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/drvoss/everything-copilot-cli/prompt-optimizernpx skills add drvoss/everything-copilot-cli --skill prompt-optimizergit clone --depth 1 https://github.com/drvoss/everything-copilot-cliWrote 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/drvoss/everything-copilot-cli/prompt-optimizer)<a href="https://agentmods.dev/skills/drvoss/everything-copilot-cli/prompt-optimizer"><img src="https://agentmods.dev/badge/skills/drvoss/everything-copilot-cli/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 | $0.00054 | $0.01030 |
| Opus 5 | $0.00027 | $0.00515 |
| Sonnet 5 | $0.00011 | $0.00206 |
| Haiku 4.5 | $0.00005 | $0.00103 |
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 yesterday.
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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Optimizer
Prompt Optimizer turns rough prompting intent into a single reusable prompt that the user can paste directly into a chat interface.
This is for chat-interface prompts only - not API parameter tuning, system prompts, agent files, or full promptware design.
When to Use
- The user says "rewrite this prompt", "improve this prompt", or "turn this into a prompt"
- The user has a half-formed idea and wants a strong prompt instead of a direct answer
- The user pasted a draft prompt and wants it sharpened for quality, structure, or clarity
- The user wants a reusable prompt they can send to Copilot, Claude, Codex, or another chat LLM
When NOT to Use
| Instead of prompt-optimizer | Use |
|---|---|
| The user wants the answer to the task right now | answer directly |
| Designing context packs or task briefs for agents | context-engineering |
| Generating a new SKILL.md for this repository | skill-creator |
Two Hard Rules
1. No placeholders
Do not output blanks like:
[insert X]{topic}<your input here>
The result must be ready to send as-is. No brackets, braces, fill-in-the-blank tokens, or other placeholder syntax should survive in the final prompt.
2. Always ship a finished prompt
There are only two acceptable modes:
- Case A - real content was provided: bake that content directly into the final prompt
- Case B - only the task type was described: write a self-contained prompt that asks the next-model turn for the missing inputs
In both cases, the user should be able to copy, paste, and send immediately.
Workflow
1. Identify the real goal
Before rewriting, decide:
- what output the user wants
- who the output is for
- what constraints matter
- whether this is Case A or Case B
2. Choose the right amount of structure
Use simple prose for simple tasks. Use sections or tags only when the task is complex enough to benefit from them.
Good structure helps. Unnecessary ceremony hurts.
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.
- yesterday First seen · 145 lines · 54 tokens per session scan A 1af3c58c848f
prompt-optimizer is a skill published in the GitHub repository drvoss/everything-copilot-cli (45 stars, last pushed 8d ago), licensed MIT. It adds 54 tokens to every session and 1,030 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 2026-09-03.
Other skills, from other repositories
prompt-writer
Use when creating, reviewing, or revising prompts, system prompts, developer instructions, agent policies, prompt templates, eval prompts, or skill files consumed by LLMs and AI agents. Routes to OpenAI, Anthropic/Claude, or generic prompt-writing guidance based on the target model/provider.
promptify
Transform user requests into detailed, precise prompts for AI models. Use when users say "promptify", "promptify this", or explicitly request prompt engineering or improvement of their request for better AI responses.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…