NodeBenchAI: Skill for Claude Code

.claude/skills/dep-skills-howto/SKILL.md

dep-skills-howto is a skill for Claude Code from HomenShum/NodeBenchAI. It costs 50 tokens per session (1,319 once invoked), scanned A, original, MIT.

A guide and format for writing project-local upgrade runbooks for software packages. A runbook is a step-by-step record of how to move from one package version to another.

In plain words
What is it for?
Use it when a dependency upgrade breaks continuous integration, when package APIs change, or when creating a repeatable migration recipe for a project.
Why use it?
Major package upgrades can break builds and produce many errors. These runbooks preserve the affected files, API changes, and checks so developers do not have to rediscover them each time.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

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

Reuse

Borrowing it

Nothing to install: this file belongs to HomenShum/NodeBenchAI. 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/HomenShum/NodeBenchAI/main/.claude/skills/dep-skills-howto/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/HomenShum/NodeBenchAI

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 dep-skills-howto

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/homenshum/nodebenchai/dep-skills-howto"><img src="https://agentmods.dev/badge/skills/homenshum/nodebenchai/dep-skills-howto.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,319 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 5 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 45
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 50
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 51
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 99
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 52
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
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 $0.00050 $0.01319
Opus 5 $0.00025 $0.00660
Sonnet 5 $0.00010 $0.00264
Haiku 4.5 $0.00005 $0.00132

Measured 10d ago against content hash 39e4919ba9e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

dep-skills-howto 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.

.claude/skills/dep-skills-howto/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

How to write dep-* skills

Project-local migration runbooks for dependencies that bite us on upgrade. Each dep-<package> skill captures the mechanical recipe for moving from one version to the next, plus the list of files in this repo that consume the package.

Why these exist

Without these, every dependabot major bump turns into a 30-90 minute archaeology session: read upstream MIGRATION.md, grep for affected files, learn the new API, hope I didn't miss anything. Multiply by 9 packages in a single dependabot group bump and you get the kind of cascade we hit on 2026-04-26 (467 typecheck errors after PR #107 admin-merged a convex-runtime group).

These skills are the runbook. Read once, apply with confidence.

Schema

Each skill is .claude/skills/dep-<short-name>/SKILL.md with this frontmatter:

---
name: dep-<short-name>           # matches directory; loaded as skill of this name
description: <one sentence — what package, what bumps it covers>
trigger: when <package> appears in package.json diff, when CI fails with <signature errors>, when user asks to bump <package>
---

Required body sections:

## Last verified

The exact version-pair you tested against. Format: from X.Y.Z to A.B.C, verified 2026-MM-DD.

## Coupled bumps

Other packages that MUST move in lockstep (peer deps, AI-SDK families, etc.). Include exact version constraints.

## Recipe

Numbered steps. Each step is one mechanical action. Format:

1. Edit `<file>:<line range>` — change `oldPattern` to `newPattern`
2. Run `<command>` — should produce `<expected outcome>`

## Affected files

List of files in THIS repo that import or use the package. Auto-regenerable from npx tsc --noEmit failure output after the bump (see Maintenance below).

## Verification

Commands that must pass before the migration is considered complete:

npx tsc --noEmit                        -> 0 errors
npx tsc --noEmit -p convex/tsconfig.json -> 0 errors
npx vite build                          -> success

Read the full file on GitHub · 107 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. 10d ago First seen · 107 lines · 50 tokens per session scan A 39e4919ba9e9

Subscribe to this mod's changes

dep-skills-howto is a skill published in the GitHub repository HomenShum/NodeBenchAI (14 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 1,319 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

convex-agents

Building AI agents with the Convex Agent component including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration.

waynesutton/convexskills · 32 tokens

convex-agents

Building AI agents with the Convex Agent component including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration.

J-StaR-Films-Studios/VibeCode-Protocol-Suite · 32 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

deploy-docker-compose

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…

omnigent-ai/omnigent · 84 tokens

haiku

When writing a haiku for this bot, follow these conventions.

agno-agi/agno · 0 tokens

fastapi-router-py

Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.

microsoft/skills · 46 tokens