llms: Skill for Claude Code

.claude/skills/deps/SKILL.md

deps is a skill for Claude Code from matteocervelli/llms. It costs 70 tokens per session (3,041 once invoked), scanned A, original, MIT.

A dependency audit that checks whether project packages are outdated or affected by known security vulnerabilities, then records update decisions.

In plain words
What is it for?
Use it to scan dependencies, classify findings, decide whether to update or defer them, and review dependency history.
Why use it?
It makes dependency maintenance easier to track and highlights packages that may need attention.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

This is matteocervelli/llms's own configuration. It tells Claude Code how to work on llms 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 llms configures →

Reuse

Borrowing it

Nothing to install: this file belongs to matteocervelli/llms. 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/matteocervelli/llms/main/.claude/skills/deps/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/matteocervelli/llms

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 deps

README.md
[![agentmods](https://agentmods.dev/badge/skills/matteocervelli/llms/deps.svg)](https://agentmods.dev/skills/matteocervelli/llms/deps)
Your own site
<a href="https://agentmods.dev/skills/matteocervelli/llms/deps"><img src="https://agentmods.dev/badge/skills/matteocervelli/llms/deps.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,041 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00070 $0.03041
Opus 5 $0.00035 $0.01520
Sonnet 5 $0.00014 $0.00608
Haiku 4.5 $0.00007 $0.00304

Measured 3d ago against content hash d78c6df0d4f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

deps 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 3d 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.

DECISIONS=$(curl -sf --max-time 5 \
.claude/skills/deps/SKILL.md · 372 lines

How it starts

The opening of the file, as written. The whole thing — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/deps — Dependency Health & Decision Tracker

Scans project dependencies for outdated versions and CVEs, classifies severity, and records human decisions (update / defer / skip) in Atrium so the reasoning survives across sessions.

Data flow: /deps scan both reads AND writes to Atrium:

  • Reads: existing decisions to mark assessed deps
  • Writes: fresh outdated findings via POST /api/dev-projects/sync (keeps Atrium current between scheduled audit runs)

Graceful degradation: When Atrium is unreachable, scan/classify still works locally. Decision storage and decision-coverage checks are silently skipped with a note.

Quick Start

/deps                        # summary: outdated deps + decision status for current project
/deps scan                   # full scan → PASS/WARN/FAIL gate (used by /health deps)
/deps decide                 # interactive: assess each unassessed finding, record to Atrium
/deps status                 # fetch current snapshot from Atrium (deps + active decisions)
/deps history                # fetch version changelog from Atrium (newest first)

Invoked by: /health deps as part of the full project health audit.


Atrium URL Resolution

All subcommands that talk to Atrium resolve the base URL in this order:


Subcommand: /deps (summary)

Show dependency status for the current project — outdated count by severity, decision coverage.

Steps:

  1. Detect project slug from current directory (last segment of pwd).
  2. If Atrium unreachable: fall through to local scan mode (show outdated only, no decisions).
  3. If Atrium available: show dep table with decision column.

Output:

## Dependency Status — <project> — <date>

  next                 14.2.0 → 15.0.0   [HIGH]     DEFERRED until 2026-04-27
  fastapi              0.109.0 → 0.115.0  [MEDIUM]   unassessed
  httpx                0.27.0 → 0.28.0    [LOW]      unassessed

Summary: 1 CRITICAL · 0 HIGH unassessed · 2 MEDIUM unassessed
Run `/deps decide` to record decisions. Run `/deps scan` for full gate.

Read the full file on GitHub · 372 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. 3d ago First seen · 372 lines · 70 tokens per session scan A d78c6df0d4f4

Subscribe to this mod's changes

deps is a skill published in the GitHub repository matteocervelli/llms (25 stars, last pushed 3mo ago), licensed MIT. It adds 70 tokens to every session and 3,041 once invoked, about $0.0003 per session on Opus 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 2026-09-03.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens