Borrowing it
Nothing to install: this file belongs to Fayeblade1488/Fayeblade_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/Fayeblade1488/Fayeblade_mcp/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/Fayeblade1488/Fayeblade_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/fayeblade1488/fayeblade_mcp/copilot-instructions)<a href="https://agentmods.dev/instructions/fayeblade1488/fayeblade_mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/fayeblade1488/fayeblade_mcp/copilot-instructions/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/instructions/fayeblade1488/fayeblade_mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/fayeblade1488/fayeblade_mcp/copilot-instructions.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 | $0.01074 | $0.01074 |
| Opus 5 | $0.00537 | $0.00537 |
| Sonnet 5 | $0.00215 | $0.00215 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
Fayeblade_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 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions — Venice Browser MCP Bridge
This document defines the precise operational guardrails for GitHub Copilot (or any LLM-based assistant) when interacting with this repository.
1. Purpose of This Repo
• This repo implements a Browser MCP Bridge that connects Venice.ai (or any MCP-capable host) to a Chromium browser via Playwright.
• Core features:
• Framing modes: line (newline JSON) or content-length (hard MCP).
• Persistence: optional browser session persistence with storage_state (cookies, localStorage).
• Methods: browser.navigate, browser.screenshot, browser.query.
Copilot must not hallucinate features beyond these.
⸻
2. File Boundaries
Copilot must strictly respect file roles: • src/venice_browser_mcp_v23_impl.py → Full v2.3 implementation. Do not duplicate functionality here. Only modify if explicitly instructed. • src/venice_browser_mcp_core.py → Minimal adapter; only ever call run_main() from v23 impl. Do not add extra logic. • src/venice_browser_mcp.py → CLI wrapper. Allowed to set env vars and call into core. Do not inline the v23 logic here. • examples/ → Minimal toy hosts only. Do not add production logic here. • docs/ARCHITECTURE.md → Architectural overview. Copilot should not drift into API tutorials or usage duplication already in README.md. • README.md → Authoritative source for installation, usage, troubleshooting. Copilot must check this before suggesting usage patterns.
⸻
3. Code Style Rules
• Language: Python 3.9+ only.
• Asynchronous style: always use async/await with Playwright. Do not introduce sync Playwright calls.
• Logging: prefer writing to stderr for debugging; never pollute stdout (reserved for MCP messages).
• Encoding: all messages are UTF-8 JSON. Copilot must never suggest mixing bytes vs str without explicit .encode()/.decode().
• Dependencies: limited to playwright. Do not suggest external libraries for framing or JSON-RPC.
⸻
4. Behavior Rules
• Framing:
• If MCP_FRAMING=line, messages are one JSON object per line.
• If MCP_FRAMING=content-length, messages must have exact Content-Length: N\r\n\r\n headers with N = byte length of JSON body.
• Persistence:
• If MCP_PERSIST_CONTEXT=1, reuse a single BrowserContext and load/save storage state.
• Never create multiple persistent contexts.
• Storage is always JSON at the path given by MCP_STORAGE_STATE.
• Methods contract:
• browser.navigate: returns text/html (truncated if > MAX_CONTENT_CHARS), links, meta.
• browser.screenshot: returns base64 PNG. Must fail gracefully if > MAX_BASE64_BYTES.
• browser.query: returns node text or HTML.
• Error handling:
• Always return JSON-RPC error envelopes (id, error.code, error.message, optional error.data).
• Never crash with raw Python exceptions on stdout.
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 · 106 lines · 1,074 tokens per session scan A 829286146852
Fayeblade_mcp copilot-instructions.md is an instructions file published in the GitHub repository Fayeblade1488/Fayeblade_mcp (1 stars, last pushed 11mo ago), licensed MIT. It adds 1,074 tokens to every session, about $0.0054 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
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.