Deps Vet logo

Deps Vet

Community
oliver-kriska
deps-vet

Record a vetted Hex package version in hex_vet.exs after a security review — manages the audit ledger, not the scanner. Use to approve a dep after /phx:deps-audit findings or to initialize hex_vet.exs.

Overview

Publisheroliver-kriska
Repositoryclaude-elixir-phoenix
Skill namedeps-vet
Stars
555
Forks
40
Bundled files
3
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by oliver-kriska on GitHub. Read the source before you install it.

Installation

Install the Deps Vet AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/oliver-kriska/claude-elixir-phoenix.git /tmp/claude-elixir-phoenix
mkdir -p .claude/skills
cp -r /tmp/claude-elixir-phoenix/plugins/elixir-phoenix/skills/deps-vet .claude/skills/deps-vet
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Deps Vet in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Deps Vet on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Deps Vet is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Deps Vet — Hex package audit ledger

Review a Hex package version, run Phase 1 supply-chain rules against it, prompt the user for a verdict, append the result to hex_vet.exs (project-root audit ledger). Vetted versions get downgraded to INFO on subsequent /phx:deps-audit runs.

Run this AFTER /phx:deps-audit to clear findings. Run this BEFORE merging a mix.lock PR to certify new versions.

Usage

text
/phx:deps-vet phoenix 1.7.21      # vet a single package version
/phx:deps-vet --seed              # import curated baseline seed (~30 pkgs)
/phx:deps-vet --list              # show existing ledger entries
/phx:deps-vet --check             # cross-check mix.lock vs ledger

Iron Laws

  1. NEVER auto-approve. Every entry MUST come from an AskUserQuestion confirmation. Drive-by trust ruins the ledger's value.
  2. Lock wins on disagreement. If mix.lock has version X and the ledger vets X-1, emit INFO and treat X as unvetted. Don't silently trust the older entry.
  3. Ledger lives at project root. hex_vet.exs is a first-class security artifact, visible in PR review. Don't move it into .claude/.
  4. Round-trip via inspect/2. When appending, read the file with Code.eval_file/1, mutate the map, and write back via inspect(term, pretty: true, limit: :infinity). Hand-rolled string appends drift over time.
  5. Always show findings before prompting. The user must see what's being vetted. No silent :safe_to_deploy defaults.
  6. Confirmation counts are COMPUTED, never estimated. Any number in an AskUserQuestion (criteria split, new/overwrite/no-op) MUST be derived from the loaded data before prompting — e.g. Enum.frequencies_by(seed.audits, & &1.criteria). Eyeballing the file and approving on wrong numbers corrupts the consent.

Execution flow

Step 1: Locate or seed hex_vet.exs

text
If hex_vet.exs exists at project root:
    Read it via Code.eval_file/1
Else:
    Write the empty-ledger stub (see ${CLAUDE_SKILL_DIR}/references/hex-vet.md §"Empty ledger")
    Inform user: "Created hex_vet.exs at project root."

Step 2: Branch by mode

  • <pkg> <version> → single-vet path (Step 3-7).
  • --seed → import priv/hex_vet_seed.exs. Before prompting, Code.eval_file/1 the seed and compute (Iron Law #6): the criteria split (Enum.frequencies_by(seed.audits, & &1.criteria)) and, against any existing ledger, exact new / overwrite / no-op counts. Put those computed numbers in the AskUserQuestion. Also state up front that the seed is a provenance baseline, not certification of your current mix.lock (per Iron Law #2, seed versions older than the locked ones stay unvetted). Ask before overwriting existing entries.
  • --list → render the audits table; exit.
  • --check → compare ledger entries with mix.lock; warn on drift. Read the lock via Code.eval_file("mix.lock") with 2>/dev/null — modern locks have quoted keys and emit a found quoted keyword warning per package (tens of KB of noise that gets persisted as an oversized tool result otherwise).

Step 3: Fetch the tarball (single-vet)

Run the deps-audit corpus loader. Cache lives at ~/.cache/phx-deps-audit/corpus/<pkg>/<version>/contents/. Use:

text
bash plugins/elixir-phoenix/skills/deps-audit/smoke-test/corpus.d/fetch.sh \
    <pkg> <version>

Step 4: Run Phase 1 rules

Source the rules from ../deps-audit/references/rules-impl.md. Run run_all_rules over the cached dir. Write findings to a temp vet-findings.jsonl. Set FINDINGS_FILE to override default path.

Step 5: Present findings

Print the findings table per ../deps-audit/references/output-renderer.md. On zero findings: say "No findings — vet from a clean baseline." On any finding: show severity, file, line, snippet inline.

Step 6: Prompt for verdict

Call AskUserQuestion with these 4 options:

  • :safe_to_deploy — full trust; findings investigated and cleared.
  • :safe_to_run — trust in non-production envs only (test deps).
  • :does_not_implement_crypto — Mozilla-style sub-criterion.
  • Skip — defer decision; don't write an entry.

If any finding is BLOCK severity: default-highlight Skip. Require explicit override before writing :safe_to_deploy over a BLOCK.

Step 7: Append to ledger

Read existing hex_vet.exs via Code.eval_file/1. Append the audit map below to :audits. Write back via Code.format_string!(inspect(...)).

elixir
%{
  package: "<pkg>",
  version: "<version>",
  criteria: <verdict_atom>,
  reviewer: "<git config user.email>",
  notes: "<user-provided one-liner OR findings summary>",
  reviewed_at: ~D[<today>]
}

Write back via Code.format_string!(inspect(term, pretty: true)). Confirm to user: "Added <pkg> <version> to hex_vet.exs."

Integration

  • Run after /phx:deps-audit to clear vetted findings.
  • Run before merging a mix.lock PR to certify new versions.
  • Run /phx:deps-vet --check to detect ledger drift vs mix.lock.
  • /phx:deps-audit auto-downgrades vetted findings to INFO.

References

  • ${CLAUDE_SKILL_DIR}/references/hex-vet.md — schema, parser, lookup
  • ${CLAUDE_SKILL_DIR}/references/seed.md--seed flag, curated baseline
  • ${CLAUDE_SKILL_DIR}/../deps-audit/references/rules-impl.md — the same rules /phx:deps-audit runs

Out of scope (Phase 3+)

  • Mix task surface — defer mix phx.deps_vet to a separate Hex package phx_deps_vet for non-CC users.
  • Block-on-unvetted enforcement — defer to a PreToolUse hook that gates mix deps.get.
  • Distributed imports — defer cargo-vet imports: until trust-chain semantics are designed.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Deps Vet AI skill do?

Record a vetted Hex package version in hex_vet.exs after a security review — manages the audit ledger, not the scanner. Use to approve a dep after /phx:deps-audit findings or to initialize hex_vet.exs.

Why use Deps Vet on TypingMind?

Because you install it once and use it with any model. Deps Vet is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Deps Vet in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/oliver-kriska/claude-elixir-phoenix/tree/main/plugins/elixir-phoenix/skills/deps-vet. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Deps Vet?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Deps Vet?

As many as you like. As long as a model supports skills, you can use Deps Vet with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Deps Vet AI skill free?

Yes. It is published on GitHub by oliver-kriska under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