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/emilyli2020/wave/agents-mdgit clone --depth 1 https://github.com/emilyLi2020/WAVEWhat 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 | $0.07117 | $0.07117 |
| Opus 5 | $0.03558 | $0.03558 |
| Sonnet 5 | $0.01423 | $0.01423 |
| Haiku 4.5 | $0.00712 | $0.00712 |
Grade A, and why
WAVE 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Overview
WAVE is an AI-powered urge surfing companion for people in Substance Use Disorder (SUD) recovery. It guides patients through evidence-based urge surfing sessions (Marlatt's Mindfulness-Based Relapse Prevention protocol), personalized in real time by the patient's current medication status, craving intensity, and trigger. Over time it learns each patient's personal high-risk windows and fires prophylactic notifications 15 minutes before a predicted craving, intervening during the anticipation phase when patients still have executive function.
The production vision is a React Native mobile app that runs Gemma 4 entirely on-device with all data stored locally (encrypted SQLite). The hackathon deliverable is a Next.js web demo in client/ that showcases the session UX, medication-aware prompting, and pattern dashboard. Both surfaces read from the same PRD in PRD.md.
Repo Layout
client/— Next.js 16 (App Router) + TypeScript + Tailwind v4 web demo. This is the active hackathon surface and whatpnpm dev/npm run devruns. Includesapp/routes, scripted session chunks, the multi-turn check-in UI, dashboard/history/insights pages, and developer-only training screens.supabase/migrations/— historical SQL migrations for an earlier demo storage path. The current checked-in web demo uses mock data / local UI state; production mobile replaces this with encrypted on-device SQLite..agents/skills/,.claude/skills/— Cursor / Claude Code agent skills (domain-to-spec,scaffold-frontend,scaffold-backend,v0-prompt-crafter,demo-prep, etc.). Do not edit these during feature work.frontend/,backend/,web/,clients/— Legacy or stale paths. Do not use. The live app is inclient/.AGENTS.md— This file. Shared instructions for every AI agent working in the repo.PRD.md— Product Requirements Document. The source of truth for what to build and the medication-aware prompt logic.README.md— Human-facing quickstart.
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 · 192 lines · 7,117 tokens per session scan A 10a11bc1ac34
WAVE AGENTS.md is an instructions file published in the GitHub repository emilyLi2020/WAVE (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 7,117 tokens to every session, about $0.0356 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
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.