Borrowing it
Nothing to install: this file belongs to djuntgen/firewalla-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/djuntgen/firewalla-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/djuntgen/firewalla-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/djuntgen/firewalla-mcp/claude-md)<a href="https://agentmods.dev/instructions/djuntgen/firewalla-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/djuntgen/firewalla-mcp/claude-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/djuntgen/firewalla-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/djuntgen/firewalla-mcp/claude-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 | $0.00987 | $0.00987 |
| Opus 5.5 | $0.00395 | $0.00395 |
| Sonnet 5.5 | $0.00197 | $0.00197 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
firewalla-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 20d 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 — 82 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.
What this is
A local stdio MCP server wrapping the Firewalla MSP API v2 — boxes, devices, people/apps,
alarms, rules, flows, target lists, trends, and statistics — as tools for Claude Code and other
MCP clients. Public, MIT, published as firewalla-mcp and runnable straight from GitHub with
uvx. Requires Python 3.12+ and an active Firewalla MSP subscription.
Small on purpose: ~700 lines across three modules.
Commands
uv sync
uv run pytest -v
uv run pytest tests/test_client_rules.py::test_name # single test
uv run ruff check . && uv run ruff format --check . # both enforced in CI
The suite is fully mocked with respx — no Firewalla credentials or network access are
needed to run it, and no test should ever require them.
Architecture
Two layers, one file each. Every MSP API operation is implemented in both:
src/firewalla_mcp/client.py— a method onFirewallaClientthat callsself._request(...)and returns parsed JSON. All HTTP behavior (auth, retries, error shaping) lives here.src/firewalla_mcp/server.py— a thin@mcp.tool()wrapper calling the client method. Its docstring is the MCP tool description the model reads, so write it for that audience.
config.py reads FIREWALLA_MSP_DOMAIN, FIREWALLA_TOKEN, and optional FIREWALLA_TIMEOUT
(default 10s) from the environment at startup; a pasted https:// prefix or trailing slash on
the domain is tolerated.
To add a tool: follow an existing method as a template, add client tests that mock the HTTP call
with respx, and update the expected tool set in tests/test_server.py — that test pins the
full inventory and will fail otherwise.
Deliberate design decisions — do not change casually
Retry policy (client.py, MAX_ATTEMPTS/RETRY_BACKOFF_SECONDS/MAX_RETRY_AFTER_SECONDS):
- 4xx fails immediately, raising
FirewallaAPIError(status_code, body)with the body truncated toMAX_ERROR_BODY_CHARSso failures stay readable. - 429 retries once, honoring
Retry-Afterup to 10s. - 5xx and connection errors retry once with 0.5s backoff — except non-idempotent writes
(
create_rule,create_target_list,update_device,mute_alarm,archive_alarm), which are never retried so a timed-out request cannot silently duplicate or double-apply a write. - Non-JSON responses (e.g. an HTML proxy error page) raise a readable error, not a decoder traceback.
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.
- 20d ago First seen · 82 lines · 987 tokens per session scan A c933ae1cb393
firewalla-mcp CLAUDE.md is an instructions file published in the GitHub repository djuntgen/firewalla-mcp (0 stars, last pushed 14d ago), licensed MIT. It adds 987 tokens to every session, about $0.0039 per session on Opus 5.5. 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 2026-09-30.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.