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/bborn/lewsnetter/agents-mdgit clone --depth 1 https://github.com/bborn/lewsnetterWhat 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 | $0.02323 | $0.02323 |
| Opus 5 | $0.01162 | $0.01162 |
| Sonnet 5 | $0.00465 | $0.00465 |
| Haiku 4.5 | $0.00232 | $0.00232 |
Grade A, and why
lewsnetter AGENTS.md scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST https://your-domain.com/mcp/messages \ How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI coding agents (Claude Code, Cursor, Codex, etc.) working on this repo. Humans should read README.md instead.
What this app is
Lewsnetter is an open-source email marketing platform on Rails 8 + BulletTrain, with a built-in MCP server and an in-app agent. The agent (powered by ruby_llm's acts_as_chat) and external MCP clients share the same tool registry — anything the agent can do, an external client can do via /mcp/messages.
The fastest way to grok the architecture: read the design spec at docs/superpowers/specs/2026-05-15-mcp-and-in-app-agent-design.md. It's the source-of-truth for "why is it built this way."
Codebase map
| Path | What's there |
|---|---|
app/mcp/ |
MCP server: Mcp::Server, Mcp::Tool::Base, Mcp::DoorkeeperAuth, all 43 tools under tools/<group>/<verb>.rb, 6 markdown skills under skills/ |
app/services/llm/configuration.rb |
Single source of truth for LLM keys/base URL/provider. All AI code reads this. |
app/services/chats/tool_adapter.rb |
Bridges Mcp::Tool::Base → RubyLLM::Tool for the in-app agent (so external MCP and in-app agent share one tool surface). |
app/services/ai/ |
Three task-specific AI services (campaign drafter, segment translator, post-send analyst). The llm_* MCP tools wrap these. |
app/services/campaign_renderer.rb |
Renders a campaign body for one subscriber: Liquid substitution → markdown → MJML → HTML → premailer-inlined. |
app/channels/chat_channel.rb |
ActionCable channel for the in-app agent. Streaming + tool indicators. |
app/models/{chat,message,tool_call,model}.rb |
acts_as_chat from ruby_llm. Don't add custom logic here unless necessary. |
app/controllers/well_known_controller.rb |
OAuth 2.1 RFC 8414 + 9728 metadata endpoints. |
app/controllers/oauth/registrations_controller.rb |
RFC 7591 dynamic client registration for MCP clients. |
config/initializers/ruby_llm.rb |
LLM key + gateway URL wiring. |
config/initializers/cloudflare_ai_gateway.rb |
Optional CF AI Gateway BYOK support. Self-contained — copy to support a different gateway. |
config/deploy.yml |
Kamal 2 production deploy config. |
docs/superpowers/specs/ |
Design specs (the why). |
docs/superpowers/plans/ |
Implementation plans, phase by phase (the how). |
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.
- 2d ago First seen · 171 lines · 2,323 tokens per session scan A ec595731f0ac
lewsnetter AGENTS.md is an instructions file published in the GitHub repository bborn/lewsnetter (329 stars, last pushed 1mo ago), licensed MIT. It adds 2,323 tokens to every session, about $0.0116 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
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).
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.