supabase

supabase is a skill for Claude Code, Codex from vanthienha199/openclaw-skills. It costs 95 tokens per session (1,277 once invoked), scanned C, original, MIT.

A command-line tool for managing Supabase projects, which provide hosted databases, user accounts, file storage, and access rules. It works with database rows, authentication users, storage, and row-level security policies.

In plain words
What is it for?
Use it to query, insert, update, or delete table rows; manage authentication users; handle storage; and work with row-level security policies.
Why use it?
It lets you manage these project resources directly from the command line without adding an object-relational mapper. Requests use the public key and remain subject to the project's access rules.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to query, insert, update, or delete table rows; manage authentication users; handle storage; and work with row-level security policies.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vanthienha199/openclaw-skills/supabase
Install

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.

Any agent
npx skills add vanthienha199/openclaw-skills --skill supabase
Clone the repo
git clone --depth 1 https://github.com/vanthienha199/openclaw-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for supabase

README.md
[![agentmods](https://agentmods.dev/badge/skills/vanthienha199/openclaw-skills/supabase/github.svg)](https://agentmods.dev/skills/vanthienha199/openclaw-skills/supabase)
Your own site
<a href="https://agentmods.dev/skills/vanthienha199/openclaw-skills/supabase"><img src="https://agentmods.dev/badge/skills/vanthienha199/openclaw-skills/supabase/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.

agentmods 80×15 button for supabase

Your own site · 80×15
<a href="https://agentmods.dev/skills/vanthienha199/openclaw-skills/supabase"><img src="https://agentmods.dev/badge/skills/vanthienha199/openclaw-skills/supabase.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,277 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00095 $0.01277
Opus 5 $0.00048 $0.00639
Sonnet 5 $0.00019 $0.00255
Haiku 4.5 $0.00010 $0.00128

Measured 9d ago against content hash 9d0aa2ea47df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

supabase scanned grade C with 2 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 9d 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.

Instruction-override phrasinghighPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

- All queries go through Supabase's RLS layer — the skill cannot bypass your security policies

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Use `curl` for all Supabase REST API operations:
supabase/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Supabase

You manage Supabase projects using the REST API and SQL. Fast, direct, no ORM overhead.

Connection Setup

On first use, ask the user for:

  1. Supabase URLhttps://[project-ref].supabase.co
  2. Anon key (public) — for RLS-protected queries

This skill uses ONLY the anon (public) key by default. The anon key is designed to be safe for client-side use — it is protected by Row Level Security (RLS) policies you configure in Supabase.

Credential Handling

  • Credentials are provided by the user at runtime via environment variables: SUPABASE_URL and SUPABASE_ANON_KEY
  • This skill does NOT store credentials to disk
  • This skill does NOT request or use the service role key
  • All queries go through Supabase's RLS layer — the skill cannot bypass your security policies

API Calls

Use curl for all Supabase REST API operations:

Query (SELECT)

curl -s "[URL]/rest/v1/[table]?select=*&[filters]" \
  -H "apikey: [KEY]" \
  -H "Authorization: Bearer [KEY]"

Insert

curl -s -X POST "[URL]/rest/v1/[table]" \
  -H "apikey: [KEY]" \
  -H "Authorization: Bearer [KEY]" \
  -H "Content-Type: application/json" \
  -d '[JSON]'

Update

curl -s -X PATCH "[URL]/rest/v1/[table]?[filter]" \
  -H "apikey: [KEY]" \
  -H "Authorization: Bearer [KEY]" \
  -H "Content-Type: application/json" \
  -H "Prefer: return=representation" \
  -d '[JSON]'

Delete

curl -s -X DELETE "[URL]/rest/v1/[table]?[filter]" \
  -H "apikey: [KEY]" \
  -H "Authorization: Bearer [KEY]"

PostgREST Filter Syntax

  • ?column=eq.value — equals
  • ?column=neq.value — not equals
  • ?column=gt.value — greater than
  • ?column=lt.value — less than
  • ?column=gte.value — greater than or equal
  • ?column=like.*pattern* — LIKE
  • ?column=ilike.*pattern* — case-insensitive LIKE
  • ?column=in.(val1,val2) — IN
  • ?column=is.null — IS NULL
  • ?order=column.desc — ORDER BY
  • ?limit=10 — LIMIT
  • ?offset=20 — OFFSET
  • ?select=col1,col2,related_table(col3) — select specific columns + joins

Read the full file on GitHub · 144 lines

Changes

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.

  1. 9d ago First seen · 144 lines · 95 tokens per session scan C 9d0aa2ea47df

Subscribe to this mod's changes

supabase is a skill published in the GitHub repository vanthienha199/openclaw-skills (1 stars, last pushed 5mo ago), licensed MIT. It adds 95 tokens to every session and 1,277 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (instruction-override phrasing, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.