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 yuchenbigpen1/normies --skill prompt-improvergit clone --depth 1 https://github.com/yuchenbigpen1/normiesWrote 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/yuchenbigpen1/normies/prompt-improver)<a href="https://agentmods.dev/skills/yuchenbigpen1/normies/prompt-improver"><img src="https://agentmods.dev/badge/skills/yuchenbigpen1/normies/prompt-improver/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/yuchenbigpen1/normies/prompt-improver"><img src="https://agentmods.dev/badge/skills/yuchenbigpen1/normies/prompt-improver.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 | $0.00035 | $0.00920 |
| Opus 5 | $0.00017 | $0.00460 |
| Sonnet 5 | $0.00007 | $0.00184 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
prompt-improver 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Improver Skill
Purpose
Help non-technical business operators articulate their needs clearly by asking focused, business-relevant questions. This skill is invoked when a request is too vague to determine the right approach (build vs. buy, custom vs. off-the-shelf, etc.).
When This Skill is Invoked
The Explore agent evaluates each user message for clarity. If the request is too vague to determine the right approach, the agent invokes this skill to ask clarifying questions.
Key principle: Most prompts should pass through without interruption. Only truly ambiguous requests trigger this skill.
Core Workflow
Phase 1: Context Review
Before asking questions, review what you already know:
- Check conversation history — Has the user already explained their business, team, or goals?
- Review any connected sources — Are there existing tools, APIs, or data sources that provide context?
- Identify the ambiguity — What specifically is unclear? The goal? The scale? The constraints?
Rules:
- Never ask about things already discussed in conversation
- Focus on business context, not technical details
- If you can reasonably infer intent, just proceed
Phase 2: Ask 1-3 Focused Questions
Based on what's missing, formulate at most 3 questions. Less is better.
Question categories:
| Category | Example |
|---|---|
| Goal | "What outcome are you looking for?" |
| Scale | "How many people will use this?" |
| Existing tools | "What tools does your team use today?" |
| Timeline | "Is this urgent, or a longer-term improvement?" |
| Constraints | "Are there budget or tool restrictions?" |
Question guidelines:
- Use plain, non-technical language
- Provide concrete options (multiple choice preferred)
- Keep descriptions brief — one sentence max
- Never reference code, files, APIs, or technical concepts
Phase 3: Get Clarification
Use the ask_user_question tool:
questions: [{
question: "Clear business question ending with ?"
options: [
{ label: "Plain language (1-5 words)", description: "What this means for them (one sentence)" },
...2-4 options total
]
multiSelect: false
}]
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 · 123 lines · 35 tokens per session scan A 069932f35270
prompt-improver is a skill published in the GitHub repository yuchenbigpen1/normies (4 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 920 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
prompt-engineering
Universal prompt engineering techniques for any LLM. Use when crafting, optimizing, or reviewing prompts for AI models. Triggers on requests like "improve this prompt", "write a system prompt", "optimize my instructions", "help me prompt engineer", "audit this prompt", "review my prompt", or when building agentic…
refine
Transform a brief or prompt into a structured, production-ready prompt via prompt-optimizer. File or text mode.
better-prompt
A prompt editor that turns rough instructions for AI systems into clearer, more complete prompts. It follows published OpenAI and Anthropic guidance.
prompt-writer
Write maximally terse agent prompts from scratch. Use when creating agent specs, command prompts, or instruction sets with constitutional governance.
building-agent-systems
AI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt injection, jailbreak defense, output filtering), RAG architecture (chunking, hybrid retrieval, rerank), and prompt…
tersify-prompt
Rewrites agent-instruction prompts to be maximally terse while preserving full intent.