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/structured-datanpx skills add fullstack-phoenix/saas_kit --skill structured-datagit 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 | $0.00032 | $0.01674 |
| Opus 5 | $0.00016 | $0.00837 |
| Sonnet 5 | $0.00006 | $0.00335 |
| Haiku 4.5 | $0.00003 | $0.00167 |
Grade A, and why
structured-data 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structured Data
Use this skill when an AI feature should return validated Elixir data instead of freeform text.
Goal
- Keep provider config in one place.
- Keep agent modules easy to find under
MyApp.Agents.*. - Return typed, validated structs through
InstructorLite. - Keep tests isolated with Mimic.
Install
def deps do
[
{:instructor_lite, "~> 1.2.0"}
]
end
Root Agents Module
Create one shared module for API keys and model names:
defmodule MyApp.Agents do
@moduledoc """
Central configuration for AI agents.
Import this module in agent implementations to access API keys and models.
"""
def anthropic_key, do: Application.get_env(:my_app, :anthropic)[:api_key]
def openai_key, do: Application.get_env(:my_app, :openai)[:api_key]
def gemini_key, do: Application.get_env(:my_app, :gemini)[:api_key]
def model(:haiku), do: "claude-haiku-4-5"
def model(:sonnet), do: "claude-sonnet-4-5"
def model(:opus), do: "claude-opus-4-5"
def model(:gpt_5_nano), do: "gpt-5-nano"
def model(:gpt_5_mini), do: "gpt-5-mini"
def model(:gpt_5), do: "gpt-5.2"
def model(:gpt_4_1_mini), do: "gpt-4.1-mini"
def model(:gemini_flash), do: "gemini-3-flash-preview"
def model(:gemini_pro), do: "gemini-3-pro-preview"
end
Credential Placement
Do not put provider credentials in shared config/config.exs.
Keep local credentials in config/dev.exs:
config :my_app, :anthropic, api_key: System.get_env("ANTHROPIC_API_KEY")
config :my_app, :openai, api_key: System.get_env("OPENAI_API_KEY")
config :my_app, :gemini, api_key: System.get_env("GEMINI_API_KEY")
Module Naming and Location
- Put agents in
lib/my_app/agents/. - Use
MyApp.Agents.TopicSomeActionstyle names. - Prefer names that describe one business task, such as
MyApp.Agents.PostsWritePost.
Example:
lib/my_app/agents/posts_write_post.ex
defmodule MyApp.Agents.PostsWritePost do
end
Agent Pattern
Use one task-specific module with a nested Response schema:
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 · 239 lines · 32 tokens per session scan A f89baaafc6ae
structured-data is a skill published in the GitHub repository fullstack-phoenix/saas_kit (2 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 1,674 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…