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 instructions/oguzc/playwright-wizard-mcp/copilot-instructionsgit clone --depth 1 https://github.com/oguzc/playwright-wizard-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/instructions/oguzc/playwright-wizard-mcp/copilot-instructions)<a href="https://agentmods.dev/instructions/oguzc/playwright-wizard-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/oguzc/playwright-wizard-mcp/copilot-instructions.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 | $0.00590 | $0.00590 |
| Opus 5 | $0.00295 | $0.00295 |
| Sonnet 5 | $0.00118 | $0.00118 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
playwright-wizard-mcp copilot-instructions.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 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions
Response Style
- Default to concise & direct responses
- Provide detailed explanations when explicitly asked or when explaining crucial concepts
- Adopt tone of a friendly senior developer (casual, helpful, knowledgeable)
- Use emojis sparingly and contextually
- Assume expert-level knowledge by default, but adapt dynamically based on conversation context
Markdown Files
Context-Aware Structure
- Agent instructions: Ultra-concise (token efficiency critical)
- Standard documentation: Minimal/clean approach
- Teaching/tutorials: Full structure with examples and detailed sections
- Choose format based on document purpose and intended audience
Formatting Conventions
- Headings: Title Case for H1, sentence case for H2+
- Lists: Use
-for unordered,1.for ordered - Code blocks: Always specify language
- Emphasis:
- Bold for important concepts and warnings
- Italic for emphasis and technical terms on first use
Code formatfor filenames, commands, variables, technical identifiers
Code Style
General Principles
- Comments: Moderate - explain key logic and complex parts only, avoid comment bloat
- Examples: Focused snippets showing relevant parts (not full boilerplate)
- Error handling: Include for important operations, skip for trivial code
- TypeScript: Use strict types
- Async patterns: Prefer async/await over promises
Naming & Structure
- Files:
PascalCase.tsxfor React componentskebab-case.tsfor utilities, hooks, serviceskebab-case.mdfor documentation
- Folders: Feature-based organization when appropriate
- Variables: Descriptive names, avoid abbreviations unless standard
Workflow
Decision Making
- Gather context first when unsure (use multiple tools if needed)
- Make sensible defaults for formatting/structure choices
- Suggest new files proactively when it improves organization
- Try alternative approaches automatically when something fails
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 · 71 lines · 590 tokens per session scan A 27c60e03abbf
playwright-wizard-mcp copilot-instructions.md is an instructions file published in the GitHub repository oguzc/playwright-wizard-mcp (7 stars, last pushed 9mo ago), licensed MIT. It adds 590 tokens to every session, about $0.0030 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 instructions, from other repositories
sap-mcp-servers AGENTS.md
Instructions for marianfoo/sap-mcp-servers, covering agents.md — sap-mcp-servers monorepo, what this repo is, the one thing to know: build order, first-time setup and everyday commands (run from repo root).
linkedin-mcp-server AGENTS.md
AGENTS.md instructions for prakharagarwal-dev/linkedin-mcp-server, covering repository instructions, product boundary, access and secrets, technical conventions and working style.
sap-mcp-servers CLAUDE.md
Instructions for marianfoo/sap-mcp-servers: This repo's contributor/agent guide lives in AGENTS.md — read that. It applies to all agents (Claude Code, Codex, Cursor, …), not just Codex, and covers the workspace layout, the build order (auth first), the env contract, secrets policy, and the release/publish flow.
freetaxusa-mcp CLAUDE.md
Claude Code instructions for schwarztim/freetaxusa-mcp, covering freetaxusa mcp server, architecture, commands, tool categories and phase 1 (implemented).
mcp-recipe-shopping-list AGENTS.md
AGENTS.md instructions for KrivchenkoEgor/mcp-recipe-shopping-list, covering ⛔ критические запреты (читать первым), 1. 🚫 картинки в чате запрещены, 2. 🚫 оба сайта — spa (javascript-heavy), 3. 🚫 не формируем корзину — только список покупок and 4. 🚫 уважение к серверам.
tradingview-mcp AGENTS.md
AGENTS.md instructions for moeuu/tradingview-mcp, covering repository instructions and codex review waiting.