Borrowing it
Nothing to install: this file belongs to Mats2208/MCP-Packet-Tracer. 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/Mats2208/MCP-Packet-Tracer/main/AGENTS.mdgit clone --depth 1 https://github.com/Mats2208/MCP-Packet-TracerWrote 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/mats2208/mcp-packet-tracer/agents-md)<a href="https://agentmods.dev/instructions/mats2208/mcp-packet-tracer/agents-md"><img src="https://agentmods.dev/badge/instructions/mats2208/mcp-packet-tracer/agents-md/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/mats2208/mcp-packet-tracer/agents-md"><img src="https://agentmods.dev/badge/instructions/mats2208/mcp-packet-tracer/agents-md.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 | $0.00997 | $0.00997 |
| Opus 5 | $0.00498 | $0.00498 |
| Sonnet 5 | $0.00199 | $0.00199 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
MCP-Packet-Tracer AGENTS.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 9d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Notes for coding agents working in this repo. Read this before changing anything
under src/.
What this is
An MCP server that automates Cisco Packet Tracer. It plans network topologies, validates them, generates JavaScript for PT's script engine and IOS CLI config for the devices, and can push all of it into a running copy of Packet Tracer over a local HTTP bridge.
Build and test
pip install -e ".[test]"
python -m pytest # from the repo root, no PT required
There is no linter or formatter configured. Match the surrounding style: type
hints on public functions, from __future__ import annotations at the top,
comments in Spanish or English following whatever the file already uses.
Layout
| Path | What lives there |
|---|---|
src/packet_tracer_mcp/domain/ |
Pydantic models, validation rules, planning services |
src/packet_tracer_mcp/application/ |
Use cases: rules + generators, dependencies injected |
src/packet_tracer_mcp/infrastructure/ |
Generators, executors, the HTTP + file bridges, device catalog |
src/packet_tracer_mcp/adapters/mcp/ |
tool_registry.py — the 61 MCP tools |
EXTENSION/script-engine/ |
Script-engine side of the extension. main.js is ours (tracked); the rest are PTBuilder reference copies (gitignored) |
EXTENSION/webview/ |
The MCP Control Center webview (index.html + interface.js) |
tool_registry.py is ~3000 lines and every tool is a closure inside
register_tools(). That means helpers defined there cannot be imported by
tests. If you write a helper worth testing, put it in shared/utils.py.
Rules that are not negotiable
- Never build JavaScript with raw f-strings. Use
json.dumpsfor each field. PT runs it throughnew Function(), so an unescaped device name is arbitrary code execution.ptbuilder_generator.pyshows the correct pattern. - Never build a path by concatenation. Use
safe_name_component()thenresolve_within()fromshared/utils.py. - Never add an unauthenticated bridge endpoint. Everything except
/pingrequires the token; seebridge_token.pyfor why loopback alone is not a control. (The file-bridge channel needs no token — the mailbox lives under a user-ACL'd%LOCALAPPDATA%dir a browser page can't reach.) - Don't validate in the models. Validation belongs in
domain/rules/and returnsValidationResult, so the use case decides whether to proceed. - A bug fix needs a test that fails without it. Write the failing test first; if it passes before your change, it isn't testing the bug.
- Never guess a PT API signature. If a method isn't already used somewhere
in this repo, confirm it against Cisco's reference before writing code on top
of it — PT answers a wrong call with a bare
Invalid arguments for IPC call "X", so a guess fails without telling you why.
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.
- 9d ago First seen · 83 lines · 997 tokens per session scan A 0bc991328610
MCP-Packet-Tracer AGENTS.md is an instructions file published in the GitHub repository Mats2208/MCP-Packet-Tracer (170 stars, last pushed 9d ago), licensed MIT. It adds 997 tokens to every session, about $0.0050 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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.