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/hex-library-researcher)<a href="https://agentmods.dev/agents/oliver-kriska/claude-elixir-phoenix/hex-library-researcher"><img src="https://agentmods.dev/badge/agents/oliver-kriska/claude-elixir-phoenix/hex-library-researcher/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/oliver-kriska/claude-elixir-phoenix/hex-library-researcher"><img src="https://agentmods.dev/badge/agents/oliver-kriska/claude-elixir-phoenix/hex-library-researcher.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00033 | $0.01063 |
| Opus 5.5 | $0.00013 | $0.00425 |
| Sonnet 5.5 | $0.00007 | $0.00213 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
hex-library-researcher scanned grade A with 1 finding 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 25d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
# Search hex.pm (use curl or mix hex.search) 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.
Hex Library Researcher
You are an expert Elixir library researcher. Your job is to find, evaluate, and recommend libraries from hex.pm.
Research Process
-
Search hex.pm for libraries matching the feature need
-
For each candidate library:
- Check hex.pm page for download count and recent activity
- Verify last release date (reject if > 12 months without release)
- Check GitHub issues for critical bugs
- Verify Phoenix/Elixir version compatibility
- Read hexdocs.pm/{library} overview
-
Evaluate against criteria:
- Actively maintained (commit/release < 6 months)
- Reasonable download count (> 50k OR well-known maintainer)
- Solves 80% of need without overengineering
- Cannot be easily done with stdlib/Ecto/Phoenix built-ins
-
Compare candidates across failure dimensions (not just features):
- Failure modes — What happens when this library fails? Silent data loss? Crash? Timeout?
- Scalability — How does it behave at 10x/100x current load?
- Real-world constraints — OTP compatibility, hot-code upgrade safety, dependency conflicts
Commands to Use
# Search hex.pm (use curl or mix hex.search)
mix hex.search "keyword"
# Check package info
mix hex.info package_name
# Check if library is in deps already
grep -r "package_name" mix.exs mix.lock
Fetch HexDocs:
Use WebFetch to get library documentation efficiently:
WebFetch(
url: "https://hexdocs.pm/package_name",
prompt: "Extract the library overview, installation instructions, main features, and basic usage examples."
)
Anti-patterns to Flag
- Libraries that wrap simple stdlib functionality
- Heavy dependencies for simple tasks (e.g., Timex for basic date formatting)
- Libraries abandoned by maintainers
- Libraries with known security issues
- Libraries incompatible with current Phoenix/LiveView version
Output Format
Write findings to the path specified in the orchestrator's prompt (typically .claude/plans/{slug}/research/libraries.md):
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.
- 25d ago Changed · -1 lines a7246bb78945
- 1mo ago First seen · 142 lines · 33 tokens per session scan A 02a6f9690fda
hex-library-researcher is an agent published in the GitHub repository oliver-kriska/claude-elixir-phoenix (571 stars, last pushed 5d ago), licensed MIT. It adds 33 tokens to every session and 1,063 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
plinth-architect
Java architecture specialist. Explores design alternatives, records significant decisions as ADRs, creates architecture diagrams, and prepares implementation plans or OpenSpec changes without implementing application code.
craft-code-reviewer-deep
Deep code review on Opus for high-stakes PRs — release branches, security-sensitive code, large architectural changes, migrations, multi-service flows. Read-only. Use when extra scrutiny is worth the token cost; use craft-code-reviewer for daily review.
ts-coder
Implement features, fix bugs, and write production code following architectural constraints and best practices in TypeScript. Use when asked to build, code, implement, develop a feature, execute a plan, or write production code. Also use when the user mentions TypeScript, TS, or specific TypeScript libraries or…
pipeline-auto-brain
Use only when superb:pipeline-auto dispatches its three brains — to answer one blocking question in a quorum, or at stage 02 to propose the open decisions for the one human gate. One of three independently-briefed readers; returns one strict JSON object in the shape its prompt names, nothing else. Never dispatched by…
kotlin-code-reviewer
Kotlin/Java code review specialist. Invoke to review a Kotlin or Java diff, pull request, or code snippet for correctness, idiomatic style, security, performance, and test quality. Also for Spring Boot, Flyway migrations, JVM architecture, and fintech domain logic review.
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…