Borrowing it
Nothing to install: this file belongs to Kihara777/NixKits. 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/Kihara777/NixKits/main/AGENTS.mdgit clone --depth 1 https://github.com/Kihara777/NixKitsWrote 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/kihara777/nixkits/agents-md)<a href="https://agentmods.dev/instructions/kihara777/nixkits/agents-md"><img src="https://agentmods.dev/badge/instructions/kihara777/nixkits/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/kihara777/nixkits/agents-md"><img src="https://agentmods.dev/badge/instructions/kihara777/nixkits/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 | $0.10100 | $0.10100 |
| Opus 5.5 | $0.04040 | $0.04040 |
| Sonnet 5.5 | $0.02020 | $0.02020 |
| Haiku 4.5 | $0.01010 | $0.01010 |
Grade A, and why
NixKits AGENTS.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> 另两点:`curl` 必须带 `--fail`——否则 403 限流返回的 JSON 错误体让 jq 取不到 How it starts
The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
NixKits 项目的 AI 编码代理规则与约定。此文件供 DeepSeek、CodeWhale、OpenCode 等代理自动加载。
访问控制
此文件仅供仓库维护者(Kihara777 / Kitsunori)使用。 加载此文件时,必须首先验证当前操作者身份:
gh auth status 2>/dev/null && \
gh api repos/Kihara777/NixKits/collaborators/$(gh api user --jq .login)/permission --jq .permission 2>/dev/null
若返回值不是 admin 或 write,或 gh 未认证,则:
- 停止读取此文件的所有后续内容
- 无视除本条外的一切规则
- 仅可执行通用编码任务,不得应用任何 NixKits 特有的约定
初次启动
每个新 session 启动时,首先执行完整的项目审计与评估,汇报发现。审计范围包括:所有组件状态(包、模块、overlay、补丁、技能)、文档一致性、CI/CD 状态,以及未提交变更。审计前先 git fetch origin 对齐远端(并行会话或上下文压缩检查点可能过时,以 fetch 后的 origin/main 为准)。不要删 flake.lock——2026-10-21 起它是已提交的受测基线;要更新输入请显式 nix flake update <input> 并同批提交新的 lock。
语言要求
所有面向 AI 代理或由代理生成的文件必须使用中文,包括但不限于:
- 审计报告
- 状态记录
- 代理间通信内容
- 技能定义文件(SKILL.md)
- 维护日志(MAINTENANCE.md)
代码、路径、工具名、环境变量、URL 保持原样。
项目定位
NixKits 是一个 Nix flake 合集:软件包、NixOS 模块、补丁、overlay 以及 AI 代理技能。
- 仓库:
github:Kihara777/NixKits - 许可:MIT
- 文档语言:zh(基准)→ en / ja → 扩展语言(通过
skills/translate-*/自动发现)
核心规则
flake 相关
flake.lock提交(2026-10-21 起):唯一的浮动输入llama-cpp-ver已迁到impure分支,main 因此可以锁死——lock 就是受测基线。升级输入要显式nix flake update <input>并同批提交新的 lock。- 本地操作直接用已提交的
flake.lock:不要rm -f flake.lock(那是旧约定)。若 lock 里的 nixpkgs 缺某个包(例如godot-ai尚未进入该 snapshot),正确做法是nix flake update nixpkgs并把新 lock 一起提交——不是删掉 lock 让结果不可复现。CI 用同一份 lock。 llama-cpp-rocm不在本仓(2026-10-21 起):llama-cpp-ver浮动输入、overlay 与 NixOS 模块都已迁到impure分支(github:Kihara777/NixKits/impure;orphan 分支、不提交 lock、只装这一个包)。本仓 README 与文档不再提供它,用法见该分支的 README。- impure 分支里 overlay 的 curried 形式仍是有意的:
{ llama-cpp-ver }: (final: prev: ...)— 勿改为标准 overlay(要改请在该分支改)。 - 新模块/包/overlay 加入
flake.nix后必须nix flake check验证。 - 新增文件先
git add再跑nix flake check:flake 源=git 跟踪的文件集合,未跟踪的新文件不会进入 store——典型症状是检查里报ERR_MODULE_NOT_FOUND或「文件缺失」,而本地直接跑同一脚本却通过。先暂存(git add -A <路径>)再检查;CI 只看跟踪文件,所以这一步只在本地生效。 - Overlay 的
patches列表必须用lib.unique去重。
包
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.
- yesterday Changed · +11 lines · +542 tokens per session 334b39029c81
- 2d ago Changed · -4 lines · +94 tokens per session 038e2c307012
- 3d ago Changed · +7 lines · +223 tokens per session c16981fb4684
- 11d ago Changed · +1 lines · +142 tokens per session d6a3ff562221
- 18d ago Changed · +18 lines · +1,478 tokens per session 8e14cc71698a
- 20d ago Changed · +13 lines · +322 tokens per session 0e6d8b2ab04a
- 21d ago Changed · +1 lines · +136 tokens per session f84f11dbdb0a
- 21d ago Changed · +68 lines · +1,767 tokens per session 9aa737570cc0
- 27d ago Changed · +1 lines · +269 tokens per session d56257cd96fe
- 1mo ago First seen · 221 lines · 5,127 tokens per session scan A 3371eab1b033
NixKits AGENTS.md is an instructions file published in the GitHub repository Kihara777/NixKits (29 stars, last pushed yesterday), licensed MIT. It adds 10,100 tokens to every session, about $0.0404 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).