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/fullstack-phoenix/saas_kit/ecto-multinpx skills add fullstack-phoenix/saas_kit --skill ecto-multigit clone --depth 1 https://github.com/fullstack-phoenix/saas_kitWhat 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 | $0.00025 | $0.03269 |
| Opus 5 | $0.00013 | $0.01635 |
| Sonnet 5 | $0.00005 | $0.00654 |
| Haiku 4.5 | $0.00003 | $0.00327 |
Grade A, and why
ecto-multi 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 — 498 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ecto Transactions (Repo.transact)
Use Repo.transact for atomic multi-step database operations. Valified has moved away from Ecto.Multi/Valified.Sequence in favor of the cleaner Repo.transact API.
⚠️ PROJECT CONVENTION: Use Repo.transact
IMPORTANT: In Valified, use Repo.transact for multi-step transactions instead of Ecto.Multi or Valified.Sequence.
Benefits of Repo.transact:
- Simpler API: Just a function, no complex builders
- Standard Elixir: Works naturally with
with/1 - Clearer control flow: Read top-to-bottom like normal code
- Automatic rollback: On exceptions or
{:error, _}returns
Why Use Transactions?
Multi-step operations that must all succeed or all fail:
- Creating a user with account and permissions
- Processing a payment with multiple updates
- Complex workflows with multiple database operations
- Operations that need consistency guarantees
Benefits:
- Atomic: All operations succeed or all rollback
- Simple: Just wrap operations in
Repo.transact - Safe: No partial states in the database
- Familiar: Standard Elixir patterns
Basic Transaction Pattern
def create_user_with_account(user_attrs, account_attrs) do
Repo.transact(fn ->
with {:ok, user} <- Repo.insert(User.changeset(%User{}, user_attrs)),
{:ok, account} <- Repo.insert(Account.changeset(%Account{user_id: user.id}, account_attrs)) do
{:ok, %{user: user, account: account}}
end
end)
end
Returns:
{:ok, %{user: user, account: account}}if all operations succeed{:error, changeset}if any operation fails- Transaction automatically rolls back on error
Transaction Patterns
1. Simple Transaction (Arity 0)
Just wrap operations, uses default Repo:
def create_company_with_admin(company_attrs, admin_attrs) do
Repo.transact(fn ->
with {:ok, company} <- Repo.insert(Company.changeset(%Company{}, company_attrs)),
{:ok, admin} <- Repo.insert(User.changeset(%User{company_id: company.id}, admin_attrs)) do
{:ok, company}
end
end)
end
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 · 498 lines · 25 tokens per session scan A 2b04b774dc33
ecto-multi is a skill published in the GitHub repository fullstack-phoenix/saas_kit (2 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 3,269 once invoked, about $0.0001 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…