wandb-onboarding

wandb-onboarding is a skill for Claude Code from happyhappy-jun/writing-driven-autoresearch. It costs 40 tokens per session (1,380 once invoked), scanned C, original, Apache-2.0.

A guided setup for W&B Cloud, a service that records machine-learning experiments and their results. It covers account setup, API-key authentication, and creating a first tracking project or run.

In plain words
What is it for?
Use it to sign up for W&B Cloud, configure or check SDK authentication, follow an offline tutorial, or create an experiment-tracking run.
Why use it?
It explains the setup while keeping passwords, API keys, and other identity steps out of chat and source code. It also checks the software setup before data is uploaded.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ralphthon-icml plugin — 8 skills shipped together

Good fit Use it to sign up for W&B Cloud, configure or check SDK authentication, follow an offline tutorial, or create an experiment-tracking run.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/happyhappy-jun/writing-driven-autoresearch/wandb-onboarding
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add happyhappy-jun/writing-driven-autoresearch --skill wandb-onboarding
Clone the repo
git clone --depth 1 https://github.com/happyhappy-jun/writing-driven-autoresearch

Made for: Claude Code.

Or install ralphthon-icml, the plugin that ships this one along with the rest of its 8 skills.

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 wandb-onboarding

README.md
[![agentmods](https://agentmods.dev/badge/skills/happyhappy-jun/writing-driven-autoresearch/wandb-onboarding/github.svg)](https://agentmods.dev/skills/happyhappy-jun/writing-driven-autoresearch/wandb-onboarding)
Your own site
<a href="https://agentmods.dev/skills/happyhappy-jun/writing-driven-autoresearch/wandb-onboarding"><img src="https://agentmods.dev/badge/skills/happyhappy-jun/writing-driven-autoresearch/wandb-onboarding/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 wandb-onboarding

Your own site · 80×15
<a href="https://agentmods.dev/skills/happyhappy-jun/writing-driven-autoresearch/wandb-onboarding"><img src="https://agentmods.dev/badge/skills/happyhappy-jun/writing-driven-autoresearch/wandb-onboarding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,380 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 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 $0.00040 $0.01380
Opus 5 $0.00020 $0.00690
Sonnet 5 $0.00008 $0.00276
Haiku 4.5 $0.00004 $0.00138

Measured 12d ago against content hash 4cd4712e6cb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

wandb-onboarding scanned grade C 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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (assets/wandb-quickstart.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

**Never ask** the user to paste an API key, password, MFA code, or OAuth token into chat. Do not read cookies, browser storage, password managers, `~/.netrc`, environment variable values, or raw credential files.
ralphthon-icml/skills/wandb-onboarding/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

W&B Onboarding

Overview

Guide signup with browser assistance, hand sensitive identity steps to the user, then verify the SDK offline before any upload. Read the current official workflow for URLs and commands. For official examples and autoresearch analysis, also read the W&B official ecosystem.

Preflight

Classify the target as signup, SDK authentication, offline tutorial, or online run. Confirm browser and uv availability without inspecting credentials, secret files, cookies, browser storage, or environment-variable values.

Safety Contract

Never ask the user to paste an API key, password, MFA code, or OAuth token into chat. Do not read cookies, browser storage, password managers, ~/.netrc, environment variable values, or raw credential files.

The user must complete identity-provider selection, credentials, OAuth consent, CAPTCHA, MFA, email verification, legal acceptance, final signup, and API-key copy. Use an interactive prompt for the key; never place it in a command argument, source file, generated asset, or repository.

Workflow

  1. Open the official W&B signup page with the available Browser skill. Inspect the current visible options; do not guess selectors when the page changes. If browser control is unavailable, give the exact manual link and checkpoint list.
  2. Recommend the Cloud-hosted Free plan and personal entity for an individual tutorial. Present any discovered organization/team separately and let the user choose.
  3. Hand off the sensitive signup steps. After the user returns, verify only the visible logged-in state.
  4. Guide the user to User Settings → API Keys. The user creates and stores the key privately.
  5. For existing credentials, run wandb login --verify. For a new key, explain the local credential write, obtain explicit confirmation, then run wandb login --relogin --cloud --verify. The user enters the key only in the interactive prompt.
  6. Copy assets/wandb-quickstart.py into a disposable uv workspace. Run it first with WANDB_MODE=offline and inspect the completed local run.
  7. Before any online run or offline-run sync, show the target entity, project, visibility, metrics/config fields, group, job_type, code/Git/console/system capture settings, every offline run directory, and files or data that would upload. Set or verify project visibility in the official UI, bind the approved destination through WANDB_ENTITY and WANDB_PROJECT, then obtain explicit confirmation.
  8. Prefer syncing the already verified offline run with wandb sync --entity ... --project ... --skip-console --no-sync-tensorboard <run-directory>. Verify the authoritative run URL and visible fields after upload. Report what was uploaded and how to remove or change access if needed.

Read the full file on GitHub · 79 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 79 lines · 40 tokens per session scan C 4cd4712e6cb4

Subscribe to this mod's changes

wandb-onboarding is a skill published in the GitHub repository happyhappy-jun/writing-driven-autoresearch (21 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,380 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). 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

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

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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens