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 agentmods add skills/wasintoh/toh-framework/prompt-optimizernpx skills add wasintoh/toh-framework --skill prompt-optimizergit clone --depth 1 https://github.com/wasintoh/toh-frameworkWrote 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/wasintoh/toh-framework/prompt-optimizer)<a href="https://agentmods.dev/skills/wasintoh/toh-framework/prompt-optimizer"><img src="https://agentmods.dev/badge/skills/wasintoh/toh-framework/prompt-optimizer.svg" alt="Measured on agentmods" 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 | $0.00101 | $0.01782 |
| Opus 5 | $0.00051 | $0.00891 |
| Sonnet 5 | $0.00020 | $0.00356 |
| Haiku 4.5 | $0.00010 | $0.00178 |
Grade A, and why
prompt-optimizer 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 5d 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Best Prompt Optimizer and Composer
Transform prompts from functional to exceptional through deep analysis, strategic optimization, and iterative refinement. This skill applies "ultrathink" principles to prompt engineering—questioning assumptions, obsessing over details, and iterating relentlessly to create prompts that don't just work, but excel.
Philosophy: Think Different About Prompts
Most prompts merely work. Great prompts are inevitable—they feel like the only right way to ask. Achieve this by:
- Question every assumption: Why this structure? What if we started from zero?
- Obsess over details: Every word choice matters. Every instruction must be precise yet clear.
- Plan before writing: Understand the goal deeply before crafting a single sentence.
- Iterate relentlessly: The first version is never the final version.
- Simplify ruthlessly: Remove complexity without losing power.
Core Optimization Framework
1. Deep Understanding Phase
Before optimization, understand the prompt's true purpose:
Questions to explore:
- What is the desired output format and quality?
- Who is the audience? What's their expertise level?
- What context is essential vs. nice-to-have?
- What are the failure modes to prevent?
- Are there implicit assumptions that should be explicit?
Analyze current prompt for:
- Clarity of instructions
- Completeness of context
- Ambiguity or vagueness
- Missing constraints or guidelines
- Structural organization
- Token efficiency
2. Strategic Optimization by Prompt Type
For System Prompts (AI Agents/Chatbots)
- Define clear role and persona
- Establish behavioral boundaries and guardrails
- Specify output format and tone
- Include response patterns and examples
- Add error handling and edge cases
- Balance flexibility with consistency
For Task-Specific Prompts
- Break down complex tasks into clear steps
- Provide concrete examples (input/output pairs)
- Specify success criteria explicitly
- Include context about what NOT to do
- Add verification checkpoints
- Use structured formatting for clarity
What ships with it
1 file 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.
- 5d ago First seen · 272 lines · 101 tokens per session scan A 73685e19af25
prompt-optimizer is a skill published in the GitHub repository wasintoh/toh-framework (95 stars, last pushed 2d ago), licensed MIT. It adds 101 tokens to every session and 1,782 once invoked, about $0.0005 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
gpt-image-2-style-library
Choose GPT-Image2 / gpt-image-2 visual styles and industrial prompt templates from the awesome-gpt-image-2 style library. Use when an agent needs to create, rewrite, classify, or improve image-generation prompts with repository-backed templates, categories, style tags, scene tags, pitfalls, and example cases.
prompt-linter
Checks new prompt versions for unsafe patterns, format drift, registry consistency.
smoke-test
End-to-end smoke test skill for DeerFlow. Guides through: 1) Pulling latest code, 2) Docker OR Local installation and deployment (user preference, default to Local if Docker network issues), 3) Service availability verification, 4) Health check, 5) Final test report. Use when the user says "run smoke test", "smoke…
image-generation
Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.
podcast-generation
Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.
vercel-deploy
Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.