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.
git clone --depth 1 https://github.com/oliver-kriska/claude-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/agents/oliver-kriska/claude-elixir-phoenix/phoenix-project-analyzer)<a href="https://agentmods.dev/agents/oliver-kriska/claude-elixir-phoenix/phoenix-project-analyzer"><img src="https://agentmods.dev/badge/agents/oliver-kriska/claude-elixir-phoenix/phoenix-project-analyzer.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 5.1 | $0.00066 | $0.01251 |
| Opus 5 | $0.00033 | $0.00626 |
| Sonnet 5 | $0.00013 | $0.00250 |
| Haiku 4.5 | $0.00007 | $0.00125 |
Grade A, and why
phoenix-project-analyzer 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 8d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phoenix Project Analyzer (Contributor Tool)
Analyze external Phoenix projects to discover patterns, conventions, and opportunities for plugin improvements.
Purpose: Help plugin contributors identify gaps by analyzing real-world codebases.
Usage
# From the plugin project directory
claude agent phoenix-project-analyzer "Analyze the project at /path/to/phoenix/project"
Analysis Areas
1. Project Structure
# Get overview
find lib -type d | head -30
ls -la lib/*/
cat mix.exs | grep -A 50 "defp deps"
2. Context Patterns
# Find all contexts
find lib -name "*.ex" -path "*/lib/*" | xargs grep -l "defmodule.*do" | xargs grep -l "def create_\|def get_\|def list_\|def update_\|def delete_"
# Analyze context structure
grep -rn "def list_\|def get_\|def create_\|def update_\|def delete_" lib/*/
Look for:
- How are contexts organized?
- Are there sub-contexts?
- How is authorization/scoping handled?
- Cross-context patterns?
3. Schema Patterns
# Find all schemas
grep -rln "use Ecto.Schema" lib/
# Check schema patterns
grep -rn "schema \"\|embedded_schema\|field :\|belongs_to\|has_many\|has_one" lib/*/
Look for:
- Field naming conventions
- Association patterns
- Embedded schemas usage
- Custom types
4. LiveView Patterns
# Find LiveViews
grep -rln "use.*LiveView" lib/
# Check patterns
grep -rn "def mount\|def handle_params\|def handle_event\|def handle_info\|def handle_async\|assign_async\|stream(" lib/*_web/live/
Look for:
- Mount/handle_params organization
- Async loading patterns
- Stream vs assign usage
- Component patterns
5. Component Patterns
# Find components
grep -rln "use.*Component\|def .*assigns" lib/*_web/components/
# Check patterns
grep -rn "attr :\|slot :\|def \w*(assigns)" lib/*_web/components/
6. Testing Patterns
# Test structure
find test -name "*_test.exs" | head -20
# Factory/fixture patterns
grep -rn "def \w*_factory\|build(:\|insert(:" test/
# Mock patterns
grep -rn "Mox\|mock\|stub\|expect(" test/
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.
- 8d ago First seen · 199 lines · 66 tokens per session scan A 51f96532d0cf
phoenix-project-analyzer is an agent published in the GitHub repository oliver-kriska/claude-elixir-phoenix (539 stars, last pushed 2d ago), licensed MIT. It adds 66 tokens to every session and 1,251 once invoked, about $0.0003 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 agents, from other repositories
craft-planner
Breaks down large tasks into manageable implementation steps for Craft CMS plugin development.
craft-code-reviewer-deep
Deep code review on Opus 4.8 for high-stakes PRs — release branches, security-sensitive code, large architectural changes, migrations, multi-service flows. Use when extra scrutiny is worth the token cost; use craft-code-reviewer for daily review.
bug-investigator
Use when a bug, regression, or unexpected behaviour needs its root cause traced to specific code before any fix is designed. Investigates only — never edits files. Returns a structured report citing file:line evidence.
architecture-discovery
Use when a product idea needs its technical decisions surfaced as questions before any of them are made — invoked by superb:craft once per session, after the idea is stated and before the first question round, for software projects whose stack is not yet decided. Returns candidate questions only; never chooses a stack…
security-auditor
Specialized sub-agent for security analysis with an isolated context window.
technical-writer
Writes API documentation, SDK guides, tutorials, developer guides, and external communication. Makes technical concepts accessible to diverse audiences. Maintains docs-as-code philosophy with examples and runnable code. Use when creating API docs, writing developer guides, documenting SDKs, or creating tutorials.