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 0fuk/OpenACCP --skill db-cutovergit clone --depth 1 https://github.com/0fuk/OpenACCPWrote 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/0fuk/openaccp/db-cutover)<a href="https://agentmods.dev/skills/0fuk/openaccp/db-cutover"><img src="https://agentmods.dev/badge/skills/0fuk/openaccp/db-cutover/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/0fuk/openaccp/db-cutover"><img src="https://agentmods.dev/badge/skills/0fuk/openaccp/db-cutover.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 | $0.00000 | $0.02944 |
| Opus 5.5 | $0.00000 | $0.01178 |
| Sonnet 5.5 | $0.00000 | $0.00589 |
| Haiku 4.5 | $0.00000 | $0.00294 |
Grade A, and why
db-cutover 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 2d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/db-cutover — 旧系统快照 → 新系统换库(读取 · 验真 · 研判 · 方案 · 配置 · 彩排 · 切库 · 收口)
存在理由:换库是公司级不可逆动作,每次都带一份新的旧系统导出、一套新的业务口径、一个漂移过的库结构。2026-09-21 第一次换库靠临时工具与人肉串接跑通;2026-10-08 第二次 owner 要求固化。本 skill 是固定流程与标准;程序在 C:\VyqoAI\Yirun\部署相关\数据库导入程序(独立仓,远端 github),两者同步迭代:流程改了改这里,规则改了改程序的快照配置,不许在对话里口头定口径。项目事实(服务器、库名、lane、台账)读 PROJECT-PROFILE.md。
0 · 铁律(任一条不满足 = 不切)
- 终版快照 = 旧系统停写后导出的那份;白天导的只能彩排。停写后若仍有零星写入,切后按「差量补录」走(§7),不重导。
- 整库换,不就地改:当晚克隆生产 → 在克隆上洗 / 清 / 灌 / 对账 → 开门前 swap;旧正库改名保留 + 切前 dump 锚,分钟级可回滚。
- 全部以新导入为准(owner 2026-10-08 口径):双跑期新系统里的单据 / 划扣 / 库存流水洗掉;员工 / 账号 / 权限 / 凭据 / 卡模板 / 目录版本 / 项目变更审批保留。改口径 = 改快照配置的
wash段并记 owner 原话。 - 零解释转录 + 规则落配置:导入器不猜业务;每条业务规则(特价可赠送、适用门店只记录、无手机跳过、门店别名、关店迁移)都是快照配置里的一行,带 owner 原话与日期。
- 幂等二遍零变化 + 逐店对账四平(储值本金 / 赠金 / 欠款 / 通卡余;券数、卡数、次卡余额按店)是过门条件;脚本口径差必须有书面解释并被 owner 认可过,不许「大致对」。
- 个人信息零原值:源表格只在本机
公司资料\与服务器工作目录;交回件 / 日志 / 仓库 / 信箱只放聚合数与客户号;服务器源件切完即删并记时刻。 - 凭据不入命令行;服务器动作只由部署线 / 凭据线按令执行;生产写只经执行令。
1 · 八步与产物(每步一个文件,缺一步不许进下一步)
| 步 | 做什么 | 产物(协调目录) | 过门判据 |
|---|---|---|---|
| ① 读取 | 解包、列清单、逐表画像(行数 / 门店分布 / 状态 / 时间上下限 / 手机形态 / 金额合计);找出「新出现的表与列」 | C<n>-快照画像-<日期>.md + 画像脚本留程序仓 snapshots/<日期>/profile.* |
每张表有画像;最晚写入时刻已标;新表 / 新列逐一列出 |
| ② 验真 | 对上一期快照与生产现值逐项比;同名不同日的文件按内容判新旧(行集差、最近到店 max、md5);README / 门店口头口径逐条落字 | 画像件「对照」节 | 每个数字有出处;重复文件已判定取舍 |
| ③ 研判 | 生产只读取「换库以来真实写入」8 组(单据 / 消耗 / 客户 / 库存 / 员工权限 / 审批 / 底数 / 受触客户);判洗单范围与风险 | 致CRED-令-…只读取数 → CRED-交回-…;C<n>-评估-…md |
评估件有「结论 / 画像 / 导入器差异 / 规则处置 / 换库方式 / 候 owner / 前置清单」七节;候 owner 项带推荐与代价 |
| ④ 方案 | 按程序仓 RUNBOOK.md 定本期:阶段顺序、每阶段执行体、彩排与切库窗口、回滚点、门店动作 |
工单集(五门台账)C<n>-工单集-CUT<日期>.md |
每张卡六要素 + 五门格;执行体点名 |
