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 write-maintenance-loggit 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/write-maintenance-log)<a href="https://agentmods.dev/skills/kihara777/nixkits/write-maintenance-log"><img src="https://agentmods.dev/badge/skills/kihara777/nixkits/write-maintenance-log/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/write-maintenance-log"><img src="https://agentmods.dev/badge/skills/kihara777/nixkits/write-maintenance-log.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 245 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00051 | $0.03753 |
| Opus 5 | $0.00026 | $0.01877 |
| Sonnet 5 | $0.00010 | $0.00751 |
| Haiku 4.5 | $0.00005 | $0.00375 |
Grade A, and why
write-maintenance-log 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 10d 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 — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
维护日志撰写
按 NixKits 统一规范撰写 MAINTENANCE.md 维护记录，确保格式一致、信息完整、多语同步。
自动发现契约
本技能通过纯自然语言约定发现语言扩展：
- 扫描 — 在
skills/translate-*/目录下查找所有翻译技能 - 读取 — 解析各 SKILL.md frontmatter 中的
language_code/display_name/base_language字段 - 注册 — 自动将发现的语言扩展纳入多语同步流程。各翻译技能的 SKILL.md 正文中定义翻译规则（词典、语序调整、假名剥离）和列名映射表（TITLE / SUBTITLE / SUMMARY 等多语对照）。
入口
本技能由 AGENTS.md 规则强制触发：每次 git push 后必须执行入口 1 的 SHA 查重流程。
本技能提供两个独立入口，根据用户意图自动匹配。
入口 1：记入维护记录
触发词：「记入维护记录」「记录本次修复」「写入维护日志」
基于当前对话中完成的软件更新或错误修复，撰写单条维护记录并插入 MAINTENANCE.md。
此入口被
nixkits-check-updates技能在软件更新完成后自动调用。
入口 2：更新维护记录
触发词：「更新维护记录」「补全维护记录」「同步维护日志」
基于 git log 扫描全部提交历史，找出以下未记录的内容并补全：
- 未被记录的
fix(...)/feat(...)提交 - 缺失关联 commit id 的旧记录（回填
| 提交 | 说明 |表） - 格式不统一、行文不规范的历史条目（统一为新格式）
执行流程：
# 1. 提取所有 fix / feat 提交（排除 docs 和 chore(pkgs) 类型）
git log --oneline --all | grep -E 'fix\(|feat\(' | while read hash msg; do
# 检查是否已在 MAINTENANCE.md 中
grep -q "$hash" MAINTENANCE.md || echo "MISSING: $hash $msg"
done
# 2. 对每个缺失的提交：
# a. 按日期分组
# b. 生成摘要（从 commit message 提取）
# c. 按格式规范生成条目
# d. LIFO 插入 MAINTENANCE.md
# 3. 补全已有记录缺失的 commit id
# a. 解析所有现有记录日期
# b. 按 ±2h 窗口匹配未关联的提交
# c. 补充到对应记录的提交表中
# 4. 多语同步并提交
此入口不修改软件版本表中已记录的版本号与 hash 值，仅补充元数据。
记录范围
维护日志覆盖以下类别的变更：
| 类别 | 记录条件 | 示例 |
|---|---|---|
| 软件 | 版本更新或 bug 修复 | chore(pkgs): bump codewhale fix(mcp-searxng): ... |
| 技能 | 新增技能、重大章节添加、bug 修复、重大重构 | feat(skill): extract write-maintenance-log fix(skill): generalize 基本情報 rule refactor(skills): generalize hardcoded content |
| 文档 | 模块/包文档的实质性更新（新增章节、配置指南、故障排查、迁移指南） | docs(mcp-searxng): add CodeWhale config docs(llama-cpp-rocm): add multilingual migration guide |
| 模块 | 新增模块或重大功能添加 | feat(rcc-fix): add NixOS module feat(llama-cpp-rocm): restore modelsPreset |
不记录：纯机械性多语 sync（docs(skills): sync ... to multilingual docs）、仅涉及维护日志本身的提交（docs(MAINTENANCE): ...）。
记录类型
类型 1：软件版本更新
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.
- 10d ago First seen · 319 lines · 51 tokens per session scan A 0e264e477f64
write-maintenance-log is a skill published in the GitHub repository Kihara777/NixKits (25 stars, last pushed 6d ago), licensed MIT. It adds 51 tokens to every session and 3,753 once invoked, about $0.0003 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.
Other skills, from other repositories
china-translate
A Chinese-English translation and localisation guide for technical text and product interfaces. Localisation means adapting wording and cultural references so they sound natural to users in the target language.
content-translator
Translate text content between languages with high quality and natural phrasing. Covers document translation, content localization, and multi-language research support for teams working across language barriers.
translator
Translate text between 100+ languages with automatic source detection. Use when: the user asks to translate text, detect a language, or work with multilingual content. NOT for: translating code/documentation in bulk, summarization, or rewriting text in the same language.
video-subtitles
Generate SRT subtitles from video/audio with translation support. Transcribes Chinese (FunASR/Whisper), English (Whisper), Hebrew (ivrit.ai), translates between languages, burns subtitles into video. Use for creating captions, transcripts, or hardcoded subtitles.
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…
translation
A translation tool for text, files, spreadsheets, and online-shop product listings between Chinese, English, Japanese, Korean, French, German, Spanish, Thai, Vietnamese, and Indonesian.