Borrowing it
Nothing to install: this file belongs to petergaultney/lemonaid. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/petergaultney/lemonaid/main/AGENTS.mdgit clone --depth 1 https://github.com/petergaultney/lemonaidWrote 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/petergaultney/lemonaid/agents-md)<a href="https://agentmods.dev/instructions/petergaultney/lemonaid/agents-md"><img src="https://agentmods.dev/badge/instructions/petergaultney/lemonaid/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/petergaultney/lemonaid/agents-md"><img src="https://agentmods.dev/badge/instructions/petergaultney/lemonaid/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01012 | $0.01012 |
| Opus 5.5 | $0.00405 | $0.00405 |
| Sonnet 5.5 | $0.00202 | $0.00202 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
lemonaid 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 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lemonaid Development Guidelines
Never touch the live install or its state
The maintainer's installed lemonaid runs from a checkout, and every hook on the machine
writes their real inbox. A lemon working on lemonaid must not change either.
- Work in a separate worktree or clone. Never edit, switch branches in, or run
uv syncin the checkout the tool is installed from (uv tool list --show-paths/ the.pthunder~/.local/share/uv/tools/lemonaid-inboxsays which). For example,git worktree add ../lemonaid-<branch> -b <branch> main. - Run anything outside pytest through
scripts/sandbox:scripts/sandbox lemonaid ...,scripts/sandbox lma. It points the database, config, state directory, and tmux at.z/sandbox/in your worktree, seeded once from a read-only snapshot. A bareuv run lemonaid ...writes the live inbox. - Never open the live database, config, or
~/.local/state/lemonaidfor writing, and never touch the real tmux server's options or sessions, without asking the maintainer first - including to repair something you broke. Say what happened and what you'd do. - To show the maintainer a change working, give them
scripts/sandbox attachorscripts/sandbox lmafrom the worktree. Making a branch live is their step. - Your own coordination commands are not development use. A lemon working on or
reviewing lemonaid still runs its own
lemonaid brief,tell,inboxandwatchcommands with the installedlemonaid, as its brief asks. They write the live state on purpose, andscripts/sandboxwould hide them from the other lemons.
Before Committing
- Bump the version in
pyproject.tomlif adding features or fixes - Update CHANGES.md with a brief description of what changed
- Update docs/ if the change affects user-facing behavior (new config options go in
docs/config.md) - Update README.md if adding significant features (add to Features list)
Only a change to the product gets a version bump and a CHANGES.md entry. A change that touches only docs or tests gets neither.
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 Changed · +4 lines · +83 tokens per session 867519848c1a
- 5d ago Changed · +12 lines · +131 tokens per session 93b31321baa0
- 7d ago Changed 3b5078d9e1f1
- 8d ago Changed · +2 lines · +28 tokens per session bbfa484c71a2
- 13d ago First seen · 68 lines · 770 tokens per session scan A 1a1189af08c0
lemonaid AGENTS.md is an instructions file published in the GitHub repository petergaultney/lemonaid (11 stars, last pushed today), licensed MIT. It adds 1,012 tokens to every session, about $0.0040 per session on Opus 5.5. 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 2026-09-25.
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).
next.js AGENTS.md
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, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
generative-ai-for-beginners AGENTS.md
AGENTS.md instructions for microsoft/generative-ai-for-beginners, covering agents.md, project overview, setup commands, initial repository setup and clone the repository.