| ⑤ 配置 | 写快照配置 snapshots/<日期>/config.json(文件名 / sheet 名 / 门店别名 / 规则 / 洗单范围 / 快照键);导入器升级到当前库结构(SCHEMA_PIN = 生产 tag),单测 + 本机真库 rehearse 绿;新格式(新系统源)另写导入段,不塞进旧导入器 |
程序仓 commit + 推远端;V-交回-… |
inspect 零表头违规;rehearse 全 ok;两遍零变化;无手机跳过清单已出给门店 |
| ⑥ 彩排 | 服务器生产克隆库全流程:洗 → 清旧批 → 灌(各源)→ 库存换码导入 → 目录刷新 → 二遍 → reconcile → 65 张非单据表与生产哈希比对 → 候选库换到演练站给真人看一天 | DEPLOYX-交回-彩排-…;对账表(按店,给门店签) |
四平;非单据表差异只剩「已知成因」;演练站真人无红 |
| ⑦ 切库 | 执行令(五拍:现场 / 构建物不变 / 窗口前复核 / 停 api → 冻结终比 → 候选库会话失效 → dbswap preflight / anchor / adopt / prepare / verify / swap → 起 api / 切后冒烟);全员重登 | 致DEPLOYX-执行令-…;DEPLOYX-交回-… |
SWITCH_OK;冒烟逐项等于彩排读数;登录会话 = 0 |
| ⑧ 收口 | 差量补录(停写后旧系统零星写入,门店报清单,按单补);门店首日值守;旧正库 / 锚保留期;服务器源件删除;程序仓打 tag cutover-<日期>;CLAUDE.md 生产现役行加「库 = <快照日期>」;台账 |
C<n>-收口-CUT<日期>.md |
全部有路径;补录清单归零或挂候 owner |
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.
- 2d ago First seen · 54 lines · 0 tokens per session scan A c07479e0fce3
db-cutover is a skill published in the GitHub repository 0fuk/OpenACCP (2 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,944 tokens. 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 2026-10-14.
Other skills, from other repositories
handoff-mesh
Built-in communication layer for multi-agent setups. Full-mesh handoff folders (any agent can hand off to any other), an hourly watcher that surfaces open handoffs, weekly archive cleanup, and a completion-reporting loop so every handoff is handled AND verified. The durable 'brain' counterpart to real-time channels…
api-canvas
DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…
api-mirror
Stand up a persistent, self-refreshing local mirror of a bulk upstream dataset with the MirrorService (@cyanheads/mcp-ts-core/mirror). Use when a server wraps a large or slow API and should query a synced local index (embedded SQLite + FTS5) instead of paginating the live API per request.
oma-db
Design schemas and migrations, tune queries, or plan vector retrieval and database operations. Application API implementation uses oma-backend.
moai-platform-database-cloud
Cloud database platform specialist covering Neon (serverless PostgreSQL), Supabase (PostgreSQL 16 with real-time), and Firebase Firestore (NoSQL with offline sync). Use when choosing or setting up cloud databases.
sql_query
A procedure for answering data questions with read-only SQL queries, such as counting users or orders. It first finds the available data source and relevant tables, then checks their columns before running a query.