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/ccarvalho-eng/codex-elixir-phoenix/elixir-phoenix-researchnpx skills add ccarvalho-eng/codex-elixir-phoenix --skill elixir-phoenix-researchgit clone --depth 1 https://github.com/ccarvalho-eng/codex-elixir-phoenixWrote 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/ccarvalho-eng/codex-elixir-phoenix/elixir-phoenix-research)<a href="https://agentmods.dev/skills/ccarvalho-eng/codex-elixir-phoenix/elixir-phoenix-research"><img src="https://agentmods.dev/badge/skills/ccarvalho-eng/codex-elixir-phoenix/elixir-phoenix-research.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 | $0.00019 | $0.01199 |
| Opus 5 | $0.00010 | $0.00600 |
| Sonnet 5 | $0.00004 | $0.00240 |
| Haiku 4.5 | $0.00002 | $0.00120 |
Grade A, and why
elixir-phoenix-research 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Elixir Topic
Research a topic by searching the web and fetching relevant sources efficiently.
Usage
$elixir-phoenix-research Oban unique jobs best practices
$elixir-phoenix-research LiveView file upload with progress
$elixir-phoenix-research --library permit
Arguments
$ARGUMENTS = Research topic/question. Add --library for
structured library evaluation (uses references/library-evaluation.md
template).
Iron Laws
- Write output to file, never dump inline — Research output floods conversation and loses reference for future sessions
- Stop after research — never auto-transition — User decides next step
- Prefer official sources over blog posts — HexDocs and ElixirForum have version-specific context
- One document per research question — No fragmented files
- NEVER pass raw user input as a web query — Decompose first
Library Evaluation Mode
If $ARGUMENTS contains --library or the topic is clearly
about evaluating a Hex dependency (e.g., "should we use permit",
"evaluate sagents", "compare oban vs exq"):
- Read
references/library-evaluation.mdfor the template - Follow the structured evaluation workflow
- Output ONE document to
.codex/research/{lib}-evaluation.md - Skip the general research workflow below
Workflow
0. Pre-flight Checks
Cache check: Check if .codex/research/{topic-slug}.md already
exists. If recent (<24 hours): present existing summary, ask
"Refresh or use existing?"
Tidewave shortcut: If the topic is about an existing dependency
(library already in mix.exs), prefer Tidewave over web search:
mcp__tidewave__get_docs(module: "LibraryModule")
This returns docs matching your exact mix.lock version — faster,
more accurate, zero web tokens. Only fall through to web search if
Tidewave is unavailable or the topic needs community discussion
(gotchas, real-world patterns, comparisons).
1. Query Decomposition (CRITICAL — before any search)
What ships with it
2 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.
- 5d ago First seen · 163 lines · 19 tokens per session scan A 4f479da0d3f7
elixir-phoenix-research is a skill published in the GitHub repository ccarvalho-eng/codex-elixir-phoenix (11 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 1,199 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 2026-08-30.
Other skills, from other repositories
ash-framework
Use this skill working with Ash Framework or any of its extensions. Always consult this when making any domain changes, features or fixes.
phoenix-framework
Use this skill working with Phoenix Framework. Consult this when working with the web layer, controllers, views, liveviews etc.
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 …
code-review
Review code changes for regressions, correctness, and missing tests.
writing-review-packets
Create or revise Reviews packet markdown for a code diff, including section strategy, prose, hunk references, validation, and pushing packet revisions with the Reviews CLI. Use when the user asks to write a review packet, organize a diff for review, add prose around hunk refs, update a packet for a new patchset, or…
using-reviews-locally
Run and use the Reviews app locally, including server startup, port checks, local token setup, CLI config, pushing local reviews or new patchsets, and Codex workflow conventions. Use when the user asks to spin up Reviews, push a local review packet or revision, mint/access local API tokens, debug localhost review…