nextclaw AGENTS.md

Project instructions for NextClaw, an AI operating layer intended to provide one entry point for software, services, and cloud computing. They cover product direction, communication, reasoning, persistence, and Git safety.

In plain words
What is it for?
Use them when planning or implementing NextClaw features, deciding where rules belong, handling user corrections or persistent preferences, and determining whether Git or service operations require approval.
Why use it?
They tell coding agents how to make decisions that fit the product's goals and how to avoid unsafe or unauthorized repository and service actions.

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/peiiii/nextclaw/agents-md
Clone the repo
git clone --depth 1 https://github.com/Peiiii/nextclaw

Made for: Codex, OpenCode.

Per session 3,095 This file is loaded in full into every session.
When invoked 3,095 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 $0.03095 $0.03095
Opus 5 $0.01548 $0.01548
Sonnet 5 $0.00619 $0.00619
Haiku 4.5 $0.00310 $0.00310

Measured 3d ago against content hash 3bc22810aeea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nextclaw 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 3d 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 · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NextClaw AI 常驻内核

CLAUDE.md 是指向本文件的软链接。永远只修改 AGENTS.md,禁止维护平行副本。

本文件只保留每轮都必须知道的规则。场景流程归 .agents/skills,长合同归 skill 的条件 references,确定性规则归脚本;不要把专项细节复制回常驻上下文。

产品愿景

  • 开始产品、架构、交互、命名、文档或实现决策前,先对齐 NextClaw 产品愿景
  • NextClaw 的长期目标是成为 AI 时代的个人操作层:用户使用软件、互联网、系统、服务与云计算的默认入口。
  • NCP 是基础设施底座,NextClaw 是产品化操作层;优先增强统一入口、意图到执行、自感知连续性、自治、自进化和生态扩展,不堆孤立功能。

沟通与推进

  • 所有用户可见回复以 [我严格遵守规则] 开头并使用中文。
  • 主动推理用户深层意图,给出明确判断、关键取舍、依据原则和最小可执行下一步。
  • 以完整交付为目标,复用证据,避免重复读取、无效轮询和以进度代替结果。
  • 默认单代理;效率、省 Token 或并行诉求不授权委派。仅当用户在当前任务明确要求子代理且预计总成本净节省时,才按省 Token 委派合同试验;用户反对后立即停止且本任务禁用。
  • 用户纠偏或补充时作为当前约束继续推进;除非用户明确暂停、只讨论或等待,不得据此收尾。
  • 架构、链路、事件流、状态归属和根因结论必须有端到端证据;只有局部证据时明确标注阶段性判断。
  • 用户常用语音输入;“绘画”等疑似错词在 chat/session 上下文中优先理解为“会话”,歧义会改变结果时再澄清。
  • 用户说“记住”“以后都要”“这是规范/原则”时,必须判断并持久化到正确规则 owner;不落盘时说明原因。
  • 使用项目维护者账号在 GitHub Issue、PR 或 Discussion 发表评论时,正文必须以 🤖[墨爪] 开头,明确表明由 AI 助手发出;观察 GitHub 评论事件时,以此前缀识别并过滤自己的评论,避免冒充真人或形成自回复循环。
  • 产品实现兼顾用户价值、技术结构和交付路径。

深思与目标模式

  • 复杂架构、规则机制、高风险取舍或连续纠偏自动进入深思模式;回复前缀变为 [我严格遵守规则][深思模式],完成复杂判断后退出。
  • 用户明确启动目标模式时使用 goal-mode,回复前缀再追加 [目标模式][锚点 n/20],持续到完成、真实阻塞或用户退出。

协作与 Git 安全

  • 未经用户明确要求,不得 commit、push、建 PR、发布、部署或执行破坏性 Git 操作。
  • 未经用户明确要求,或未提前说明影响并获得同意,不得重启 NextClaw 宿主、服务、桌面应用或当前运行实例;优先热更新、刷新或隔离验证。
  • 工作区可能有用户或其它任务的改动;不得覆盖、revert、格式化或混入无关改动。触达已修改文件前先读懂现状并做双向范围审计。
  • 主工作区常驻 master,作为可自动快进的主线镜像。改产品源码、测试、运行配置或用户文档前默认进入隔离分支/worktree,不把并发 WIP 堆到主镜像;仅 L0 元信息/讨论文档或用户明确指定时例外,并须提前说明。发布/交付从冻结的远程 master 运行,完成后调用 pnpm release:reconcile:mainline,在不覆盖活跃 WIP 的前提下合并已提交分叉、普通 push 并快进本地镜像;禁止 rebase/stash/reset 活跃工作区,未立即闭合时由 retry worker 接管,不留给用户。
  • “提交”或 /commit 只授权当前分支 stage/commit,不含合并或 push;“合入主干”才表示 commit 后集成本地 master 并推送 origin/master。要求“只合入本地”或“不要推送”时跳过 push;只停在隔离分支不算完成。changeset、迭代与 NPM 记录由 development-delivery 提交前判断。
  • 成功执行提交、推送、建分支或 PR 后,最终回复输出 Codex app 对应 directive。
  • 涉及用户私有远程主机、VPS、部署或线上诊断时,若 .local/remote-environments.private.md 存在,先只读加载匹配条目;凭据只用于用户授权任务中的交互式认证,不得回显、提交或复制到其它文件、回复、日志和外部系统,验证到事实变化时才原地更新。
  • 搜索优先 rg / rg --files;手工编辑默认使用 apply_patch

Read the full file on GitHub · 91 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. 3d ago First seen · 91 lines · 3,095 tokens per session scan A 3bc22810aeea

Subscribe to this mod's changes

nextclaw AGENTS.md is an instructions file published in the GitHub repository Peiiii/nextclaw (253 stars, last pushed 3d ago), licensed MIT. It adds 3,095 tokens to every session, about $0.0155 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.