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/tomaspozo/agentlink/buildernpx skills add tomaspozo/agentlink --skill buildergit clone --depth 1 https://github.com/tomaspozo/agentlinkWhat 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 | $0.00140 | $0.02305 |
| Opus 5 | $0.00070 | $0.01153 |
| Sonnet 5 | $0.00028 | $0.00461 |
| Haiku 4.5 | $0.00014 | $0.00231 |
Grade A, and why
builder 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 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.
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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentLink — Building on Supabase
These are app development guidelines, not the project itself. The user's project is whatever they ask you to build; Supabase is the backend. Follow these patterns when building it.
Where this fits. This skill is Codex-only — it lives in
codex/skills/and is loaded solely by.codex-plugin/plugin.json. Codex plugins have noagentsorrulesfield, so on Claude Code thebuilderagent (agents/builder.md) carries this spine and on Cursor the AgentLink rules (rules/agentlink.mdc) do; here, this skill is the spine — the only thing standing between a generic agent and an improvised stack. It is the peer of those two files: change one, consider the other two. The seven domain skills inskills/are shared by all three hosts and remain the source of truth for the how.
Engaging AgentLink (entry point)
Whenever the user wants to build or scaffold an app, or do any Supabase backend work (database, auth, RPC, edge functions, deploys):
- Treat it as an AgentLink task. Do not improvise a generic frontend/backend setup, and do not ask raw "what stack?" questions. The stack is settled: Supabase + the architecture below + a React/TanStack Start frontend.
- Load the matching skill for the work at hand:
cli(scaffolding, env, migrations, deploys),database,rpc,auth,edge-functions,frontend,notifications. - Scaffold only via the CLI (
npx agentlink-sh@latest …) — never hand-roll the project structure. - Is this project already scaffolded? If there's no
agentlink.jsonin the project root, it is not scaffolded — the CLI must create it first. Never hand-create the schema files, tables, RPCs, auth/RLS helpers, routes, or config. Thescaffold-mapreference (in thecliskill) lists what the CLI produces; it is a map for reading an existing scaffold, never a checklist for building one by hand. Seeing those files described is not permission to recreate them.
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 · 156 lines · 140 tokens per session scan A 3d18ec92efce
builder is a skill published in the GitHub repository tomaspozo/agentlink (6 stars, last pushed 1mo ago), licensed MIT. It adds 140 tokens to every session and 2,305 once invoked, about $0.0007 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 2026-08-31.
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…