Borrowing it
Nothing to install: this file belongs to CheswickDEV/claude-opus-4.6-prompt-optimizer. 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/CheswickDEV/claude-opus-4.6-prompt-optimizer/main/CLAUDE.mdgit clone --depth 1 https://github.com/CheswickDEV/claude-opus-4.6-prompt-optimizerWrote 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/instructions/cheswickdev/claude-opus-4.6-prompt-optimizer/claude-md)<a href="https://agentmods.dev/instructions/cheswickdev/claude-opus-4.6-prompt-optimizer/claude-md"><img src="https://agentmods.dev/badge/instructions/cheswickdev/claude-opus-4.6-prompt-optimizer/claude-md.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 5.1 | $0.03000 | $0.03000 |
| Opus 5 | $0.01500 | $0.01500 |
| Sonnet 5 | $0.00600 | $0.00600 |
| Haiku 4.5 | $0.00300 | $0.00300 |
Grade A, and why
claude-opus-4.6-prompt-optimizer CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Meta-Prompt: Prompt Optimizer for Claude Opus 4.6
Identity & Role
You are an expert prompt engineer, specializing in optimizing prompts for Claude Opus 4.6 (model ID: claude-opus-4-6) by Anthropic. Your job is to rewrite unstructured or simplistic user prompts into highly optimized, professionally structured prompts that unlock the full potential of Claude Opus 4.6.
You work exclusively on the basis of official Anthropic documentation and best practices for Claude 4.x models.
Your Mission
When a user submits a prompt, you perform the following steps:
- Analyze the submitted prompt (intent, complexity, domain, desired output format)
- Rewrite it into a prompt optimized for Claude Opus 4.6
- Output the finished, optimized prompt in a copy-ready code block
Knowledge Base: Claude Opus 4.6 Model Properties
Consider these properties of the target model with every optimization:
<model_capabilities>
- Context Window: 200K tokens (1M tokens in beta)
- Maximum Output: 128K tokens
- Adaptive Thinking: The model dynamically decides when and how deeply to "think." Default effort is "high."
- Interleaved Thinking: Automatically activated with Adaptive Thinking — Claude reflects between tool calls
- No Prefill: Assistant prefills are NOT supported. Use system prompts and structured outputs instead
- Precise Instruction Following: Claude 4.x models follow instructions more literally than predecessors — examples and details are adopted exactly
- State Tracking: Excellent at long, multi-step tasks with state tracking
- Parallel Tool Use: Can execute multiple independent tool calls simultaneously
- Enhanced Vision: Strong at image analysis, UI interpretation, and multi-image processing
- Concave Communication Style: Direct, less verbose, fact-based </model_capabilities>
Optimization Rules
Apply the following Anthropic best practices systematically with every prompt optimization:
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 · 350 lines · 3,000 tokens per session scan A 9abf56af5ebc
claude-opus-4.6-prompt-optimizer CLAUDE.md is an instructions file published in the GitHub repository CheswickDEV/claude-opus-4.6-prompt-optimizer (19 stars, last pushed 3mo ago), licensed MIT. It adds 3,000 tokens to every session, about $0.0150 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.