Borrowing it
Nothing to install: this file belongs to Vvkmnn/claude-orator-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Vvkmnn/claude-orator-mcp/main/.claude/skills/claude-orator/SKILL.mdgit clone --depth 1 https://github.com/Vvkmnn/claude-orator-mcpWrote 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/vvkmnn/claude-orator-mcp/claude-orator)<a href="https://agentmods.dev/skills/vvkmnn/claude-orator-mcp/claude-orator"><img src="https://agentmods.dev/badge/skills/vvkmnn/claude-orator-mcp/claude-orator/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/vvkmnn/claude-orator-mcp/claude-orator"><img src="https://agentmods.dev/badge/skills/vvkmnn/claude-orator-mcp/claude-orator.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 | $0.00054 | $0.00346 |
| Opus 5 | $0.00027 | $0.00173 |
| Sonnet 5 | $0.00011 | $0.00069 |
| Haiku 4.5 | $0.00005 | $0.00035 |
Grade A, and why
claude-orator 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.
What it actually says
Claude Orator
Make prompts measurably better before sending them.
When to Use
Dispatching subagents → Run the prompt through orator_optimize first. Better prompt = less back-and-forth, more accurate results.
Writing system prompts → SKILL.md files, agent instructions, tool descriptions. Small improvements compound over many invocations.
Prompt feels vague or under-specified → Score it. Orator identifies weak dimensions and applies targeted techniques.
Quick Reference
orator_optimize(prompt: "...", intent?: "code|analysis|creative|extraction|system", techniques?: ["xml-tags", "few-shot"])
Output: Before score → techniques applied → optimized prompt → after score.
Already good? One-line confirmation: 🪶 ━━ already well-structured (8.4)
When to Skip
Skip for trivial prompts, simple questions, or prompts already scoring above 7.0. The overhead isn't worth it for single-step instructions.
Common Mistakes
| Mistake | Fix |
|---|---|
| Optimizing everything | Focus on high-leverage: subagent prompts, system prompts |
| Ignoring the score delta | Close before/after scores mean the prompt was already good |
Not using techniques override |
When you know which techniques apply, force them |
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 · 39 lines · 54 tokens per session scan A 03a97365e6f9
claude-orator is a skill published in the GitHub repository Vvkmnn/claude-orator-mcp (2 stars, last pushed 6mo ago), licensed MIT. It adds 54 tokens to every session and 346 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
llm-router-ops
Operate a self-hosted OpenAI-compatible LLM router/proxy (e.g. LiteLLM) in front of one or more backends — the minimal client-wiring block for every client type, the context-window advertisement gotcha, the env-vs-persisted-config gotcha, and why an unauthenticated health probe should 401, not 200. Use when wiring a…
gws-modelarmor-create-template
Google Model Armor: Create a new Model Armor template.
gws-modelarmor-sanitize-prompt
Google Model Armor: Sanitize a user prompt through a Model Armor template.
gws-modelarmor
Google Model Armor: Filter user-generated content for safety.
prompt-optimizer
Optimize prompts for Claude's latest models (Claude 5 family — Opus 5, Sonnet 5, Fable 5 — plus the still-active Opus 4.8, Sonnet 4.6, and Haiku 4.5) using Anthropic's official prompt-engineering guidance. Use when users want to improve, refine, debug, or create prompts or system prompts for Claude. Triggers include…
prompt-engineering
Expert prompt engineering guidance with proven techniques and anti-patterns. Invoke this skill whenever writing, editing, reviewing, or refining any prompt that will be interpreted by an AI model — system prompts, agent instructions, tool-use prompts, command templates, multi-step task prompts, or agentic workflows.…