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 agentmods add skills/volcengine/volcengine-skills/volcengine-db-supabasenpx skills add volcengine/volcengine-skills --skill volcengine-db-supabasegit clone --depth 1 https://github.com/volcengine/volcengine-skillsWrote 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/volcengine/volcengine-skills/volcengine-db-supabase)<a href="https://agentmods.dev/skills/volcengine/volcengine-skills/volcengine-db-supabase"><img src="https://agentmods.dev/badge/skills/volcengine/volcengine-skills/volcengine-db-supabase.svg" alt="Measured on agentmods" 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 | $0.00239 | $0.07340 |
| Opus 5 | $0.00120 | $0.03670 |
| Sonnet 5 | $0.00048 | $0.01468 |
| Haiku 4.5 | $0.00024 | $0.00734 |
Grade A, and why
volcengine-db-supabase 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 4d 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.
This is a copy
91% identical to byted-supabase — 38 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
火山引擎 AI 原生 BaaS 平台 · Supabase 版
本 Skill 用于在对话中充当火山引擎「AI 原生 BaaS 平台 Supabase 版」的智能运维与开发代理。
ℹ️ 这是火山引擎自研的 AI 原生 BaaS 平台（Supabase 版），不是官方开源 Supabase。 它在 Supabase 协议/生态之上做了火山引擎的平台化适配，与官方存在差异：
- 用
byted-supabase-cli操作（不是官方supabaseCLI），通过 火山引擎账号 / AK-SK 鉴权；- 资源模型为 workspace（工作区）/ branch（分支）/ compute（算力），并有
endpoints、computes等火山专有命令；- 部分命令、参数与行为与官方 Supabase CLI 不同。
👉 操作以本 Skill 文档与
byted-supabase-cli <command> --help为准，不要套用官方 Supabase CLI 的命令习惯。
它会：
- 识别用户的 Supabase 自然语言需求
- 直接调用
byted-supabase-cli命令行工具获取实时结果 - 基于返回结果做解释、排障和下一步建议
核心原则
本节为通用工作纪律，任何 Supabase 任务都应遵守。
1. 平台演进快 —— 先查在线文档/发布记录，不要只信训练数据。
命令、参数、config 项、API 约定会随版本变化。动手前先查火山引擎官方文档与发布记录（见文末在线文档），尤其涉及不确定的命令/参数时；CLI 子命令一律 byted-supabase-cli <command> --help 现查，不要凭记忆猜命令。
2. 验证你的工作。 任何变更落地后，再跑一条只读查询确认生效。没有验证的修复＝未完成。
3. 从错误中恢复，不要死循环。 同一方法连续失败 2-3 次就停下来换思路：换方法、查文档、更仔细地看报错、必要时查日志。Supabase 类问题不总是靠重试同一条命令解决。
4. 把表暴露给 Data API（REST）。 新建的表不一定自动通过 Data API 暴露。若要让 anon / authenticated 角色经 REST 访问某表，需显式 GRANT。
注意：这与 RLS 是两回事 —— Data API 暴露 + 角色授权决定表是否可达；RLS 决定表可达后哪些行可见。当用户反馈"SQL 建的表访问不到"，先确认是否已授权这两个角色。对外（anon/authenticated）授权时务必同时启用 RLS。
5. ⛔ 高危红线：projects stop（暂停 workspace）会让客户业务彻底不可用。
暂停后的实例无法靠客户 IO / 访问流量自动唤醒（这与分支休眠的「访问即唤醒」本质不同）——整个 workspace 及其下所有分支停服，REST / Auth / Storage / 直连 DB 全部不可达，必须由人手动 projects start 才能恢复。因此执行 projects stop 前必须：
- 向用户明确复述影响并取得二次确认——「这会停掉整个 workspace
<ref>，期间客户业务完全不可用、且不会自动恢复，确认吗？」- 核对目标
ref无误，绝不停错 workspace；- 绝不把它当作「重启 / 休眠 / 省资源」的手段——重启用
branches restart，休眠是平台自动行为，二者都不会导致业务停服。（
projects delete同属不可逆高危操作，同样需先确认。）
6. 暴露 schema 内的表必须启用 RLS。 任何对外暴露的 schema（默认含 public）里的每张表都要 ENABLE ROW LEVEL SECURITY；私有 schema 也建议启用作为纵深防御。启用后，按真实访问模型写策略，不要无脑给每张表套同一个 auth.uid() 模式。
7. 安全 checklist。 凡涉及 Auth、RLS、视图、Storage 或用户数据的任务，逐条过一遍下面这些 Supabase 特有的安全陷阱（完整版见 references/security-guide.md）：
What ships with it
20 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.
- references/app-integration-guide.md 14 KB
- references/deploy-provider.md 5.6 KB
- references/edge-function-dev-guide.md 9.4 KB
- references/iam-permission-guide.md 3.5 KB
- references/pg-best-practices/advanced.md 3.8 KB
- references/pg-best-practices/conn.md 6.5 KB
- references/pg-best-practices/data.md 6.0 KB
- references/pg-best-practices/index.md 1.7 KB
- references/pg-best-practices/lock.md 6.7 KB
- references/pg-best-practices/monitor.md 4.6 KB
- references/pg-best-practices/query.md 7.1 KB
- references/pg-best-practices/schema.md 9.9 KB
- references/pg-best-practices/security.md 7.0 KB
- references/rls-guide.md 9.4 KB
- references/schema-guide.md 8.4 KB
- references/security-guide.md 6.2 KB
- references/sql-playbook.md 5.6 KB
- references/tool-reference.md 23 KB
- references/workflows.md 8.0 KB
- scripts/supabase_dataplane.py 31 KB runs code
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.
- 4d ago First seen · 317 lines · 239 tokens per session scan A 8fbb740658fe
volcengine-db-supabase is a skill published in the GitHub repository volcengine/volcengine-skills (19 stars, last pushed 3d ago), licensed MIT. It adds 239 tokens to every session and 7,340 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to byted-supabase, differing in 38 lines, and is treated as a copy.
Other skills, from other repositories
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
debugging
How to debug tursodb using Bytecode comparison, logging, ThreadSanitizer, deterministic simulation, and corruption analysis tools.
sdk-design
Doctrine for designing and evolving any SDK Grida ships — TypeScript, Rust, or otherwise. "SDK" here means a surface that crosses a foreign-or-foreign-treated boundary: published packages, separately-versioned consumers, FFI bindings, public-by-design modules. An SDK's job is to refuse; a strict, honest surface…
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
supabase
Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…
nornicdb-cypher-queries
Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.