What is eAI AGENTS.md?

Role instructions for eAI, dividing software work among planning, architecture, backend, frontend, testing, security, performance, and review roles.

Use them to guide agents through planning tasks, designing structure, building APIs or interfaces, testing, checking security and performance, and reviewing completed work.

They clarify who owns each part of a change and keep implementation separate from approval, which helps reduce missed problems during review.

eAI AGENTS.md — Instructions file by embeddedos-org

Install

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.

agentmods

npx agentmods add instructions/embeddedos-org/eai/agents-md

Clone the repo

git clone --depth 1 https://github.com/embeddedos-org/eAI

Made for: Codex, OpenCode.

Per session 658 This file is loaded in full into every session.

When invoked 658 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00658	$0.00658
Opus 5	$0.00329	$0.00329
Sonnet 5	$0.00132	$0.00132
Haiku 4.5	$0.00066	$0.00066

Measured 2d ago against content hash eb4af7169d57, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

AGENTS.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Responsibilities

Each role owns a slice of the work and does only that slice. Full briefs are in .ai/. These are responsibilities, not a required agent count — one agent may hold several roles on a small change. Split when the roles need genuinely different context, not by default.

One rule is structural rather than stylistic: whoever implements does not approve. Review is a separate role because self-review reliably misses the thing the implementer already believes is correct.

Planner — .ai/planner.md

Understand the request.
Break work into tasks.
Assign work.

Architect — .ai/architect.md

Design structure.
Choose patterns.
Own dependencies, scalability and maintainability.

Backend — .ai/backend.md

APIs
Database
Business logic

Frontend — .ai/frontend.md

UI
Components
Accessibility

Testing — .ai/testing.md

Unit tests
Integration tests
Regression tests

Security — .ai/security.md

Authentication and authorization
Validation
Secrets
Dependency review

Performance — .ai/performance.md

Profiling
Optimization
Scalability

Reviewer — .ai/reviewer.md

Final review
Verify requirements
Merge findings

Documentation — .ai/docs.md

README
API docs
Changelog
Migration and architecture notes

Release — .ai/release.md

Release notes
Deployment preparation
Rollback guidance

Switching roles

Switch when the task changes domain, when specialist knowledge is required, when independent review is required, or when the context has grown past what one agent can hold accurately. Every switch runs the protocol in HANDOFF.md.

Finding work that is not yours

You will. The rule is: record it, do not absorb it, do not drop it.

Read the full file on GitHub · 99 lines

Changes

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 · 99 lines · 658 tokens per session scan A eb4af7169d57

Subscribe to this mod's changes

eAI AGENTS.md is an instructions file published in the GitHub repository embeddedos-org/eAI (5 stars, last pushed 5d ago), licensed MIT. It adds 658 tokens to every session, about $0.0033 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.

ai ai-agents ai-assistant ai-tools

eAI AGENTS.md