it
10 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.
- agents/librarian.md 6.6 KB
- assets/approved-examples/.gitkeep 0 B
- assets/approved-examples/the-inversion-toc-prompt.md 5.8 KB
- evals/evals.json 6.0 KB
- README.md 2.7 KB
- references/edge-cases.md 201 B
- references/example-outputs.md 9.1 KB
- references/learnings.md 531 B
- references/prompt-engineer-master.txt 18 KB
- references/research-guide.md 5.0 KB
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.
- 1mo ago First seen · 135 lines · 0 tokens per session scan A bb8df76abdc3
prompt-engineer-master is a skill published in the GitHub repository Agent-Engineer-Master/skill-engineer (8 stars, last pushed 3mo ago), licensed MIT. It adds 109 tokens to every session and 2,079 once invoked, about $0.0004 per session on Opus 5.5. 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
agent-evolution
A guide to making an AI agent improve from its past runs. It covers how to judge results, extract reusable lessons, and decide whether to store them as knowledge, instructions, code, or model training.
post-training-strategy
A guide to choosing and planning ways to improve an AI model after its initial training. It explains when to add knowledge, teach a response format, use trial-and-error training, or use a smaller model to learn from a larger one.
refine
Improve a prompt using official OpenAI or Claude guidance. Text or @file mode; --for openai or --for claude selects guidance, not a runtime model.
prompt-writer
Write maximally terse agent prompts from scratch. Use when creating agent specs, command prompts, or instruction sets with constitutional governance.
tersify-prompt
Rewrites agent-instruction prompts to be maximally terse while preserving full intent.
opus-4-5-migration
Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string updates and prompt adjustments for known Opus 4.5 behavioral differences. Does NOT migrate Haiku 4.5.