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/georgeguimaraes/claude-code-elixir/phoenix-thinkingnpx skills add georgeguimaraes/claude-code-elixir --skill phoenix-thinkinggit clone --depth 1 https://github.com/georgeguimaraes/claude-code-elixirWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/georgeguimaraes/claude-code-elixir/phoenix-thinking)<a href="https://agentmods.dev/skills/georgeguimaraes/claude-code-elixir/phoenix-thinking"><img src="https://agentmods.dev/badge/skills/georgeguimaraes/claude-code-elixir/phoenix-thinking.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00108 | $0.01309 |
| Opus 5 | $0.00054 | $0.00655 |
| Sonnet 5 | $0.00022 | $0.00262 |
| Haiku 4.5 | $0.00011 | $0.00131 |
Grade A, and why
phoenix-thinking 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 5d ago.
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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phoenix Thinking
Mental shifts for Phoenix applications. These insights challenge typical web framework patterns.
Where to Load Data: mount vs handle_params
Default: load data in mount/3.
def mount(_params, _session, socket) do
posts = Blog.list_posts(socket.assigns.current_scope)
{:ok, assign(socket, posts: posts)}
end
Yes, mount runs twice on initial load (HTTP dead render + WebSocket connect). So does handle_params/3. That's the LiveView lifecycle, not a bug to route around. Moving queries from mount to handle_params does not dedupe them.
Use handle_params/3 for data that changes on live navigation (push_patch / <.link patch={...}>). mount does not re-run on patches, handle_params does.
def handle_params(%{"filter" => filter}, _uri, socket) do
posts = Blog.list_posts(socket.assigns.current_scope, filter)
{:noreply, assign(socket, posts: posts, filter: filter)}
end
When the initial double-load actually matters, the real tools are:
connected?(socket)to gate work to the connected render (loses SEO / no-JS rendering)assign_async/3to load after mount returns, in a separate processassign_new/3to reuse values already set onconn.assignsby upstream Plugs (e.g.:current_user), or shared from a parent LiveView. It does not dedupe arbitrary work across the dead/connected boundary: the function still runs on connected mount.
def mount(_params, _session, socket) do
posts = if connected?(socket), do: Blog.list_posts(socket.assigns.current_scope), else: []
{:ok, assign(socket, posts: posts)}
end
Scopes: Security-First Pattern (Phoenix 1.8+)
Scopes address OWASP #1 vulnerability: Broken Access Control. Authorization context is threaded automatically—no more forgetting to scope queries.
def list_posts(%Scope{user: user}) do
Post |> where(user_id: ^user.id) |> Repo.all()
end
PubSub Topics Must Be Scoped
def subscribe(%Scope{organization: org}) do
Phoenix.PubSub.subscribe(@pubsub, "posts:org:#{org.id}")
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.
- 5d ago First seen · 141 lines · 108 tokens per session scan A 3d36a80be00b
phoenix-thinking is a skill published in the GitHub repository georgeguimaraes/claude-code-elixir (168 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 108 tokens to every session and 1,309 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
elixir
Use when writing or refactoring Elixir/OTP on the BEAM — GenServers, supervision trees and restart strategies, pattern matching, mix projects and releases — or when processes misbehave (restart loops, mailbox growth, call timeouts). NOT a Phoenix web app, LiveView, Ecto or channels (that is phoenix).
pixir-delegate
Use Pixir as a headless subagent runtime from Claude Code or any harness with skill ! preprocessing (Codex roots and other no-hydration hosts use pixir-delegate-codex instead) — one-shot workers (pixir --json), parallel fan-out to N children (pixir delegate --spec), resumable steering (pixir resume), evidence…
pixir-delegate-codex
Use when a Codex CLI/Desktop root should fan out subagents, delegate to Pixir workers, run parallel workers, or manage a resident delegation daemon via Pixir Delegate; covers Codex preflight, AGENTS.md, approvals/sandbox, dry-run, daemon start/status/attach/cancel, closure evidence, and audited single-run execution…
pixir-diagnostics
Diagnose Pixir and T3 Code Pixir incidents from local canonical evidence. Use when a Pixir run, ACP/T3 thread, subagent/workflow, provider replay, or daily-driver dogfood session appears stuck, inconsistent, missing tool output, or hard to classify.
phoenix
Use when building an Elixir web app with Phoenix — contexts, Ecto schemas, changesets and migrations, LiveView, channels and PubSub, the generators, and the boundary between domain logic and the web layer. Covers the classic LiveView over-rendering and Ecto N+1 traps. NOT pure OTP work with no web or Ecto layer …
readonly-review
Run a no-network read-only review practice with two explorer steps and one synthesis step.