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 DeAI1227/God-Of-Prompt --skill gopgit clone --depth 1 https://github.com/DeAI1227/God-Of-PromptWrote 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/deai1227/god-of-prompt/gop)<a href="https://agentmods.dev/skills/deai1227/god-of-prompt/gop"><img src="https://agentmods.dev/badge/skills/deai1227/god-of-prompt/gop/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/deai1227/god-of-prompt/gop"><img src="https://agentmods.dev/badge/skills/deai1227/god-of-prompt/gop.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 | $0.00040 | $0.01138 |
| Opus 5 | $0.00020 | $0.00569 |
| Sonnet 5 | $0.00008 | $0.00228 |
| Haiku 4.5 | $0.00004 | $0.00114 |
Grade A, and why
gop 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GOP — God Of Prompt
Turn a requirement into a six-part XML system prompt, show it, then apply it immediately. Use the workshop's Starter → Context → Task → Examples → Output → Repeat structure as the prompt skeleton. Use MUST / SHOULD / MAY, acceptance criteria, and failure handling as cross-cutting controls.
Read references/evidence-map.md before drafting. It defines the workshop-to-paper mapping and its limits.
Non-negotiable response contract
Return exactly two ordered sections and nothing else:
## 完整 System Promptcontaining one complete copy-ready XML prompt in atextfence.## 執行結果containing the result of applying that prompt to the original requirement and supplied material.
Do not ask for prompt approval, confirmation, copy-and-paste, or a second turn. Do not expose drafting analysis, hidden reasoning, scoring, test plans, paper citations, or version notes. For a role-only requirement, execute by asking the target system's first necessary question.
Build the prompt
1. Extract the operating brief
Identify the user, mission, supplied inputs, trusted sources or tools, factual boundary, desired deliverable, language, constraints, risk level, and observable success condition. Make conservative, low-risk defaults for non-material gaps. If an ambiguity blocks safe or correct execution, state the missing information and ask one targeted question in the execution result; never invent it.
2. Use this XML shape every time
<system_prompt version="2.0">
<starter>Role or mission in one or two sentences.</starter>
<context>Only facts, audience, inputs, and boundaries that change judgment.</context>
<task>
<mission>Executable task.</mission>
<rules>
<MUST>Non-negotiable permissions, data, content, and output boundaries.</MUST>
<SHOULD>Default quality strategy that may yield to an explicit user need.</SHOULD>
<MAY>Optional tools, presentation choices, or safe fallbacks.</MAY>
</rules>
<acceptance_criteria>Verifiable completion conditions.</acceptance_criteria>
<failure_handling>What to ask, label, decline, or escalate when evidence or authority is missing.</failure_handling>
</task>
<examples>Representative demonstrations or an explicit statement that none are needed.</examples>
<output>Container, headings or fields, order, length, evidence treatment, and missing-data behavior.</output>
<repeat>One or two critical reminders only.</repeat>
</system_prompt>
What ships with it
2 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.
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 · 76 lines · 40 tokens per session scan A 4320fcc9c64a
gop is a skill published in the GitHub repository DeAI1227/God-Of-Prompt (2 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,138 once invoked, about $0.0002 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.
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…
forensic-prompt-compiler
Forensic image-to-prompt compiler for image generation models. Use this skill whenever the user wants to: convert/describe an existing image into a generation prompt, reconstruct a scene as a prompt, generate prompts from reference images for AI image tools (Midjourney, FLUX, Stable Diffusion, DALL-E, or any diffusion…
llm-engineering-expert
Build reliable applications on large language models: prompt design, structured output, evaluation, guardrails, and cost and latency control. Use when the user mentions LLMs, prompts, prompt engineering, few-shot examples, structured or JSON output, function calling, hallucination, model evaluation, token costs…
ai-engineering-toolkit
AI Engineering Toolkit workflow skill. Use this skill when the user needs 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 and the operator…
prompt-optimization
Improves LLM-facing context while preserving intent, execution boundaries, and proportional work. Use when creating or reviewing prompts, agent definitions, skill definitions, or other instructions for an LLM.