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/btafoya/mailsandbox/claude-mdgit clone --depth 1 https://github.com/btafoya/mailsandboxWrote 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/btafoya/mailsandbox/claude-md)<a href="https://agentmods.dev/instructions/btafoya/mailsandbox/claude-md"><img src="https://agentmods.dev/badge/instructions/btafoya/mailsandbox/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 | $0.01392 | $0.01392 |
| Opus 5 | $0.00696 | $0.00696 |
| Sonnet 5 | $0.00278 | $0.00278 |
| Haiku 4.5 | $0.00139 | $0.00139 |
Grade A, and why
mailsandbox 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 — 157 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 Overview
MailSandbox is an email and SMTP testing tool for developers. It captures emails via SMTP (port 1025), provides a web UI (port 8025) for viewing/testing, and includes a REST API for automation.
Tech Stack: Go 1.24.3 backend, Vue 3 + Bootstrap 5 frontend, SQLite storage, WebSockets for real-time updates
Essential Commands
Running MailSandbox
# Run locally with default settings
go run main.go
# Run with custom ports
go run main.go --smtp 0.0.0.0:1025 --ui 0.0.0.0:8025
Development Workflow
# Frontend development (watch mode)
npm install
npm run watch
# Build for production
npm run package
CGO_ENABLED=0 go build -ldflags "-s -w" -o mailsandbox
Testing
# Run Go tests for specific packages
go test ./internal/storage ./server -v
# Run all tests (use -p 1 to avoid parallel execution issues)
go test -p 1 ./internal/storage ./server ./internal/smtpd ./internal/pop3 ./internal/tools ./internal/html2text ./internal/htmlcheck ./internal/linkcheck -v
# Run a single test
go test ./internal/storage -v -run TestSpecificFunction
Code Quality
# Format Go code (REQUIRED before commits)
gofmt -s -w .
# Check Go formatting
gofmt -s -d .
# Lint JavaScript/Vue
npm run lint
# Fix JS/Vue linting issues
npm run lint-fix
Architecture
/internal/ - Private packages (core business logic)
/smtpd/ - SMTP server implementation
/storage/ - Database layer (SQLite/RQLite)
/auth/ - Authentication logic
/htmlcheck/ - HTML compatibility checking
/linkcheck/ - Link validation
/pop3/ - POP3 server (optional)
/server/ - HTTP server and API
/apiv1/ - REST API v1 endpoints
/ui-src/ - Vue.js source code
/ui/ - Compiled/embedded UI assets
/websockets/ - WebSocket handlers for real-time updates
/config/ - Application configuration
main.go - Application entry point
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 · 157 lines · 1,392 tokens per session scan A 3fb72e217e81
mailsandbox CLAUDE.md is an instructions file published in the GitHub repository btafoya/mailsandbox (7 stars, last pushed 11mo ago), licensed MIT. It adds 1,392 tokens to every session, about $0.0070 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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.