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/hamr0/beeperbox/claude-mdgit clone --depth 1 https://github.com/hamr0/beeperboxWhat 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 | $0.01903 | $0.01903 |
| Opus 5 | $0.00951 | $0.00951 |
| Sonnet 5 | $0.00381 | $0.00381 |
| Haiku 4.5 | $0.00190 | $0.00190 |
Grade A, and why
beeperbox 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 3d 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 — 133 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.
@.claude/remember/MEMORY.md
Consult when building something new or adding a feature — a standards guide, not hot context like MEMORY.md above: @.claude/remember/AGENT_RULES.md
What this is
beeperbox exposes every network Beeper bridges (WhatsApp, iMessage,
Signal, Telegram, Discord, Slack, Matrix, …) to an AI agent through one MCP endpoint instead of
50 per-platform SDKs. It is not a thin proxy over Beeper's raw API — it is an opinionated verb
layer that normalizes everything into one Chat / Message schema.
There is no build step, no framework, no lint/format/TS config, and no root package.json. The
entire product is one file: mcp/server.js (CommonJS, Node ≥18, zero runtime deps).
Commands
# Unit tests (node:test — no framework)
node --test mcp/server.test.js
node --test --test-name-pattern 'assertServableSrcUrl' mcp/server.test.js # single test
# download_asset / attachments E2E against a stub Beeper API (exit 0 = pass)
node scripts/asset-serve-check.js
# MCP tool-contract + HTTP guard matrix (200/403/413/401) — needs docker
bash scripts/mcp-guard-check.sh beeperbox:dev
# x11vnc auth posture (RFB security types) — needs xvfb + x11vnc
bash scripts/vnc-auth-check.sh
# Container: build from source + wait-for-healthy + probe /v1/info
./scripts/smoke-test.sh
docker compose -f docker-compose.yml -f docker-compose.dev.yml up -d --build
# Lite mode (no Docker) — same file the container runs
BEEPER_TOKEN=... node mcp/server.js # HTTP transport on :23375
BEEPER_TOKEN=... node mcp/server.js --stdio # stdio transport
Live-testing working-tree code. A healthy beeperbox container usually runs locally, but its
image is older than the tree. To exercise your edits against the real Beeper API, run the
working-tree server against the container's API on a spare port — never trust the container to be
running your changes:
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.
- 3d ago First seen · 133 lines · 1,903 tokens per session scan A 3c9ccb61b348
beeperbox CLAUDE.md is an instructions file published in the GitHub repository hamr0/beeperbox (23 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,903 tokens to every session, about $0.0095 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
fastapi-langgraph-agent-production-ready-template AGENTS.md
Instructions for wassim249/fastapi-langgraph-agent-production-ready-template, covering ai agent development guide, quick commands, project structure, project overview and quick reference: critical rules.
serve-sim AGENTS.md
Instructions for EvanBacon/serve-sim, covering native build notes, e2e testing with agent-browser and e2e testing via the serve-sim cli.
OpenInstinct AGENTS.md
Instructions for Merit-Systems/OpenInstinct, covering eve agent app, read the docs before writing code, prefer an existing integration, use eve for vercel operations and validate the change.
zhin AGENTS.md
Instructions for zhinjs/zhin, covering zhin.js agent guide, 项目概览, 先读哪些文件, 仓库结构与技术栈 and 分层架构（依赖方向单向，由 harness 强制）.
zhin CLAUDE.md
Instructions for zhinjs/zhin, covering claude.md, project overview, commands, bootstrap (first-time or after clean) and single package.
zhin zhin-plugin.instructions.md
Instructions for zhinjs/zhin, covering zhin plugin runtime authoring, package contract, convention directories, imports and native typescript and command routes.