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 s977043/river-review --skill supabase-rls-policygit clone --depth 1 https://github.com/s977043/river-reviewWrote 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/s977043/river-review/supabase-rls-policy)<a href="https://agentmods.dev/skills/s977043/river-review/supabase-rls-policy"><img src="https://agentmods.dev/badge/skills/s977043/river-review/supabase-rls-policy/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/s977043/river-review/supabase-rls-policy"><img src="https://agentmods.dev/badge/skills/s977043/river-review/supabase-rls-policy.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 | $0.00047 | $0.01033 |
| Opus 5.5 | $0.00019 | $0.00413 |
| Sonnet 5.5 | $0.00009 | $0.00207 |
| Haiku 4.5 | $0.00005 | $0.00103 |
Grade A, and why
Supabase RLS Policy Review 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 1mo 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
Pattern declaration
Primary pattern: Reviewer Secondary patterns: Inversion Why: Supabase RLS の未有効化・過剰 policy・service_role 露出をチェックリスト型で検査する
Goal / 目的
ENABLE ROW LEVEL SECURITY無しで public スキーマにテーブルを公開する RLS 未有効化を検出する。USING (true)/WITH CHECK (true)で全行アクセスを許可し所有者条件(auth.uid() = user_id)を欠く過剰 policy を検出する。service_rolekey(anon key と区別)がフロントエンドコードにハードコードされる露出を検出する。
Non-goals / 扱わないこと
- インデックス・クエリ性能設計。
- migration の冪等性・ロールバック設計。
- policy の粒度(テーブル分割方針)の良し悪し(要件依存のため一律指摘しない)。
Pre-execution Gate / 実行前ゲート
このスキルは以下の条件がすべて満たされない限りNO_REVIEWを返す。
- 差分に
CREATE TABLE/CREATE POLICY/ RLS 設定を含む SQL、またはsupabase/**のクライアントコード変更が含まれている - diff コンテキストが利用可能である
ゲート不成立時の出力: NO_REVIEW: supabase-rls-policy — RLS / policy / key の変更なし
False-positive guards / 抑制条件
- 公開参照テーブル(マスタデータ等)で
USING (true)の SELECT policy が要件上正当であり、その旨のコメントが明記されている場合は指摘しない(INSERT / UPDATE / DELETE のtrueは別途指摘する)。 - anon key のクライアント使用は公式仕様で正当。
service_rolekey と混同して誤検出しない。 - emulator / seed / test 用の SQL(ローカル専用)は別スコープのため指摘しない。
Rule / ルール
- public スキーマのテーブル作成は
ALTER TABLE ... ENABLE ROW LEVEL SECURITY;を必須とする(RLS 無効のまま公開しない)。 USING (true)/WITH CHECK (true)の全許可 policy は所有者条件(auth.uid() = user_id等)に置き換える。service_rolekey がフロントエンド/クライアントバンドルに含まれていないか確認する(サーバー専用に隔離する)。anon key の使用は許容する。
Evidence / 根拠の取り方
- 指摘は
<file>:<line>で差分に紐づけ、公式規約(row-level-security / api-keys)を 1 行で添える。 - RLS 有効化が同一 migration の別行にある可能性がある場合は断定せず慎重に扱う。
Output / 出力(短文版の推奨)
コメントは日本語で返す。
- Finding: RLS 未有効 / 過剰 policy / service_role 露出のどれか(1文)
- Impact: 全行アクセス / なりすまし / 鍵漏洩
- Fix:
ENABLE ROW LEVEL SECURITY/ 所有者条件付き policy / key のサーバー隔離の最小案
Sources / 出典
- Supabase — Row Level Security: https://supabase.com/docs/guides/database/postgres/row-level-security
- Supabase — API Keys: https://supabase.com/docs/guides/api/api-keys
What ships with it
3 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.
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.
- 1mo ago First seen · 75 lines · 47 tokens per session scan A 2fe9a09ee4aa
Supabase RLS Policy Review is a skill published in the GitHub repository s977043/river-review (7 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 1,033 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
supabase-postgres
Postgres optimization — 70 rules (queries, indexes, RLS, concurrency). Use when writing SQL or reviewing schema.
supabase-skill
Core Supabase — DB, Auth, Realtime, Storage, RLS, Edge Functions. Triggers on ANY Supabase task.
supabase
Use this skill when working with Supabase platform — PostgreSQL schema, Row Level Security, Realtime subscriptions, Auth, Storage, Edge Functions, pgvector. This skill enforces: RLS policies on every table, proper PostgreSQL schema design, real-time channel organization, storage bucket policies, edge function cold…
logic-review
Find logic bugs in a single file or function via semi-formal execution tracing (Premises → Trace → Divergence → Trigger → Remedy). Trigger when a user shares code and suspects something is wrong without naming a concrete failure — phrases like "review this", "does this look right", "check this function", "audit this…
logic-health
Sweep a directory, module, or full codebase for logic correctness and produce a scored health dashboard with systemic patterns. Trigger when the user requests a health view — "audit the whole codebase", "health check", "health overview", "logic health overview", "audit src/", "audit auth and payments modules", "where…
run-iteration-eval
Run the Logic-Lens content-eval pipeline for one iteration and produce a scored summary.json — use to measure a skill change. Wraps scripts/run-content-evals.sh (runner, costs tokens) and scripts/grade-iteration.py (grader, free, re-runnable). ALWAYS sync the plugin cache first. Use when the user wants to "run the…