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/clinpx skills add tomaspozo/agentlink --skill cligit 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 | $0.00112 | $0.10359 |
| Opus 5 | $0.00056 | $0.05180 |
| Sonnet 5 | $0.00022 | $0.02072 |
| Haiku 4.5 | $0.00011 | $0.01036 |
Grade C, and why
cli 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 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
AgentLink does NOT install its own tooling, and it does NOT require an AI coding agent (Claude Code or Cursor) to be on PATH in order to scaffold — it writes the project files and the editor config regardless, then you o Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
AgentLink does NOT install its own tooling, and it does NOT require an AI coding agent (Claude Code or Cursor) to be on PATH in order to scaffold — it writes the project files and the editor config regardless, then you o How it starts
The opening of the file, as written. The whole thing — 540 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI
The agentlink-sh CLI scaffolds new Supabase projects and updates existing ones. It handles infrastructure setup, template files, database configuration, and migration generation.
Running the CLI (since 1.4): prefer the project-local install. Projects scaffolded with 1.4+ pin
agentlink-shas a devDependency, so the project carries its own CLI version — reproducible, and it never auto-jumps across a breaking major. Note the names differ: the package isagentlink-sh, the installed binary isagentlink(no-sh). For in-project commands (check,db apply,db migrate,env deploy,--force-update, …):
- Use
pnpm exec agentlink <cmd>when the dep is present (check withpnpm exec agentlink --version, or look foragentlink-shinpackage.json).- If it's missing (a pre-1.4 project): add it with
pnpm add -D agentlink-sh, or run--force-updateonce (it backfills the declaration), thenpnpm install.- Don't use bare
npx agentlink— with no local install it resolves a different npm package, not ours. Usepnpm exec agentlink(local) ornpx agentlink-sh@latest(one-shot).- Only
createuses@latest— a brand-new project has no local CLI yet:npx agentlink-sh@latest <name>.The command docs below still write
npx agentlink-sh@latestfor brevity; when a local install exists,pnpm exec agentlinkis the equivalent and preferred form.
Workflow playbook: see
references/workflows.mdfor common user scenarios — "start a new project from zero," "add a prod env," "deploy to prod," "recover from a failed deploy," etc. Each entry lists what questions to ask the user and which commands to run.
Prerequisites
AgentLink does NOT install its own tooling, and it does NOT require an AI coding agent (Claude Code or Cursor) to be on PATH in order to scaffold — it writes the project files and the editor config regardless, then you open the project in whichever agent you chose. It validates the tooling it needs and points users at the setup script at https://agentlink.sh/start if anything is missing; it never tries to curl | bash anything itself. This is intentional — mixing tooling installation into scaffold meant every platform-specific install failure surfaced mid-scaffold with no context.
What ships with it
8 files 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.
- yesterday First seen · 540 lines · 112 tokens per session scan C 8c04f8d10461
cli is a skill published in the GitHub repository tomaspozo/agentlink (6 stars, last pushed 1mo ago), licensed MIT. It adds 112 tokens to every session and 10,359 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). 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…