Borrowing it
Nothing to install: this file belongs to alnutile/supabase-as-a-service. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alnutile/supabase-as-a-service/main/.agents/skills/port-feature-to-template/SKILL.mdgit clone --depth 1 https://github.com/alnutile/supabase-as-a-serviceWrote 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/alnutile/supabase-as-a-service/port-feature-to-template)<a href="https://agentmods.dev/skills/alnutile/supabase-as-a-service/port-feature-to-template"><img src="https://agentmods.dev/badge/skills/alnutile/supabase-as-a-service/port-feature-to-template/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/alnutile/supabase-as-a-service/port-feature-to-template"><img src="https://agentmods.dev/badge/skills/alnutile/supabase-as-a-service/port-feature-to-template.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 | $0.00204 | $0.01557 |
| Opus 5.5 | $0.00082 | $0.00623 |
| Sonnet 5.5 | $0.00041 | $0.00311 |
| Haiku 4.5 | $0.00020 | $0.00156 |
Grade A, and why
port-feature-to-template 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 23d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Port a feature from this app into the vibe-starter template
The goal each time: take one feature out of this production app and drop it into the
supabase-vibe-starter template as a new .Codex/skills/<feature>/ skill the
template's AI can build out per-project. You are handing over concept + security
model + adapted build-spec + verbatim source — not wiring it live into the app
(unless the user asks). The template stays clean; nothing here is committed unless
the user says so.
The target
- Path:
/Users/alfrednutile/Apps/Videos/supabse-vibecoding-starter(note the typo'dsupabse— that is the real folder name). - What it is: a deliberately minimal React + Vite + TS + Supabase starter — a
"stack smoke-test" (auth +
documentstable + RLS + realtime + private Storage). - What it does NOT have (so you must adapt, not copy): no
react-router, no tailwind (plain CSS insrc/index.css), noAuthContext(App switches onsession), no admin/roles, no Vault, noactivity_log, no edge functions yet. - Read
references/target-conventions.mdfor the exact conventions + the source→target adaptation map before writing any code.
The method (what worked, do it again)
-
Map the feature's full surface in THIS repo. A feature is rarely one file. Grep for it and enumerate: the UI page(s) (
src/pages/*), pure logic + tests (src/lib/*.ts+*.test.ts), the edge function(s) (supabase/functions/*), migration(s) (supabase/migrations/*), any GitHub workflow, and the wiring (supabase/config.toml,src/App.tsxroute,src/lib/nav.ts). The feature is often documented inAGENTS.md— read that section first. -
Capture the concept + the security model. The most valuable part to hand over is why it's built this way — the trust boundary, what's owner-only vs workspace vs admin, what's attacker-reachable, what fails open vs closed. Write this as prose, not code.
-
List the dependencies and how they map. For each thing the feature leans on (Vault,
profiles.is_admin,activity_log, a storage bucket, realtime, a model profile, another builtin), decide: reuse an equivalent in the target, substitute a minimal version, or drop it as optional. Record every decision inORIGIN.md.
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.
- 23d ago First seen · 106 lines · 204 tokens per session scan A f73d2847df29
port-feature-to-template is a skill published in the GitHub repository alnutile/supabase-as-a-service (5 stars, last pushed 2d ago), licensed MIT. It adds 204 tokens to every session and 1,557 once invoked, about $0.0008 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 2026-10-14.
port-feature-to-template compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| port-feature-to-templatealnutile/supabase-as-a-service | Skill | 5 | 2d ago | MIT | A | 204 | Claude Code, Codex |
| create-prprisma/orm | Skill | 48k | yesterday | Apache-2.0 | A | 48 | Claude Code, Codex |
| schema-explorationlangchain-ai/deepagents | Skill | 31k | yesterday | MIT | A | 57 | Claude Code, Codex |
| atlas-mssqlariga/atlas | Skill | 8.8k | yesterday | Apache-2.0 | A | 163 | Claude Code |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 115 | Claude Code, Codex |
| nornicdb-cypher-queriesorneryd/NornicDB | Skill | 923 | yesterday | MIT | A | 79 | Claude Code, Codex |
| volcengine-rds-postgresqlbytedance/agentkit-samples | Skill | 484 | today | Apache-2.0 | A | 63 | Claude Code, Codex |