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/z80dev/lemon/agents-mdgit clone --depth 1 https://github.com/z80dev/lemonWhat 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 | $0.06476 | $0.06476 |
| Opus 5 | $0.03238 | $0.03238 |
| Sonnet 5 | $0.01295 | $0.01295 |
| Haiku 4.5 | $0.00648 | $0.00648 |
Grade A, and why
lemon AGENTS.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 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.
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 — 552 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lemon Agent Guide
Effective agent context for the Lemon LLM interaction stack. Lemon is a BEAM-native stack of Elixir/OTP libraries for LLM interactions, with two flagship products on top: a multi-channel personal assistant and LemonSim, a deterministic model-vs-model simulation arena. The assistant uses the stack for local-first agent work across channels; LemonSim uses it for event-sourced, replay-verified benchmark worlds.
Quick Navigation
| If you want to... | Look in... |
|---|---|
| Add/modify AI provider support | apps/lemon_ai/ |
| Work on model runtime credential glue | apps/lemon_agent/ |
| Work on coding tools or session management | apps/coding_agent/ |
| Modify Telegram/Discord channel adapters | apps/lemon_channels/ |
| Modify SMS/voice transports | apps/lemon_gateway/ |
| Add new messaging channel adapters (X, XMTP, etc.) | apps/lemon_channels/ |
| Modify setup, onboarding, or Hermes migration CLI flows | apps/lemon_cli/ |
| Work on agent routing or message flow | apps/lemon_router/ |
| Build HTTP/WebSocket API features | apps/lemon_control_plane/ |
| Manage configuration, secrets, or storage | apps/lemon_core/ |
| Work on browser capability driver | apps/lemon_browser/ |
| Work on media job capability driver | apps/lemon_media/ |
| Work on LSP capability driver | apps/lemon_lsp/ |
| Build reusable simulation harnesses | apps/lemon_sim/ |
| Work on native in-process subagent spawning | apps/coding_agent/ (task/agent tools, CodingAgent.Coordinator) |
| Create or modify skills and assistant-platform tools | apps/lemon_skills/ |
| Work on Honcho memory integration | apps/lemon_honcho/ |
| Work on deterministic eval harnesses | apps/lemon_evals/ |
| Build cron jobs or automation | apps/lemon_automation/ |
| Work on the web UI | apps/lemon_web/ |
| Debug coding agent via RPC | apps/coding_agent_ui/ |
| Record or search durable agent memory | apps/lemon_memory/ |
| Work on the MCP client/server bridge | apps/lemon_mcp/ |
| Work on the LemonSim control room UI | apps/lemon_sim_ui/ |
| Work on the on-chain TCG shop arena | apps/lemon_tcg/ |
| Write contract tests for platform behaviours | apps/lemon_platform_test/ |
| Work on the X (Twitter) API client | apps/x_api/ |
| Browser automation via CDP/Playwright | clients/lemon-browser-node/ |
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 · 552 lines · 6,476 tokens per session scan A c06fffe33ac4
lemon AGENTS.md is an instructions file published in the GitHub repository z80dev/lemon (129 stars, last pushed 2d ago), licensed MIT. It adds 6,476 tokens to every session, about $0.0324 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
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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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.
langchain 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.