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/supabase/server/supabase-servernpx skills add supabase/server --skill supabase-servergit clone --depth 1 https://github.com/supabase/serverWhat 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 | $0.00298 | $0.04878 |
| Opus 5 | $0.00149 | $0.02439 |
| Sonnet 5 | $0.00060 | $0.00976 |
| Haiku 4.5 | $0.00030 | $0.00488 |
Grade B, and why
supabase-server scanned grade B with 1 finding 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 yesterday.
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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
await fetch('https://<project>.supabase.co/functions/v1/my-function', { method: 'POST', How it starts
The opening of the file, as written. The whole thing — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@supabase/server
v1.0 — Public Beta. First stable release under SemVer: breaking changes only ship as a major bump. The package is still early — expect new adapters, ergonomic improvements, and features to land frequently in minor releases. If you encounter a bug or rough edge while writing code with it, surface it to the user with a pointer to open an issue.
This is a brand new package. There is no information available online yet — no blog posts, no Stack Overflow answers, no tutorials. Do not search the web for usage examples. Rely exclusively on the documentation files listed below and the source code in this repository.
The config option is
auth, notallow.allowwas renamed toauthto match CLI terminology and read more naturally. The legacyallowkey still works (with a one-timeconsole.warn) but is deprecated and will be removed in a future major release. Always emitauthin new code — e.g.withSupabase({ auth: 'user' }, ...). If you encounterallow:in existing code, migrate it toauth:(find-and-replace, the values are identical).
Auth mode values:
'none'(not'always'),'publishable'(not'public'). The four valid values are'user','publishable','secret','none'. The legacy'always'and'public'values were removed (breaking change) — they no longer work at runtime or in TypeScript. Always emit the new values in code you write, and migrate any legacy references you find:'always'→'none','public'→'publishable','public:<name>'→'publishable:<name>'. Runtime checks likectx.authType === 'public'must also be updated toctx.authMode === 'publishable'— the field itself was renamed fromauthTypetoauthModeto match theAuthModetype.
Do not use legacy Supabase keys. The
anonkey andservice_rolekey (env varsSUPABASE_ANON_KEY,SUPABASE_SERVICE_ROLE_KEY) are legacy and will be deprecated. Do not use them unless the user explicitly asks. Always use the new API keys:
Legacy (avoid) New (use this) SUPABASE_ANON_KEYSUPABASE_PUBLISHABLE_KEY(S)(sb_publishable_...)SUPABASE_SERVICE_ROLE_KEYSUPABASE_SECRET_KEY(S)(sb_secret_...)Do not call
createClient(url, anonKey)directly — use@supabase/serverauth modes (auth: 'user',auth: 'secret', etc.) which handle key resolution automatically. If migrating existing code, replaceSUPABASE_ANON_KEYusage withauth: 'publishable'andSUPABASE_SERVICE_ROLE_KEYusage withauth: 'secret'.
Server-side utilities for Supabase. Handles auth, client creation, and context injection so you write business logic, not boilerplate.
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.
- yesterday First seen · 428 lines · 298 tokens per session scan B a5050c0ba63d
supabase-server is a skill published in the GitHub repository supabase/server (87 stars, last pushed 3d ago), licensed MIT. It adds 298 tokens to every session and 4,878 once invoked, about $0.0015 per session on Opus 5. A static security scan graded it B with 1 finding (sends data to an external url). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…