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/mattiice/pbx/claude-mdgit clone --depth 1 https://github.com/mattiIce/PBXWrote 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/mattiice/pbx/claude-md)<a href="https://agentmods.dev/instructions/mattiice/pbx/claude-md"><img src="https://agentmods.dev/badge/instructions/mattiice/pbx/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 | $0.04606 | $0.04606 |
| Opus 5 | $0.02303 | $0.02303 |
| Sonnet 5 | $0.00921 | $0.00921 |
| Haiku 4.5 | $0.00461 | $0.00461 |
Grade A, and why
PBX 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 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.
How it starts
The opening of the file, as written. The whole thing — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Warden VoIP (PBX)
Project Overview
Warden VoIP is a comprehensive VoIP/PBX system built from scratch in Python 3.13+. It implements the full SIP protocol stack, RTP media handling, and an extensive feature set (76 modules) without depending on Asterisk or FreeSWITCH. The project includes a modern admin web interface built with TypeScript/Vite.
Quick Reference
| Item | Value |
|---|---|
| Language | Python 3.13+ (backend), TypeScript 6.0 (frontend) |
| Node.js | >=22 required |
| Package manager | uv pip (Python), npm (frontend) |
| Build system | hatchling (Python), vite 8.0 (frontend) |
| Test framework | pytest 9+ (Python), jest 30 (frontend) |
| Linter/Formatter | ruff 0.15 (Python), markdownlint-cli2 (Markdown) |
| Type checker | mypy 2.1 (strict mode, Python), tsc (TypeScript) |
| Line length | 100 characters |
| Entry point | pbx/main.py → pbx-server console script |
Common Commands
# Install dependencies (development)
make install # uv pip install -e ".[dev]"
# Run all checks (format + lint + test)
make check
# Linting and formatting
make lint # ruff check + mypy
make lint-fix # ruff check --fix
make format # ruff format + isort fix
make format-check # check only, no changes
# Testing
make test # all tests (Python + JavaScript)
make test-python # pytest only
make test-js # jest only
make test-unit # pytest -m unit
make test-integration # pytest -m integration
make test-cov # pytest with coverage report
# Development servers
make dev # backend + frontend concurrently
make dev-backend # Flask debug mode only
make dev-frontend # Vite dev server only
# Run production
make run # python main.py
# Docker
make docker-build # docker compose build
make docker-up # docker compose up -d
make docker-down # docker compose down
# Pre-commit hooks
make pre-commit-install
make pre-commit-run
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 · 363 lines · 4,606 tokens per session scan A f347f66af3be
PBX CLAUDE.md is an instructions file published in the GitHub repository mattiIce/PBX (2 stars, last pushed 2d ago), licensed MIT. It adds 4,606 tokens to every session, about $0.0230 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
turn-rs AGENTS.md
Instructions for mycrl/turn-rs, covering agents.md, project overview, core capabilities, key entry points and directories and source code architecture (modules and responsibilities).
arty AGENTS.md
Instructions for tleyden/arty, a project described as: iOS realtime voice assistant w/ translation + connectors.
node-sfu CLAUDE.md
Instructions for shinyoshiaki/node-sfu, covering claude.md, project overview, package-specific guidance, workspace structure and project-wide architecture.
3cx-mcp-server CLAUDE.md
Claude Code instructions for SSIG-IT/3cx-mcp-server, covering 3cx mcp server, was ist das?, tech stack, 3cx apis and auth.
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.