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/kylebrodeur/mcp-network-analyzer/copilot-instructionsgit clone --depth 1 https://github.com/kylebrodeur/mcp-network-analyzerWrote 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/kylebrodeur/mcp-network-analyzer/copilot-instructions)<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>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 | $0.00415 | $0.00415 |
| Opus 5 | $0.00208 | $0.00208 |
| Sonnet 5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00042 | $0.00042 |
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.
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
- Keep TypeScript strict-mode friendly and avoid
anyunless absolutely required. - Centralize shared types inside
src/lib/types.ts(create as features mature) and reuse schemas with Zod. - Prefer async/await with structured error handling and contextual logging for every tool action.
- Never block STDOUT with logs; route diagnostics through STDERR or the MCP logging channel.
- Keep generated files (captures, analyses, exports) under
data/and respect.gitignore.
Workflow Expectations
src/index.tsis the MCP entry point; register tools/patterns here.- Each tool gets its own module under
src/tools/and should rely on helpers fromsrc/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.
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.
- 4d ago First seen · 36 lines · 415 tokens per session scan A 240d6e2d53ea
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.
Other instructions, from other repositories
mcp-camoufox AGENTS.md
Instructions for RobithYusuf/mcp-camoufox, covering mcp-camoufox — agent guide, product and repository map, hard constraints, working defaults and architecture invariants.
mcp-wireshark CLAUDE.md
Instructions for khuynh22/mcp-wireshark, covering claude.md — mcp-wireshark, purpose, architecture, code conventions and token efficiency rules.
unbrowser CLAUDE.md
Instructions for protostatis/unbrowser, covering unbrowser, why this exists, architecture (locked), stealth mode (native, on by default) and host functions exposed to js.
trusty-squire CLAUDE.md
Claude Code instructions for Trusty-Squire/trusty-squire, covering claude.md, project overview, objective function (what this project optimizes for), current state and production, deployed, verified end-to-end.
google-flow-mcp CLAUDE.md
Instructions for roshanarnav25-sloth/google-flow-mcp, covering notes for ai coding agents, what this is, hard rules, before you claim it works and layout.
mcp-browser-bridge CLAUDE.md
Claude Code instructions for adbarc92/mcp-browser-bridge, covering claude.md, build & dev commands, architecture, server (src/) and extension (extension/).