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 tushaarmehtaa/tushar-skills --skill supabasegit clone --depth 1 https://github.com/tushaarmehtaa/tushar-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/tushaarmehtaa/tushar-skills/supabase)<a href="https://agentmods.dev/skills/tushaarmehtaa/tushar-skills/supabase"><img src="https://agentmods.dev/badge/skills/tushaarmehtaa/tushar-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.
<a href="https://agentmods.dev/skills/tushaarmehtaa/tushar-skills/supabase"><img src="https://agentmods.dev/badge/skills/tushaarmehtaa/tushar-skills/supabase.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 | $0.00043 | $0.00637 |
| Opus 5 | $0.00022 | $0.00318 |
| Sonnet 5 | $0.00009 | $0.00127 |
| Haiku 4.5 | $0.00004 | $0.00064 |
Grade A, and why
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 12d 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Supabase
Build a migration-backed, typed Supabase integration with explicit authorization boundaries.
Workflow
- Inspect
supabase/, migrations, generated types, installed Supabase packages/versions, framework/runtime, environment-variable names without printing values, auth/session flow, schemas exposed through the Data API, and existing grants/RLS. - Infer table ownership and tenant relationships from the domain model. Ask only when ownership, collaboration, deletion, retention, or external-auth behavior is ambiguous. Do not add
user_idor four CRUD policies to every table mechanically. - Design keys, foreign keys, constraints, indexes, timestamps, lifecycle/deletion behavior, and server-generated ownership defaults appropriate to each table. Use external provider subject IDs as text unless a local identity mapping is intentionally modeled.
- Create named migrations. Use
supabase migration newor a revieweddb difffor local changes, verify with a local reset/test database, inspectdb push --dry-run, and usedb pushonly when remote deployment is explicitly in scope.migration upis not a substitute for remote deployment. - Secure every exposed object with both Postgres grants and RLS. Scope policies to roles, use indexed predicates, add
with checkfor inserts/updates, review views/functions separately, and set a safesearch_pathonsecurity definerfunctions. - Match auth strategy:
- Supabase Auth: use
auth.uid()/auth.jwt()and current SSR session guidance. - Clerk or another supported third-party provider: configure the native integration, pass the provider token through the client, and use the actual JWT
sub/claims. Do not assume an RLS expression alone configures token verification. - Server administration: use a dedicated server-only client with explicit authorization; never expose secret/service credentials.
- Supabase Auth: use
- For current
@supabase/ssr, create a client per request, use the supported cookiegetAll/setAlladapter, await async framework cookie APIs, and add the required proxy/middleware refresh flow. Do not use legacy single-cookie adapters. - Generate TypeScript types after applying migrations to the target used for generation, then run type checks and update typed queries. Avoid
anyand handle{ data, error }explicitly.
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.
- 12d ago First seen · 32 lines · 43 tokens per session scan A 1814d92358af
supabase is a skill published in the GitHub repository tushaarmehtaa/tushar-skills (11 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 637 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
convex-explain-app
Explain an existing Convex app — data model + relationships, public vs internal functions, auth/ownership model, components, a request→data flow — read from the schema and function surface. Read-only.
platform-custom-field-generate
Use this skill when users need to create, generate, or validate Salesforce Custom Field metadata. Trigger when users mention custom fields, field types, Roll-up Summary fields, Master-Detail relationships, Lookup relationships, formula fields, picklists, dependent (controlling) picklists, referencing a value set from…
field-service-sobject-create-configure
Headless 360 REST API deployment step for creating sObject records. Handles describe-based field discovery, required-field derivation, entity-relationship ordering, and composite graph transactions. Use this skill when a designer skill (or a user directly) needs to create sObject records after design confirmation…
durable-objects
Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.
nornicdb-grpc
Drive NornicDB over gRPC — the Qdrant-compatible surface (Collections, Points, Snapshots) plus the additive NornicSearch service. Use when ingesting via Qdrant SDKs, migrating from Qdrant, or running hybrid text+vector search from a non-Bolt client. Covers connection, RPC catalog, collection→database mapping…