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 wp-a/gpt-5.6-prompt-engine --skill gpt-5-6-prompt-enginegit clone --depth 1 https://github.com/wp-a/gpt-5.6-prompt-engineWrote 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/wp-a/gpt-5.6-prompt-engine/gpt-5-6-prompt-engine)<a href="https://agentmods.dev/skills/wp-a/gpt-5.6-prompt-engine/gpt-5-6-prompt-engine"><img src="https://agentmods.dev/badge/skills/wp-a/gpt-5.6-prompt-engine/gpt-5-6-prompt-engine/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/wp-a/gpt-5.6-prompt-engine/gpt-5-6-prompt-engine"><img src="https://agentmods.dev/badge/skills/wp-a/gpt-5.6-prompt-engine/gpt-5-6-prompt-engine.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 | $0.00058 | $0.01333 |
| Opus 5 | $0.00029 | $0.00666 |
| Sonnet 5 | $0.00012 | $0.00267 |
| Haiku 4.5 | $0.00006 | $0.00133 |
Grade A, and why
gpt-5-6-prompt-engine 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 11d 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.
GPT-5.6 Prompt Engine
Operating principle
Preserve the application's contract before optimizing the prompt. Make the smallest change that improves observable behavior, and require controlled evidence before calling a candidate better.
Workflow
- Classify the request as create, audit-only, surgical rewrite, migration, or evaluation. Combine modes only when the user asks for multiple deliverables.
- Inventory the immutable contract before editing: explicit facts and values, JSON schemas, system, developer, user, and tool trust layers, output contract, permissions, and business behavior. Preserve wording verbatim when a parser, policy, or caller may depend on it.
- Apply the material-ambiguity gate. Ask one focused question only when plausible answers would change the goal, schema, facts, permissions, evidence requirements, or success criteria. Otherwise preserve the source choice and proceed. Prompt-only or use-your-judgment pressure does not authorize choosing a contradictory branch; ask the smallest blocking question before drafting.
- Perform only the selected mode's work. Keep prompt content separate from runtime settings unless configuration is in scope.
- Validate the result against the inventory and the requested output contract. Do not silently broaden tools, actions, data access, or policy.
Create
- Start with the desired outcome and application-visible result.
- Add context, constraints, permissions, evidence, tools, validation, fallback, success, and stop clauses only when they change behavior.
- Keep tool descriptions narrow: state what the tool does, when to call it, required inputs, and meaningful side effects or limits.
- Prefer one clear rule over repeated emphasis or a giant reusable template.
Audit-only
- Identify only behavior-changing defects, quote precise evidence, explain the risk, and propose the smallest correction. Do not rewrite the prompt unless requested.
- When a source prompt or JSON tool stack is available and static signals are useful, run the prompt auditor.
- Treat the auditor's heuristics as review signals and independently verify the cited evidence. Heuristics are review signals, not proof of a conflict.
- Never infer visible chain-of-thought from a reasoning phrase; require an explicit request to expose reasoning in the output. A bare reasoning phrase does not change the output contract, so omit a bare reasoning phrase from a behavior-changing audit rather than asking about or correcting possible disclosure.
- Never infer unsafe persistence from ordinary completion wording; require evidence of a permission, stop, scope, or safety conflict.
What ships with it
7 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.
- 11d ago First seen · 82 lines · 58 tokens per session scan A e5ceb1aa5a36
gpt-5-6-prompt-engine is a skill published in the GitHub repository wp-a/gpt-5.6-prompt-engine (4 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 1,333 once invoked, about $0.0003 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
optimize-claude-opus-5-prompts
Clarify, audit, and rewrite rough or existing prompts for Claude Opus 5 using Anthropic's official prompting guidance. Use when a user asks to optimize, improve, migrate, debug, or design a prompt, system prompt, or agent harness for Claude Opus 5 (claude-opus-5), including requests phrased as Opus 5 prompt…
optimize-claude-fable-5-prompts
A prompt-editing method for Claude Fable 5, an AI model. It turns rough or existing instructions into clearer prompts while keeping the original goal and important limits.
optimize-gpt-5-6-prompts
A guide for improving prompts written for OpenAI’s GPT-5.6 models, including GPT-5.6 Sol.
optimize-gpt-6-astra-prompts
Clarify, audit, migrate, and rewrite prompts for GPT-6 Astra using OpenAI's official latest-model prompting guidance. Use when a user asks to optimize, improve, rewrite, debug, migrate, or design a GPT-6 Astra prompt, including requests phrased as GPT-6, Astra, or gpt-6-astra prompt optimization, or when an…
optimize-deepseek-v4-prompts
Clarify, audit, and rewrite rough or existing prompts specifically for DeepSeek-V4 Pro and Flash using the DeepSeek-AI V4 technical report as the model-specific evidence base. Use when a user asks to optimize, improve, rewrite, debug, migrate, or design a DeepSeek-V4 prompt, including requests phrased as DeepSeek…
optimize-gemini-prompts
A prompt-editing skill for clarifying and rewriting prompts intended for Google’s Gemini models.