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/using-saas-kitnpx skills add fullstack-phoenix/saas_kit --skill using-saas-kitgit 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 | $0.00039 | $0.01017 |
| Opus 5 | $0.00019 | $0.00508 |
| Sonnet 5 | $0.00008 | $0.00203 |
| Haiku 4.5 | $0.00004 | $0.00102 |
Grade A, and why
using-saas-kit 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using SaaS Kit
SaaS Kit ships production-ready features (auth, teams, payments, oauth, …) into
an existing Phoenix app as a set of mix saaskit.* tasks. You generate a normal
Phoenix app, point it at a boilerplate token, then install features one at a
time. Each feature is a catalog entry under the kit; this skill is the entry
point — read it first, then open the matching feature skill.
Prerequisites
- Elixir/Phoenix installed (
mix phx.newavailable). - A boilerplate token from https://fullstackphoenix.com/ (the boilerplate page).
1. Create your Phoenix app
Run this outside an existing Phoenix project:
mix phx.new my_saas
2. Add SaaSKit to mix.exs
def deps do
[
{:saas_kit, "~> 3.0"}
]
end
3. Configure the boilerplate token
Add to config/dev.exs:
config :saas_kit, boilerplate_token: "<token>"
Without this, mix saaskit.setup raises and points you at the boilerplate page.
4. Fetch deps and run setup
mix deps.get
mix saaskit.setup
saaskit.setup installs the initial SaaS Kit feature and creates local project
state. It also offers to install agent guidance (--agent-skills to accept
without prompting, --no-agent-skills to skip).
5. Install features
Install a whole plan, or features individually:
mix saaskit.plan.install <token> # install a saved plan's features
mix saaskit.feature.install authentication
Mix tasks
After setup, these tasks drive everything. All support --json where shown, so
an agent can probe state machine-readably.
mix saaskit.status
Reports current state: config status, app name, installed/pending feature counts, and the suggested next command. Use it as the first probe in any session.
mix saaskit.status
mix saaskit.status --json
mix saaskit.help
Getting-started info and the full task catalog. Runs fully offline; reports
whether boilerplate_token is set.
mix saaskit.help
mix saaskit.help --json
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 · 151 lines · 39 tokens per session scan A 8e3c6ca1e948
using-saas-kit is a skill published in the GitHub repository fullstack-phoenix/saas_kit (2 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 1,017 once invoked, about $0.0002 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…