metadome-link: Skill for Claude Code

.claude/skills/dependency-cve-sweep/SKILL.md

dependency-cve-sweep is a skill for Claude Code from berntpopp/metadome-link. It costs 33 tokens per session (426 once invoked), scanned A, a copy of dependency-cve-sweep, MIT.

A procedure for reviewing dependency updates and security alerts, including Dependabot, CodeQL, and Trivy findings.

In plain words
What is it for?
Use it for routine dependency and CVE reviews, consolidating update pull requests, fixing code-scanning alerts, updating Python packages, and checking container security.
Why use it?
It keeps security fixes coordinated and verifies that dependency locks, CI checks, container scans, and GitHub Actions remain safe and reproducible.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

This is berntpopp/metadome-link's own configuration. It tells Claude Code how to work on metadome-link 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 metadome-link configures →

Reuse

Borrowing it

Nothing to install: this file belongs to berntpopp/metadome-link. 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/berntpopp/metadome-link/main/.claude/skills/dependency-cve-sweep/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/berntpopp/metadome-link

Made for: Claude Code.

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-cve-sweep

README.md
[![agentmods](https://agentmods.dev/badge/skills/berntpopp/metadome-link/dependency-cve-sweep/github.svg)](https://agentmods.dev/skills/berntpopp/metadome-link/dependency-cve-sweep)
Your own site
<a href="https://agentmods.dev/skills/berntpopp/metadome-link/dependency-cve-sweep"><img src="https://agentmods.dev/badge/skills/berntpopp/metadome-link/dependency-cve-sweep/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 dependency-cve-sweep

Your own site · 80×15
<a href="https://agentmods.dev/skills/berntpopp/metadome-link/dependency-cve-sweep"><img src="https://agentmods.dev/badge/skills/berntpopp/metadome-link/dependency-cve-sweep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 426 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 94% copy Near-identical to another mod 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 $0.00033 $0.00426
Opus 5 $0.00016 $0.00213
Sonnet 5 $0.00007 $0.00085
Haiku 4.5 $0.00003 $0.00043

Measured 10d ago against content hash 2f166dcdf36e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

dependency-cve-sweep 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 10d 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.

Origin

This is a copy

94% identical to dependency-cve-sweep — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/dependency-cve-sweep/SKILL.md · 27 lines

What it actually says

Dependency & CVE Sweep

Follow AGENTS.md first. Consolidate a repo's open Dependabot PRs into one clean PR rather than merging many.

Workflow

  1. Bump Python deps with uv lock --upgrade-package <name> (targeted) or uv lock --upgrade (full); keep uv.lock committed and --frozen in the build.
  2. SHA-pin GitHub Actions (uses: owner/action@<40-char-sha> # vX.Y.Z), never floating tags.
  3. Fix CodeQL findings at the cause; for the common py/incomplete-url-substring-sanitization test-assertion false positive, switch to exact-match assertions.
  4. Keep the Trivy gate in the ratified 2-step form (severity: CRITICAL,HIGH + ignore-unfixed: true + exit-code: "1") and retain the SBOM (../genefoundry-router/docs/CONTAINER-HARDENING-STANDARD-v1.md).
  5. Gate on make ci-local; patch-bump the app version; squash-merge only on green.

Gotcha (FastMCP bumps)

When bumping FastMCP, verify validation-error wrapping: some 3.4.x releases re-raise argument-validation errors as fastmcp.exceptions.ValidationError, so a test asserting on a Pydantic ValidationError must walk __cause__. A version/catalog guard test may also need regenerating.

Common mistakes

  • Merging Dependabot PRs one-by-one instead of one consolidated PR.
  • Floating action tags instead of SHA pins.
  • Flipping Trivy exit-code: "1" without ignore-unfixed: true — gates on unfixable base-image CVEs → self-inflicted outage.
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. 10d ago First seen · 27 lines · 33 tokens per session scan A 2f166dcdf36e

Subscribe to this mod's changes

dependency-cve-sweep is a skill published in the GitHub repository berntpopp/metadome-link (0 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 426 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to dependency-cve-sweep, differing in 2 lines, and is treated as a copy.

Related

Other skills, from other repositories

webmcp-nexus

A coding guide for adding WebMCP tools to JavaScript or TypeScript projects. WebMCP lets AI agents call selected application functions through a standard interface.

alibaba/webmcp-nexus · 159 tokens

unblock

Use whenever you need to read a web page, URL, article, documentation page, search result, product page or any live website content. Fetches through UnblockingAPI (unblockfetch, findtemplates) instead of the built-in WebFetch, starting with a plain fetch and rendering with a real browser only when the page needs…

unblockingapi/mcp · 83 tokens

dark-memory

Use for governance, memory, drift detection, and audit trail via dark-memory-mcp. Covers 52 canonical + 3 red-team tools across 16 namespaces: session lifecycle, agentmemory CRUD+search, vibe-flow spec/artifact publish + drift, LLM-as-judge, delegation+mindset, research, observability, error observatory, governance…

Opita-Code/dark-memory-mcp · 353 tokens

driving-unreal

Use when driving an Unreal Engine 5.x editor through the unreal-ai-connection MCP tools — building or populating a level, spawning/transforming actors, authoring materials and material instances, setting up lighting and atmosphere, reconstructing a scene from a reference photo, setting up a sequencer/cinematic shot…

NAJEMWEHBE/unreal-ai-connection · 269 tokens

youtube-transcripts

Read and search YouTube videos through VidWords. Use when the user supplies a YouTube URL, a bare 11-character video id, a youtu.be or Shorts link, or a channel handle, and wants any of: the transcript or subtitles (TXT/SRT/VTT), what a video says about a topic, a quote with a citable timestamp, only the words spoken…

haljishi/vidwords-mcp · 111 tokens

computase

Performs verified local nucleotide-sequence computation with Computase. Use when an agent needs sequence composition or GC bounds, a reverse complement, translation, candidate ORFs, or IUPAC motif sites through Computase MCP tools or the isolated Skill runner.

madhusudan-kulkarni/computase · 53 tokens