helix.mcp: Skill for Claude Code

.squad/skills/dependency-audit/SKILL.md

dependency-audit is a skill for Claude Code, Codex from lewing/helix.mcp. It costs 22 tokens per session (871 once invoked), scanned A, original, MIT.

A procedure for reviewing NuGet packages used by a .NET project for available updates, deprecations, and known security vulnerabilities. NuGet is .NET's package system for sharing reusable libraries.

In plain words
What is it for?
Running package audits, focusing on direct dependencies, classifying patch, minor, major, and preview updates, checking release notes when needed, and reviewing deprecated or vulnerable packages.
Why use it?
It provides a regular way to find outdated or unsafe dependencies and to judge whether an update is a routine change or may require compatibility work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is lewing/helix.mcp's own configuration. It tells Claude Code and Codex how to work on helix.mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything helix.mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lewing/helix.mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lewing/helix.mcp/main/.squad/skills/dependency-audit/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lewing/helix.mcp

Made for: Claude Code, Codex.

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 dependency-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/lewing/helix.mcp/dependency-audit.svg)](https://agentmods.dev/skills/lewing/helix.mcp/dependency-audit)
Your own site
<a href="https://agentmods.dev/skills/lewing/helix.mcp/dependency-audit"><img src="https://agentmods.dev/badge/skills/lewing/helix.mcp/dependency-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 871 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 $0.00022 $0.00871
Opus 5 $0.00011 $0.00436
Sonnet 5 $0.00004 $0.00174
Haiku 4.5 $0.00002 $0.00087

Measured 6d ago against content hash d0f1f84b5aad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

dependency-audit 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 6d 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.

.squad/skills/dependency-audit/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context

Run periodically before patch releases or when a dependency deprecation/vulnerability is flagged. This repo uses Central Package Management (CPM) — all versions live in Directory.Packages.props.

Patterns

1. Gather the full picture

# From repo root — covers all projects in one pass
dotnet list package --outdated --include-transitive
dotnet list package --deprecated
dotnet list package --vulnerable

Focus on Top-level Package rows (direct deps) from the --outdated output — transitive rows are informational unless they're security or the direct dep controls them via a floating range.

2. Classify the gap

Gap type Signal Default stance
Patch (x.y.Z) Servicing only 🟢 Bump immediately
Minor (x.Y.z) New features, typically additive 🟢 Bump unless API breakage notes
Major (X.y.z) — .NET versioning Follows runtime version cadence 🟢 Bump when targeting the matching runtime
Major (X.y.z) — third-party May break API surface 🟡 Check release notes first
Preview-only available Upstream not stable 🔴 Hold unless existing pin is preview

3. Check deprecation flags

  • "Other" with no alternative → NuGet/author marking old minor versions to push users to latest of same package. Safe to update to latest stable.
  • "Legacy" with named alternative (e.g., xunitxunit.v3) → This is a migration, not a bump. Plan separately.
  • "Security" → Treat as urgent.

4. Azure SDK packages

Azure SDK packages (Azure.*) move in step. Updating Azure.Identity typically also bumps Azure.Core and System.ClientModel transitively. The Azure SDK changelog is at: https://github.com/Azure/azure-sdk-for-net/blob/main/sdk/{area}/{PackageId}/CHANGELOG.md

5. .NET versioning lockstep

Microsoft.Data.Sqlite, Microsoft.Extensions.*, Microsoft.AspNetCore.* follow the .NET runtime version (e.g., 9.x for net9, 10.x for net10). When the target framework is net10.0, bumping these from 9.x → 10.x is a natural alignment move, not a risky major.

Read the full file on GitHub · 65 lines

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. 6d ago First seen · 65 lines · 22 tokens per session scan A d0f1f84b5aad

Subscribe to this mod's changes

dependency-audit is a skill published in the GitHub repository lewing/helix.mcp (4 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 871 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 2026-08-31.