Borrowing it
Nothing to install: this file belongs to embeddedos-org/eAI. 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/embeddedos-org/eAI/master/AGENTS.mdgit clone --depth 1 https://github.com/embeddedos-org/eAIWrote 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/embeddedos-org/eai/agents-md)<a href="https://agentmods.dev/instructions/embeddedos-org/eai/agents-md"><img src="https://agentmods.dev/badge/instructions/embeddedos-org/eai/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/embeddedos-org/eai/agents-md"><img src="https://agentmods.dev/badge/instructions/embeddedos-org/eai/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 | $0.00998 | $0.00998 |
| Opus 5.5 | $0.00399 | $0.00399 |
| Sonnet 5.5 | $0.00200 | $0.00200 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
eAI 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 1mo 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — eAI
eAI (CMake project EAI, v0.2.0) is the on-device AI layer of the EmbeddedOS
ecosystem, written in C (C11): a runtime contract for loading and running
models plus build-selectable runtimes — EAI-Min (lightweight agent runtime
for IoT devices) and EAI-Framework (industrial platform) — with
model-format loaders, optional hardware-accelerator backends, a
brain-computer-interface module, a CLI, and host/embedded platform adapters.
(Provenance: README.md intro, CMakeLists.txt project()/options.)
Layout (from README.md "What's inside")
common/— shared contracts and utilities (types, config, logging, model manifest, runtime contract, tool registry, security/permissions); buildseai_commonplatform/— platform adapters (Linux, Windows, macOS, Android, iOS, container, Zephyr, FreeRTOS, bare-metal, EoS); buildseai_platformmin/— EAI-Min lightweight agent runtime (agent loop, router, KV memory)framework/— EAI-Framework industrial platform (runtimes, connectors, orchestrator, policy, observability)bci/— brain-computer-interface modulemodels/— model manifests and metadataaccel/— accelerator backends (optional Vulkan Compute, CoreML/Metal, Qualcomm QNN)formats/— model format loaderscli/—eaicommand-line toolbindings/— C++ and Python bindingsprofiles/— example profiles:adaptive-edge,bci-assistive,industrial-gateway,mobile-edge,robot-controller,smart-cameratests/— C tests plusunit/,functional/,performance/,simulation/Python suitescmake/toolchains/,ci/,docs/,tools/— cross-compile toolchains, CI build/test scripts, docs, developer tools
CODE_STRUCTURE.md is the detailed, module-by-module developer reference.
Build (from README.md "Build" and CMakePresets.json)
Requires CMake ≥ 3.16 and a C compiler. CMakePresets.json defines the
host/target presets used by CI (e.g. linux-x64-release).
cmake --preset linux-x64-release
cmake --build --preset linux-x64-release
# or without presets
cmake -B build -DCMAKE_BUILD_TYPE=Release
cmake --build build --parallel
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.
- 1mo ago Changed · -9 lines · +340 tokens per session 00feb1012a5a
- 2mo ago First seen · 99 lines · 658 tokens per session scan A eb4af7169d57
eAI AGENTS.md is an instructions file published in the GitHub repository embeddedos-org/eAI (9 stars, last pushed today), licensed MIT. It adds 998 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 2026-08-31.
eAI AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| eAI AGENTS.mdembeddedos-org/eAI | Instructions file | 9 | today | MIT | A | 998 | Codex, OpenCode |
| arm_1a2b_k1l2_cleanCode_avoidDuplicationcolchuck-ai/ai-resource-manager | Instructions file | 24 | 7mo ago | GPL-3.0 | A | 248 | GitHub Copilot |
| arm_1a2b_7g8h_cleanCode_avoidCommentscolchuck-ai/ai-resource-manager | Instructions file | 24 | 7mo ago | GPL-3.0 | A | 231 | GitHub Copilot |
| ai-resource-manager arm_index.instructions.mdcolchuck-ai/ai-resource-manager | Instructions file | 24 | 7mo ago | GPL-3.0 | A | 238 | GitHub Copilot |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |