Borrowing it
Nothing to install: this file belongs to SkillNerds/xskill. 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/SkillNerds/xskill/main/.agents/skills/xskill-registry-db-first/SKILL.mdgit clone --depth 1 https://github.com/SkillNerds/xskillWrote 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/skillnerds/xskill/xskill-registry-db-first)<a href="https://agentmods.dev/skills/skillnerds/xskill/xskill-registry-db-first"><img src="https://agentmods.dev/badge/skills/skillnerds/xskill/xskill-registry-db-first.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00073 | $0.00576 |
| Opus 5 | $0.00036 | $0.00288 |
| Sonnet 5 | $0.00015 | $0.00115 |
| Haiku 4.5 | $0.00007 | $0.00058 |
Grade A, and why
xskill-registry-db-first 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 8d 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.
What it actually says
XSkill 盘与库
改读数据相关代码，或审查业务请求是否又在扫盘时，先看本 skill。
各库职责与每张表的 schema 见 databases.md。
架构
整体分三层。
文件系统存内容真相，例如 skill 目录里的文件。这些内容不会在每次面板请求时被重新扫描聚合。
有 worker 定期把文件系统上需要给业务侧查询的信息同步进 SQLite。同步可以按文件是否变化做增量。新的「盘到库」需求应并进已有扫描过程，而不是再开一轮同等规模的全量遍历。
面板、对外 API、推荐与其它业务读请求，一律通过数据库访问投影后的数据。业务侧不自己搭扫盘逻辑去凑结果。
内核里的 agent loop 在跑管线时可以直接读写文件系统，这是写真相的一侧，与业务读路径分开。
规则
业务面新增或修改请求时，所需数据从对应数据库取。不允许在业务请求路径里私自增加扫盘、全目录遍历、按请求反复读盘聚合。
若发现库与盘不一致，应修同步入口，而不是在查询里临时扫盘兜底。
若有新的文件系统到数据库的同步需求，去改现有的扫描同步 worker，把新投影挂进同一次遍历。不要为每个新需求再加一轮 N 加一的全量扫盘，以保持 IO 可控。
新建业务库前先查 databases.md。已有库能覆盖的，不要平行再造一套真相。
多实例或独立 home 访问库时，路径要显式，避免误连全局默认库。
检查
- 这次读的数据属于哪一个库？见 databases.md。
- 改的是业务读路径，还是内核写盘 / worker 同步？三者不要混用扫盘策略。
- 若要加盘到库同步，是否已并进现有 worker 的同一轮扫描？
- PR 是否在面板或 API 热路径新增了扫盘？有则打回。
What ships with it
1 file 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.
- 8d ago First seen · 45 lines · 73 tokens per session scan A ffea73c16632
xskill-registry-db-first is a skill published in the GitHub repository SkillNerds/xskill (122 stars, last pushed 6d ago), licensed MIT. It adds 73 tokens to every session and 576 once invoked, about $0.0004 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
redteam-sqli-detail-pack
Domain routing and boundary guidance for authorized SQL injection testing, including union-based, blind, error-based, stacked query, and second-order SQL injection variants. Use when a task belongs to the SQL injection domain and needs scope, evidence, pivot, or exit criteria.
reversi-master
One-click install + model switch:Claude Code,Codex CLI (OpenAI), Grok Build (xAI), DeepSeek Harness, Kimi Code (Moonshot) ,Qwen Code,Aider,OpenCode,MiMo Code (Xiaomi),ZCode (Z.AI),OpenClaw,Pi,OpenScience,Vibe-Trading,Claude Desktop (3P profile),ChatGPT desktop,OpenCode Desktop.
Trash Talk
AI becomes provocative and mocks the opponent during gameplay.
sqlite-expert
SQLite expert for WAL mode, query optimization, embedded patterns, and advanced features.
vector-db
Vector database expert for embeddings, similarity search, RAG patterns, and indexing strategies.
elasticsearch
Elasticsearch expert for queries, mappings, aggregations, index management, and cluster operations.