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 YuDefine/nuxt-supabase-starter --skill rls-performancegit clone --depth 1 https://github.com/YuDefine/nuxt-supabase-starterWrote 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/yudefine/nuxt-supabase-starter/rls-performance)<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/rls-performance"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/rls-performance/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/yudefine/nuxt-supabase-starter/rls-performance"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/rls-performance.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00058 | $0.00668 |
| Opus 5.5 | $0.00023 | $0.00267 |
| Sonnet 5.5 | $0.00012 | $0.00134 |
| Haiku 4.5 | $0.00006 | $0.00067 |
Grade A, and why
rls-performance 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.
What it actually says
RLS Performance Playbook
RLS 效能問題的診斷操作手冊：新增 policy join 或改 policy WHERE、新增含 pagination／filter 的 endpoint、PGRST003、pool 耗盡、特定頁面變慢。量測模板、plan 判讀、index、延遲基準在 db-schema/<variant>/query-optimization.md 與 rls-policy.md，連線池預算與 PGRST003 處置在 db-runtime/<variant>/database.md；本 skill 只串起診斷流程並補規約沒有的判讀訊號。
SOP
Phase 1 -- 收斂症狀
- READ 讀取症狀描述與
log.error：是否有PGRST003（pool 耗盡，REST 504）、哪個頁面或 endpoint 變慢、最近是否新增或修改 policy join／WHERE、是否新增含分頁的 endpoint。
Phase 2 -- 量測與判讀
- DELEGATE 在目標主機量測：慢 query 依
query-optimization.md§ 效能測量（pg_stat_statements）找出 total／mean 最高者，再依 § EXPLAIN ANALYZE 模板以目標角色（set local role，superuser 會 bypass RLS）跑EXPLAIN ANALYZE；self-hosted 連線問題依 db-runtimedatabase.md§ Connection Pool Runbook 的pg_stat_activity查詢按usename／state分組。 - THINK 讀取
rules/連線池與RLS診斷判準.md，搭配query-optimization.md§ 讀 plan 的重點，判定是 policy 寫法、缺 index、N+1 還是 pool 問題。
Phase 3 -- 修正與驗證
- WRITE 依判定修正：改 policy 寫法（
rls-policy.md§ RLS 效能）、加 index（query-optimization.md§ Index 設計原則）、N+1 改select(*, related(*))embed 或 RPC，或縮小交易批次（db-runtimedatabase.md§ Transaction 與批次寫入安全）。pool 問題照 Runbook 處置，NEVER 對 pool timeout 盲目 retry。 - DELEGATE 以相同角色重跑
EXPLAIN ANALYZE，比較修正前後與有／無 policy 的 Execution Time 與Seq Scan，依已載入規則判定是否仍超標；仍超標就回 Phase 2。
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.
- 2d ago Changed · -150 lines fb765d0f460e
- 19d ago Changed · -1 lines 25cd21e97d20
- 1mo ago Changed · -24 lines 1d17469ce7c5
- 1mo ago Changed · +1 lines e6b3c83dd9ac
- 1mo ago Changed · -2 lines a55c202f53cc
- 1mo ago Changed · +2 lines 920dcd835364
- 1mo ago First seen · 201 lines · 58 tokens per session scan A e436b8b24352
rls-performance is a skill published in the GitHub repository YuDefine/nuxt-supabase-starter (44 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 668 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
explorer
Build and modify Studio Explorer surfaces, including notebooks, chats, SQL snippets, query cells, and their shared toolbar patterns.
sql-optimizer
Analyzes SQL queries for missing indexes, N+1 patterns, suboptimal joins, and full table scans. Interprets EXPLAIN, detects anti-patterns, rewrites queries. Triggers on: "optimize this query", "slow query", "add indexes", "explain plan", "N+1 query", "why is this query slow".
nw-database-technology-selection
Database comparison catalogs, RDBMS vs NoSQL selection criteria, CAP/ACID/BASE theory, OLTP vs OLAP, and technology-specific characteristics.
sql-explain
Explains a PostgreSQL EXPLAIN ANALYZE plan and points at the slowest node. Use when the user pastes a query plan; not for rewriting schemas.
srtd-cli
This skill should be used when the user mentions "srtd", "sql templates", "migrations-templates", "live reload sql", "supabase functions", when working with files in supabase/migrations-templates/, when .buildlog.json or srtd.config.json is detected, or when writing Postgres functions/views/triggers for Supabase.
optimize-a-query
Diagnose and fix a slow Postgres query in the builders-stack — read its EXPLAIN plan, find the missing index or the ORM N+1, and confirm the fix. Use when a page or endpoint is slow, a query times out, or pgstatstatements shows a hot query. Pairs with design-a-schema for the index itself.