Borrowing it
Nothing to install: this file belongs to erosTeam/NextE. 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/erosTeam/NextE/main/AGENTS.mdgit clone --depth 1 https://github.com/erosTeam/NextEWrote 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/erosteam/nexte/agents-md)<a href="https://agentmods.dev/instructions/erosteam/nexte/agents-md"><img src="https://agentmods.dev/badge/instructions/erosteam/nexte/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/erosteam/nexte/agents-md"><img src="https://agentmods.dev/badge/instructions/erosteam/nexte/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 | $0.01282 | $0.01282 |
| Opus 5.5 | $0.00513 | $0.00513 |
| Sonnet 5.5 | $0.00256 | $0.00256 |
| Haiku 4.5 | $0.00128 | $0.00128 |
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 18d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
强制约束：未经用户明确允许，禁止创建工作树
- 默认在项目原主仓目录工作。创建任何 Git 工作树前必须取得用户明确允许，并遵守该允许限定的项目、用途和范围；没有明确允许，一律不得创建。
- 本约束适用于命令行、工具托管、临时路径和所有子代理；不得通过派工规避，也不得把旧计划、自动唤醒、代理建议或已有工作树当作新增许可。
- “保护 WIP”“并行开发”“隔离验证”“方便打包”等理由不构成允许。不得通过复制项目源码或额外克隆开发副本规避本约束；应在原主仓审查、整理并及时提交有效改动。
- 已获允许的工作树只用于获准范围；完成后及时将有效成果合回原主仓并退出工作树，未经新的明确允许不得扩展用途或长期保留为另一条开发主线。
NextE agent entry
未经用户明确允许，禁止更改样式；修 bug 也不例外。
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.
每次开始
- 先读 始终生效规则，再进行计划、修改、验证、派工或汇报。
- 用户最新明确要求优先；旧计划、摘要、记忆、租约和自动唤醒不产生新任务或授权。
- 查看当前源码、脚本、工作区与新鲜证据；计划、交接、产物和归档文档都不是当前事实。
- 修改已有行为前，用文件名和符号查询 已拒绝方案；匹配的
REJECTED条目禁止恢复，除非用户审阅失败证据后明确重新允许。
按工作读取
技能绑定是强制的：下表把每类工作钉死到具体技能与文档。压缩或从摘要恢复后，必须按表重读对应技能， 不得凭摘要里的操作模式跳过技能。
| 工作 | 必读 |
|---|---|
| HarmonyOS 源码、构建 | harmony-mandatory-preflight 和 harmony-next 技能，以及 平台约束 |
| 设备、截图、日志、UI 操作 | 另读 harmony-run-device-diagnostics 技能和 设备协议 |
| 本地构建、签名、依赖、版本发布 | 本地开发 |
| 产品语义、验收 | 产品规则 |
| 共享 Reader | 共同职责 |
| EH 集成、Cookie、远端写入 | EH 契约 |
| 漫画翻译 | 漫画翻译设计 |
| 架构、模块边界 | 架构 |
| 规划、计划生命周期 | 路线图 / 计划生命周期 |
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
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.
- 18d ago Changed · +7 lines · +215 tokens per session 4eb1a019eb36
- 23d ago Changed · +12 lines · +302 tokens per session 4d3b52f6a92f
- 24d ago Changed · +2 lines · +21 tokens per session a7c9a124eec6
- 28d ago Changed · +5 lines · +56 tokens per session b16945cba8a9
- 2mo ago Changed · +3 lines · +64 tokens per session 6d33c5e4d158
- 2mo ago First seen · 51 lines · 624 tokens per session scan A 2c9d1e69246f
NextE AGENTS.md is an instructions file published in the GitHub repository erosTeam/NextE (70 stars, last pushed 3d ago), licensed MIT. It adds 1,282 tokens to every session, about $0.0051 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 2026-08-30.
NextE AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| NextE AGENTS.mderosTeam/NextE | Instructions file | 70 | 3d ago | MIT | A | 1,282 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | 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 |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |