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 intellectronica/agent-skills --skill promptifygit clone --depth 1 https://github.com/intellectronica/agent-skillsWrote 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/intellectronica/agent-skills/promptify)<a href="https://agentmods.dev/skills/intellectronica/agent-skills/promptify"><img src="https://agentmods.dev/badge/skills/intellectronica/agent-skills/promptify.svg" alt="Measured on agentmods" height="20"></a>- Socket pass
- Snyk pass
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 | $0.00043 | $0.00393 |
| Opus 5 | $0.00022 | $0.00197 |
| Sonnet 5 | $0.00009 | $0.00079 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
promptify 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 8d 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.
What it actually says
Promptify
Transform user requests into detailed, precise prompts optimised for AI model consumption.
Core Task
Rewrite the user's request as a clear, specific, and complete prompt that guides an AI model to produce the desired output without ambiguity. Treat the output as specification language, not casual natural language.
Process
- Read and understand - Read the user's request carefully to understand the full context, intent, and all details
- Plan the rewrite - Consider what specific information, instructions, or context the AI model needs to fulfill the request effectively
- Rewrite as a detailed prompt - Transform the request into a precise prompt with clarity, specificity, and completeness
Writing Guidelines
Structure
- Begin with a single short paragraph summarising the overall task
- Use headings (##, ###, ####) for sections only where appropriate (no first-level title)
- Use bold, italics, bullet points (
-), and numbered lists (1., 2.) liberally for organisation - Never use emojis
- Never use
*for bullet points, always use-
Language
- Use plain, straightforward, precise language
- Avoid embellishments, niceties, or creative flourishes
- Think of language as specification/code, not natural language
- Be clear and specific in all instructions
Content
- Keep the prompt concise: 0.75X to 1.5X the length of the original request
- Do not add or invent information not present in the input
- Do not include unnecessary complexity or verbosity
Output
Provide only the final prompt as markdown, without additional commentary or explanation.
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.
- 8d ago First seen · 46 lines · 43 tokens per session scan A a83c9e6cebd0
promptify is a skill published in the GitHub repository intellectronica/agent-skills (292 stars, last pushed 4mo ago), licensed CC0-1.0. It adds 43 tokens to every session and 393 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 2026-08-30.
Other skills, from other repositories
LLM
Implement large language model (LLM) chat completions using the z-ai-web-dev-sdk. Use this skill when the user needs to build conversational AI applications, chatbots, AI assistants, or any text generation features. Supports multi-turn conversations, system prompts, and context management.
optimize-prompt
Optimize Claude Code and LLM prompts for token efficiency, prefix caching compliance, positional recall, and execution correctness. Use when writing/reviewing prompts, debugging agent errors/failures, managing context windows, selecting effort levels, choosing MCP vs CLI tools, designing subagents, or editing…
web-research-monitoring-workflows
Class-level workflow for web search, RSS/news/blog monitoring, source extraction, YouTube transcript lookup, summarization, and recurring news digests. Use when asked to search the web, compare search providers, gather fresh public news under search-rate limits, monitor blogs/RSS, summarize URLs/files/videos, or set…
dspy
DSPy: declarative LM programs, auto-optimize prompts, RAG.
outlines
Outlines: structured JSON/regex/Pydantic LLM generation.
agent-platform-prompt-management
Manages and orchestrates prompts in Agent Platform. Use when you need to create, list, retrieve, version, or delete managed prompts in Agent Platform. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform prompts.