NextE AGENTS.md

Repository instructions for NextE, an application project with rules for code changes, device operations, and different types of development work. They tell an agent what to read before acting and when to stop.

In plain words
What is it for?
They guide work on HarmonyOS, local development, product features, architecture, manga translation, enterprise integration, planning, and device testing.
Why use it?
They prevent outdated plans, unsupported state-management changes, and ambiguous device actions from being treated as safe. They also require a specific check for certain user-interface and state changes.

Instructions file for CodexOpenCode

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/erosteam/nexte/agents-md
Clone the repo
git clone --depth 1 https://github.com/erosTeam/NextE

Made for: Codex, OpenCode.

Per session 624 This file is loaded in full into every session.
When invoked 624 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.

ModelPer sessionOnce invoked
Fable 5 $0.00624 $0.00624
Opus 5 $0.00312 $0.00312
Sonnet 5 $0.00125 $0.00125
Haiku 4.5 $0.00062 $0.00062

Measured 2d ago against content hash 2c9d1e69246f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

NextE 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 · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NextE agent entry

This is the repository entrypoint. Keep durable rules here; put platform, product, device and build details in the linked guides. The current user request is the only source of scope or authorization.

Before acting

  1. Read always-loaded rules.
  2. Read the guide for the work: HarmonyOS, local development, product work, architecture, manga translation, EH integration, or planning / plan lifecycle.
  3. Read the applicable skill before using its workflow. Check current source, scripts, worktree state and fresh evidence; do not treat plans, handoffs, artifacts or archived documents as current facts.

Hard stops

State Management V2

entry/, feature/ and shared/ use V2 state only. Do not add or restore V1 decorators, adapters, allowlists, temporary bridges or key-churn refresh workarounds. If a requested change appears to require V1, stop with source/build evidence and propose a V2 design. For every ArkTS/UI/state change, run:

node scripts/test_v1_decorator_inventory_contract.mjs

The result must be 0 file(s).

Device operations

There is no default device. The user must select a full HDC target or an unambiguous shorthand. Resolve a shorthand against the current Connected output of hdc list targets -v; continue only on one match, and never infer a target from history, artifacts or another task. Before installation, launch, input, screenshot, layout, foreground inspection or logs, acquire the resolved target's lease with scripts/device-lease --device <target> ...; follow device lease.

Pushes

Before any push, run bash scripts/run_ci_preflight.sh and require success. After pushing, inspect the Actions run for the exact pushed commit; local builds or partial checks are not CI proof.

Read the full file on GitHub · 51 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.

  1. 2d ago First seen · 51 lines · 624 tokens per session scan A 2c9d1e69246f

Subscribe to this mod's changes

NextE AGENTS.md is an instructions file published in the GitHub repository erosTeam/NextE (47 stars, last pushed 5d ago), licensed MIT. It adds 624 tokens to every session, about $0.0031 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.