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/rajib884/bdcom_mcp/claude-mdgit clone --depth 1 https://github.com/rajib884/bdcom_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/rajib884/bdcom_mcp/claude-md)<a href="https://agentmods.dev/instructions/rajib884/bdcom_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rajib884/bdcom_mcp/claude-md.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 5.1 | $0.01842 | $0.01842 |
| Opus 5 | $0.00921 | $0.00921 |
| Sonnet 5 | $0.00368 | $0.00368 |
| Haiku 4.5 | $0.00184 | $0.00184 |
Grade A, and why
bdcom_mcp CLAUDE.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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project
A Python / FastMCP server ("device-mcp") that lets AI assistants manage network devices (Cisco IOS, BDCOM, any netmiko platform) over SSH/Telnet. Transport is netmiko; BDCOM gets a small custom driver. Requires Python >= 3.10; the repo has a venv at .venv (use .venv/bin/python / .venv/bin/pytest if not activated).
Commands
pip install -e ".[dev]" # install + pytest/pytest-timeout
python -m device_mcp.server # run the MCP server over stdio (also: device-mcp script)
python smoke_test.py # offline smoke suite: pure helpers + fakes, no sockets, <1s
pytest # emulator integration tests in tests/ (real telnet over loopback)
pytest tests/test_emulator_integration.py::test_connect_enable_password_flow # single test
python my_tester.py # manual eyeball harness (NOT pytest) against the emulator
Run both suites (python smoke_test.py and pytest) before considering a change done. Each pytest test performs a real netmiko telnet login (~9s); pyproject.toml sets a 30s per-test timeout so a hang fails one test instead of stalling the run.
Architecture
Three layers, plus a test emulator:
device_mcp/server.py— thin FastMCP tool layer. Each@mcp.toolwraps a method on a module-levelDeviceConnectionManagerand returns a string; exceptions are caught and returned as"Error: ..."text (AI-friendly, never raised to the client). Three file-transfer/firmware tools (transfer_file,upgrade_firmware,recover_firmware) are commented out here but their manager methods still exist and are tested — re-enabling means uncommenting the wrapper (enter_monitor_modeis live).device_mcp/connection.py— the core (~1800 lines).DeviceConnectionManagerholds long-lived connections keyed by target =host:port(several devices behind one console-server IP on different ports are independent connections;portmay be omitted in tool calls only when a host has exactly one connection — see_resolve). OneRLockguards the connection map and the non-reentrant netmiko channels; a per-connection daemon thread polls idle channels (non-blocking lock acquire) so unsolicited output reaches the audit log.device_mcp/bdcom.py— custom netmiko driver:_BdcomMixinover the Cisco IOS classes. BDCOM enters config withconfig(promptSwitch_config#, no parens), exits config with Ctrl-Z (not echoed, soexit_config_modecan't delegate to netmiko's echo-wait), has noterminal width, and acceptsterminal length 0only in enable mode — sosession_preparationelevates to enable before disabling paging (stock Cisco prep would leave paging on and desync later bigshowoutput). To add another vendor netmiko lacks: write a similar driver module and register it in_CUSTOM_DRIVERSinconnection.py.tests/switch_emulator.py— in-process, stdlib-only Telnet switch emulator speakingbdcomandciscodialects (login, enable password, paging/--More--, config sub-modes,?help,(y/n)confirmations, the hidden Ctrl-] boot menu and Ctrl-P monitor interrupt). Tests script it via aresponsesmap (exact string, compiled regex, or callable → output).
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 · 53 lines · 1,842 tokens per session scan A 518ac9b31fa3
bdcom_mcp CLAUDE.md is an instructions file published in the GitHub repository rajib884/bdcom_mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,842 tokens to every session, about $0.0092 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
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).
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.
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.
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.
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).