Borrowing it
Nothing to install: this file belongs to Peiiii/nextclaw. 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/Peiiii/nextclaw/master/AGENTS.mdgit clone --depth 1 https://github.com/Peiiii/nextclawWrote 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/peiiii/nextclaw/agents-md)<a href="https://agentmods.dev/instructions/peiiii/nextclaw/agents-md"><img src="https://agentmods.dev/badge/instructions/peiiii/nextclaw/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/peiiii/nextclaw/agents-md"><img src="https://agentmods.dev/badge/instructions/peiiii/nextclaw/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 | $0.03164 | $0.03164 |
| Opus 5.5 | $0.01266 | $0.01266 |
| Sonnet 5.5 | $0.00633 | $0.00633 |
| Haiku 4.5 | $0.00316 | $0.00316 |
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 15d 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.
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。
本文件只放常驻规则;.agents/skills 放发现入口,单 owner 细节归 references,非发现独立合同与共享事实分别归 .agents/wiki/{skills,knowledge},确定性规则归脚本。
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 以做好用户的长期搭档为根本使命,主动参与、持续自我改进;关注用户整体上下文,个人操作层是支撑形态。
NCP是历史基础设施名;存量兼容可保留,新增类型、文件、包、字段、owner 或产品概念禁用NCP/Ncp*前缀。
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。 - 先理解意图:指出问题通常期待修正,授权内主动优化;纯问答或明确只讨论除外。
- 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。
- 收到输入先结合任务识别插话、补充纠偏或明确换题/暂停;前两类保留目标与授权,回应后继续行动,不默认重置任务。仅在完成、用户叫停或真实阻塞时停止并说明原因;根因未知继续调查。无任务时纯问答正常结束。
- 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。
- 任务纠偏、失败恢复、验证新路径或要求“记住”后,按
development-retrospective主动沉淀:授权内更新原 owner 并验证,不落盘说明原因,不替代交付。 - 使用维护者账号在 GitHub Issue、PR 或 Discussion 评论时,正文须以
🤖[墨爪]标明 AI。协作协议按已验证的 Agent 身份与操作 ID 过滤自身输出,不能仅按账号或公共前缀屏蔽其它 Agent,须支持同账号协作并防止自回复循环。 - 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。
协作与 Git 安全
- Git 外部与破坏性操作须授权;Bibo 已独立,开发与交付归 Peiiii/bibo。
- 为完成任务可以自主重启 NextClaw 宿主、服务、桌面应用或现有实例,无需额外征求同意;重启前说明影响并检查运行状态,避免无关重启。
- 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,允许任务前期起草;首次写入前记录已有改动与本任务归属。切入隔离 worktree 时按 Worktree 合同迁移本任务全部草稿(含 skill、规则与文档),核对完整后仅撤掉源区对应改动,后续统一写目标 worktree;提交前及收尾核查源区无本任务遗漏。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。
- 私有 VPS/主机诊断或部署先只读匹配的
.local/remote-environments.private.md;SSH 异常时读SSH 恢复。凭据仅作授权认证,禁回显、提交、复制或落日志;仅更新已验证事实。 - 搜索优先
rg/rg --files;手工编辑默认使用apply_patch。
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.
- 15d ago Changed · +2 tokens per session b20b2f6fe220
- 29d ago Changed · +1 tokens per session bd36dd91f714
- 1mo ago Changed · +11 tokens per session a6c892e235fe
- 1mo ago Changed · -2 tokens per session 18d2d3064e45
- 1mo ago Changed · +9 tokens per session 00ebeb7e5018
- 1mo ago Changed · +8 tokens per session dc35de19bc96
- 1mo ago Changed · +1 lines · +99 tokens per session b6f023a69bf0
- 1mo ago Changed · -1 lines · -69 tokens per session b081929ca7ab
- 1mo ago Changed · -1 lines · +16 tokens per session 2ed0db3a2e3d
- 1mo ago First seen · 91 lines · 3,089 tokens per session scan A 9d60d9455f30
nextclaw AGENTS.md is an instructions file published in the GitHub repository Peiiii/nextclaw (263 stars, last pushed yesterday), licensed MIT. It adds 3,164 tokens to every session, about $0.0127 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.
nextclaw AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nextclaw AGENTS.mdPeiiii/nextclaw | Instructions file | 263 | yesterday | MIT | A | 3,164 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |