Borrowing it
Nothing to install: this file belongs to Elata-Biosciences/elata-bio-sdk. 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/Elata-Biosciences/elata-bio-sdk/main/AGENTS.mdgit clone --depth 1 https://github.com/Elata-Biosciences/elata-bio-sdkWrote 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/elata-biosciences/elata-bio-sdk/agents-md)<a href="https://agentmods.dev/instructions/elata-biosciences/elata-bio-sdk/agents-md"><img src="https://agentmods.dev/badge/instructions/elata-biosciences/elata-bio-sdk/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/elata-biosciences/elata-bio-sdk/agents-md"><img src="https://agentmods.dev/badge/instructions/elata-biosciences/elata-bio-sdk/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 | $0.03196 | $0.03196 |
| Opus 5 | $0.01598 | $0.01598 |
| Sonnet 5 | $0.00639 | $0.00639 |
| Haiku 4.5 | $0.00320 | $0.00320 |
Grade A, and why
elata-bio-sdk 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 yesterday.
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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Guide
This file is for AI coding agents working in this repository. Use it as a practical playbook for understanding the repo, choosing the right workflow, and avoiding common mistakes.
What This Repo Is
Elata SDK is a mixed Rust + TypeScript monorepo for biosignal tooling:
- EEG core crates and WASM bindings
- Web Bluetooth EEG headset transport (
eeg-web-ble; Muse built-in, extensible) - rPPG processing for web
- Native FFI layers for mobile/native clients
- Demo scaffolding via
create-elata-demo
The repo is not a generic JS monorepo. Many changes cross Rust, generated WASM, TypeScript wrappers, demo apps, and release tooling.
First Things To Read
When starting work, orient with these files first:
- README.md: repo overview, package list, build/demo commands
- run.sh: canonical task runner for build, test, release, and local package workflows
- CONTRIBUTING.md: contribution and verification expectations
- docs/guides/ai-assisted-development.md: map for AI agents—
docs/vselata-docs/tutorials vs packageREADME/llms.txt(includes vendor headset paths) - docs/releasing.md: release flow and publish rules
- docs/create-elata-demo.md: canonical scaffolding workflow
For package-specific work, read the nearest package README and package.json
before changing code.
Treat docs/implementation-plan-*.md as planning or historical context unless
they clearly match the current code. For operational truth, prefer run.sh,
package package.json scripts, package READMEs, and maintainer/scaffolding
docs.
Repo Map
crates/: Rust crates for EEG, rPPG, protocol support, FFI, and bridgespackages/eeg-web: TS wrapper around generated EEG WASM bindingspackages/eeg-web-ble: Web Bluetooth transport for EEG headbands —src/transport/(BleTransport) vssrc/devices/muse/(Muse protocol); open to additionalsrc/devices/modulespackages/rppg-web: TS wrapper and demo tooling for the rPPG pipelinepackages/rppg-models-web: optional ONNX waveform-reconstruction adapter forrppg-webpackages/ppg-web: Muse PPG heart-rate/HRV estimation overHeadbandFrameV1packages/app-metrics: per-user metrics storage for sandboxed appstore appspackages/app-payments: in-app purchases for sandboxed appstore appspackages/app-state: per-user, per-app key-value storage for sandboxed appstore appspackages/biosignal-session: local-first biosignal session recording — contracts, MessagePort wire protocol, Arrow IPC chunk encodingpackages/biosignal-analytics: local analytics over recorded biosignals — metric registry, WASM EEG window features, HRV/statistics, headline scorespackages/create-elata-demo: published scaffolder for demo appseeg-demo/: in-repo EEG browser demoios-demo/,android-demo/: native demosscripts/: helper scripts used by package and release flowsdocs/: architecture, scaffolding, and release docs
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.
- yesterday Changed · +41 lines · +630 tokens per session 5226b8f0c29a
- 6d ago Changed · +20 lines · +347 tokens per session b7ca0befa6a1
- 11d ago First seen · 198 lines · 2,219 tokens per session scan A 385f20cb1310
elata-bio-sdk AGENTS.md is an instructions file published in the GitHub repository Elata-Biosciences/elata-bio-sdk (90 stars, last pushed 2d ago), licensed MIT. It adds 3,196 tokens to every session, about $0.0160 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
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.
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.
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.
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).
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.