Borrowing it
Nothing to install: this file belongs to onionuser79/Open-PR-DIGI-MCP-Server-for-Claude-AI. 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/onionuser79/Open-PR-DIGI-MCP-Server-for-Claude-AI/main/CLAUDE.mdgit clone --depth 1 https://github.com/onionuser79/Open-PR-DIGI-MCP-Server-for-Claude-AIWrote 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/onionuser79/open-pr-digi-mcp-server-for-claude-ai/claude-md)<a href="https://agentmods.dev/instructions/onionuser79/open-pr-digi-mcp-server-for-claude-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/onionuser79/open-pr-digi-mcp-server-for-claude-ai/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/onionuser79/open-pr-digi-mcp-server-for-claude-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/onionuser79/open-pr-digi-mcp-server-for-claude-ai/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 | $0.01371 | $0.01371 |
| Opus 5.5 | $0.00548 | $0.00548 |
| Sonnet 5.5 | $0.00274 | $0.00274 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade A, and why
Open-PR-DIGI-MCP-Server-for-Claude-AI 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 1mo 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open PR-DIGI MCP Server
MCP server exposing packet-radio digipeater nodes — (X)Net, PC/Flexnet,
BPQ32/LinBPQ — as typed tool calls. Python 3.10+, asyncio, FastMCP over stdio.
Station-agnostic: no station knowledge in code, all of it in nodes.yaml.
Commands
.venv/bin/pip install -e ".[dev]" # dev setup (python3 -m venv .venv first)
.venv/bin/ruff check . # lint — line length 100
.venv/bin/mypy src # types — strict
.venv/bin/python -m pytest -q # unit + in-process mock-transport integration
pr-digi-mcp # run the server (stdio)
pr-digi-mcp test N0CALL-14 # smoke-test one node, read-only command
pr-digi-mcp serve-http # opt-in bearer-token HTTP, loopback by default
Those three checks are exactly what CI runs (Python 3.10–3.13). Keep them green. No network or radio hardware is needed for any test.
Hard rules
- Never commit secrets or real station data. No real callsigns, hosts or
passwords anywhere in the repo — use
N0CALL-*and192.0.2.x. Secrets live in the OS keyring (servicepr-digi-mcp) or a gitignored 0600credentials.yaml. Never innodes.yaml. - The confirm gate is not optional. Any tool that changes persistent state,
changes identity, or takes a node offline must be classified in
safety.pyand must refuse to run withoutconfirm=True. Never add an unguarded write/reset/delete path. This drives live amateur-radio infrastructure. mypy --strictmust pass onsrc. Type hints everywhere.- Tests accompany behaviour changes. If a node build behaves differently,
extend
tests/test_integration_mock.pywith a sanitised transcript rather than reaching for real hardware. - Docstrings on public functions explain why, not what.
Code map
| Area | File |
|---|---|
| MCP tool definitions + CLI | src/pr_digi_mcp/server.py (large — grep, don't read whole) |
Node inventory schema / loader / resolve_chain() |
src/pr_digi_mcp/config.py |
| Credentials (keyring → YAML fallback, 2 s timeout) | src/pr_digi_mcp/credentials.py |
| Dangerous-command classifier | src/pr_digi_mcp/safety.py |
| Command syntax tables + callsign validation | src/pr_digi_mcp/commands.py |
| Tolerant output parsers → typed records | src/pr_digi_mcp/parsers.py |
On-demand route discovery + ranking (_rank_key) |
src/pr_digi_mcp/discovery.py |
Base transport: telnet/SSH, login, SYS elevation |
src/pr_digi_mcp/transports/xnet.py |
BPQ PASSWORD elevation |
src/pr_digi_mcp/transports/bpq.py |
| AX.25 chained transport | src/pr_digi_mcp/transports/chained.py |
Family detection (MOTD, else V) |
src/pr_digi_mcp/transports/family.py |
| Bearer-token ASGI gate | src/pr_digi_mcp/http_auth.py |
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.
- 1mo ago First seen · 95 lines · 1,371 tokens per session scan A 047cd9d9411b
Open-PR-DIGI-MCP-Server-for-Claude-AI CLAUDE.md is an instructions file published in the GitHub repository onionuser79/Open-PR-DIGI-MCP-Server-for-Claude-AI (0 stars, last pushed 4d ago), licensed MIT. It adds 1,371 tokens to every session, about $0.0055 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 2026-09-17.
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.