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.
npx skills add Kihara777/NixKits --skill nix-flake-update-checkgit 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/skills/kihara777/nixkits/nix-flake-update-check)<a href="https://agentmods.dev/skills/kihara777/nixkits/nix-flake-update-check"><img src="https://agentmods.dev/badge/skills/kihara777/nixkits/nix-flake-update-check/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/skills/kihara777/nixkits/nix-flake-update-check"><img src="https://agentmods.dev/badge/skills/kihara777/nixkits/nix-flake-update-check.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 | $0.00201 | $0.07676 |
| Opus 5 | $0.00101 | $0.03838 |
| Sonnet 5 | $0.00040 | $0.01535 |
| Haiku 4.5 | $0.00020 | $0.00768 |
Grade A, and why
nix-flake-update-check scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
latest=$(curl -s "https://api.github.com/repos/$repo/releases/latest" | grep -oP '"tag_name":\s*"\K[^"]+') How it starts
The opening of the file, as written. The whole thing — 463 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nix flake 软件包更新检查（通用）
检查 nix flake 仓库中各软件包的上游发布更新并执行版本升级。
本技能只包含与仓库无关的通用方法。仓库特有的环节（文档同步、维护日志、 内置插件清单等）由仓库适配层提供——见文末「仓库适配层」。
本技能的文件构成
主流程在本文档；两份配套参考按需查阅，不必通读：
| 文件 | 内容 | 何时读 |
|---|---|---|
SKILL.md（本文） |
交互式澄清 + 第 1~10 步主流程 + 适配层契约 | 始终 |
builders.md |
按 builder 的 hash 更新流程、flake.lock 处置 |
第 4 步 |
traps.md |
nixpkgs 漂移陷阱、fail-closed 校验、外链审计、Actions 更新、补丁内版本 | 第 7 步自检命中时 |
交互式澄清：一次流程内解决所有待定项
在开始前先判断所运行的智能体是否支持交互式提问（如 DSH 提供
ask_user_question，可一次提出多个问题并等待用户选择）。支持就积极使用
——凡是不确定、有多种合理做法、或必须由用户拍板的事项，当场问，不要
先按自己的猜测执行完、再让用户在下一条消息里纠正。
为什么这条是强要求：软件更新是多决策点流程（升级策略、跨大版本取舍、 依赖冲突的解法、通道选择、是否部署）。若每个决策点都退化成「猜一次 → 被纠正 → 重来」，一次更新会膨胀成多轮往返，且每次重来都要重跑构建——而构建是 本流程最贵的环节（Rust/python 包动辄数十分钟）。把决策点前置到开始之前， 整个流程才可能一次跑完。
必须提问的情形
| 情形 | 为什么必须问 |
|---|---|
| 跨大版本升级（3.x → 4.x） | 可能含 breaking change、新的硬性要求，或需要用户接受行为变化 |
| 依赖冲突有两种以上合理解法 | 如「抬依赖版本」vs「跳过该包」vs「打补丁放宽校验」——代价与风险差别很大，且有的会破坏上游安全契约 |
| 需要新增 overlay / 补丁 / 额外 vendored 包 | 增加维护面，属结构性改动 |
| 构建时长或体积显著增加 | 用户可能宁愿暂缓 |
| 通道选择（stable / next / alpha） | 取决于用户想跟哪条线，技能无法推断 |
| 是否部署到运行中的系统 | 影响生产环境 |
| 发现的信息与文档记载冲突 | 可能是文档过时，也可能是现状异常，需用户判断 |
提问的写法
- 一次问全：把本轮所有待定项合并成一批提问，不要挤牙膏式地一问一等。
- 给出可选项与代价：每个选项写清影响（尤其「破坏上游契约」这类后果）。
- 给出推荐项并说明理由：把推荐项放第一位，标注「推荐」。
- 能自己查证的不要问：先查 release notes / 上游源码 / 构建报错， 把问题收敛到真正需要人决策的那几个。
不支持交互式提问时（如纯命令行 agent）：把上述待定项汇总成一份清单 一次性输出，并说明每项的影响与推荐做法，然后停下等待——同样避免 「猜完再被纠正」的多轮往返。宁可一次问完，不要边做边猜。
与「先做完再汇报」的取舍
默认行为是自主推进，本技能是例外：因为更新流程的返工成本极高（重建代价）， 提问的成本远低于猜测的错误成本。但只问真正需要决策的——机械步骤 （取 hash、改版本号、同步文档、记日志）自行完成，不要拿流程细节去打扰用户。
适用前提
- 仓库是 nix flake（根目录存在
flake.nix）。 - 包定义以独立
.nix文件形式存在，通常位于packages/（或其他目录）， 由flake.nix经callPackage引用。 - 若仓库布局不同（如所有包写在单个
flake.nix、或位于nix/等目录）， 以第 2 步的自动发现结果为准，不必强行套用目录名。
第 1 步：确认本地仓库
test -f flake.nix && echo "OK: $(grep -oP 'description\s*=\s*"\K[^"]+' flake.nix | head -1)" || echo "ERROR: not in a flake project"
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed · -181 lines · +65 tokens per session 44fe76b6086d
- yesterday First seen · 644 lines · 136 tokens per session scan A f964b54c17ee
nix-flake-update-check is a skill published in the GitHub repository Kihara777/NixKits (26 stars, last pushed today), licensed MIT. It adds 201 tokens to every session and 7,676 once invoked, about $0.0010 per session on Opus 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 2026-09-17.
Other skills, from other repositories
why
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics…
technical-writing
Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.
how
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Can critique architecture. Use why for…
teach
Explain a body of work plainly so a person actually understands it. Runs the how and why skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.
unslop
Cut AI tells from any writing. Must always apply.
quality-code
Standards for writing or modifying handwritten source code. Use when implementing code changes or reviewing handwritten code. Do not use for browsing, explanation, diagnosis without implementation, generated code, or vendored code.