mcp-network-analyzer copilot-instructions.md

mcp-network-analyzer copilot-instructions.md is an instructions file for GitHub Copilot from kylebrodeur/mcp-network-analyzer. It costs 415 tokens per session, scanned A, original, MIT.

A set of project instructions for GitHub Copilot and other code-generating agents working on an MCP server, a service that lets AI tools use connected capabilities.

In plain words
What is it for?
It guides work on browser network capture, API analysis, generated export tools, TypeScript code, shared types, storage, and smoke tests.
Why use it?
It gives coding agents the project’s technology choices, file organization, logging rules, and development workflow so their changes fit the repository.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/kylebrodeur/mcp-network-analyzer/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/kylebrodeur/mcp-network-analyzer

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for mcp-network-analyzer copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kylebrodeur/mcp-network-analyzer/copilot-instructions.svg)](https://agentmods.dev/instructions/kylebrodeur/mcp-network-analyzer/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/kylebrodeur/mcp-network-analyzer/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/kylebrodeur/mcp-network-analyzer/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 415 This file is loaded in full into every session.
When invoked 415 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00415 $0.00415
Opus 5 $0.00208 $0.00208
Sonnet 5 $0.00083 $0.00083
Haiku 4.5 $0.00042 $0.00042

Measured 4d ago against content hash 240d6e2d53ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-network-analyzer 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 4d 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.

.github/copilot-instructions.md · 36 lines

What it actually says

Copilot Instructions

These instructions tell GitHub Copilot (and other codegen agents) how to collaborate inside this repository.

Project Context

  • Build an MCP server that can capture browser network traffic, analyze API patterns, and auto-generate export tools.
  • Preferred stack: TypeScript + Playwright primary, Puppeteer (with stealth) as fallback.
  • Storage approach: JSON for raw captures, SQLite/FTS for indexing, Handlebars templates for generated code.

Coding Guidelines

  1. Keep TypeScript strict-mode friendly and avoid any unless absolutely required.
  2. Centralize shared types inside src/lib/types.ts (create as features mature) and reuse schemas with Zod.
  3. Prefer async/await with structured error handling and contextual logging for every tool action.
  4. Never block STDOUT with logs; route diagnostics through STDERR or the MCP logging channel.
  5. Keep generated files (captures, analyses, exports) under data/ and respect .gitignore.

Workflow Expectations

  • src/index.ts is the MCP entry point; register tools/patterns here.
  • Each tool gets its own module under src/tools/ and should rely on helpers from src/lib/.
  • Add lightweight smoke tests for complex logic before wiring it into the server.
  • Update documentation (README.md, docs/) when behavior or commands change.

Developer Experience

  • Use the provided pnpm scripts (dev, build, type-check, clean).
  • Keep VS Code tasks/launch configs in sync with new scripts.
  • When adding a new tool, also document its inputs/outputs in README and PLAN.

Documentation

  • Active documentation is in /README.md, /docs/PROJECT_STATUS.md, /docs/PLAN.md, /docs/DUAL_MODE_ARCHITECTURE.md, and /docs/BLAXEL_INTEGRATION.md.
  • Ignore archived documentation: Files in /docs/_archive/ are historical and should not be referenced for current implementation decisions.
Changes

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.

  1. 4d ago First seen · 36 lines · 415 tokens per session scan A 240d6e2d53ea

Subscribe to this mod's changes

mcp-network-analyzer copilot-instructions.md is an instructions file published in the GitHub repository kylebrodeur/mcp-network-analyzer (1 stars, last pushed 5mo ago), licensed MIT. It adds 415 tokens to every session, about $0.0021 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.