hexpm

hexpm is a skill for Claude Code from joshrotenberg/hexpm-mcp. It costs 62 tokens per session (522 once invoked), scanned A, original, MIT.

A skill for working with Elixir and Erlang packages from Hex, including package selection, upgrades, API use, and dependency audits. It uses live data from package registries, documentation, and vulnerability databases.

In plain words
What is it for?
Use it to compare dependencies, read the documentation for locked versions, check releases and upgrade paths, and audit direct or transitive dependencies for advisories.
Why use it?
Package versions, APIs, and security advisories change, so checking current sources is safer than relying on remembered information. It also separates package health checks from vulnerability audits.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the hexpm plugin — 1 skill, 1 hook shipped together

Good fit Use it to compare dependencies, read the documentation for locked versions, check releases and upgrade paths, and audit direct or transitive dependencies for advisories.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joshrotenberg/hexpm-mcp/hexpm
Install

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.

Any agent
npx skills add joshrotenberg/hexpm-mcp --skill hexpm
Clone the repo
git clone --depth 1 https://github.com/joshrotenberg/hexpm-mcp

Made for: Claude Code.

Or install hexpm, the plugin that ships this one along with the rest of its 1 skill, 1 hook.

Wrote 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.

agentmods badge for hexpm

README.md
[![agentmods](https://agentmods.dev/badge/skills/joshrotenberg/hexpm-mcp/hexpm/github.svg)](https://agentmods.dev/skills/joshrotenberg/hexpm-mcp/hexpm)
Your own site
<a href="https://agentmods.dev/skills/joshrotenberg/hexpm-mcp/hexpm"><img src="https://agentmods.dev/badge/skills/joshrotenberg/hexpm-mcp/hexpm/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.

agentmods 80×15 button for hexpm

Your own site · 80×15
<a href="https://agentmods.dev/skills/joshrotenberg/hexpm-mcp/hexpm"><img src="https://agentmods.dev/badge/skills/joshrotenberg/hexpm-mcp/hexpm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 522 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00062 $0.00522
Opus 5.5 $0.00025 $0.00209
Sonnet 5.5 $0.00012 $0.00104
Haiku 4.5 $0.00006 $0.00052

Measured 9d ago against content hash 96db3574c497, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hexpm 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 9d 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.

priv/plugin/hexpm/skills/hexpm/SKILL.md · 50 lines

What it actually says

Hex dependencies with hexpm

The hexpm MCP server answers from hex.pm, HexDocs, OSV.dev and the Elixir Toolbox at call time. Versions, release dates, owners, advisories and APIs all change after training, so prefer the tools over memory for each of them.

Before adding or recommending a dependency

  1. health for maintenance status, release cadence, downloads, owner count and retired versions.
  2. audit_mix_deps with that one dependency line, such as {:req, "~> 0.6"}, for the package's own advisories. health does not query OSV, and audit checks the package's dependencies rather than the package.
  3. audit when the package brings in dependencies the project does not already have.
  4. When the result is weak (stale, one owner, open advisories), look wider with alternatives or toolbox_search, then compare two to five candidates.

Report what the tools returned, with versions and dates, not a verdict alone.

Upgrading

  1. upgrade_check with the deps list from mix.exs. It flags major-version jumps.
  2. For each upgrade, release and dependencies for the target version, and versions for the releases in between.
  3. audit_mix_deps on the updated list before reporting the upgrade done.

Writing code against a package

Read the API for the version in mix.lock instead of recalling it. Function names, arities and options change between releases.

  1. docs with that version for the module list.
  2. search_docs to find a module or function by name.
  3. doc_item for a module's full documentation.

Auditing a project

audit_mix_deps, then upgrade_check, each with the deps list from mix.exs.

audit_mix_deps counts every advisory filed against a package, whatever the version. Before calling a dependency vulnerable, check that the version in mix.lock falls inside the advisory's affected range.

Changes

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.

  1. 9d ago First seen · 50 lines · 62 tokens per session scan A 96db3574c497

Subscribe to this mod's changes

hexpm is a skill published in the GitHub repository joshrotenberg/hexpm-mcp (2 stars, last pushed 7d ago), licensed MIT. It adds 62 tokens to every session and 522 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-29.

Related

hexpm compared with skills from other repositories

hexpm next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
hexpmjoshrotenberg/hexpm-mcpSkill27d agoMITA62Claude Code
elixir-expertpersonamanagmentlayer/pclSkill4413d agoApache-2.0A47Claude Code
elixir-reviewcamilooscargbaptista/cto-toolkitSkill87mo agoMITA25Claude Code
elixirericrisco/rsc-harnessSkill5293d agoMITA72Claude Code, Codex
tree-sitter-language-pack-extracting-code-structurexberg-io/tree-sitter-language-packSkill483yesterdayMITA52Claude Code
tree-sitter-language-pack-chunking-for-llmsxberg-io/tree-sitter-language-packSkill483yesterdayMITA52Claude Code
tree-sitter-language-pack-detecting-languagesxberg-io/tree-sitter-language-packSkill483yesterdayMITA55Claude Code