whiteboard: Skill for Claude Code

.claude/skills/dependabot-review/SKILL.md

dependabot-review is a skill for Claude Code from kamiazya/whiteboard. It costs 120 tokens per session (2,709 once invoked), scanned A, original, Apache-2.0.

A process for reviewing Dependabot updates and security alerts in the whiteboard project. Dependabot is a service that proposes updates to software libraries and reports known security problems.

In plain words
What is it for?
It is for reviewing and merging dependency-update pull requests and clearing Dependabot security alerts.
Why use it?
It helps classify dependency changes, check their effects, verify tests and security scans, and handle update conflicts safely. It also follows this project’s rule that the main integrator controls merges.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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

Part of the whiteboard plugin — 22 skills, 18 agents, 3 hooks shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to kamiazya/whiteboard. 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/kamiazya/whiteboard/main/.claude/skills/dependabot-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kamiazya/whiteboard

Made for: Claude Code.

Or install whiteboard, the plugin that ships this one along with the rest of its 22 skills, 18 agents, 3 hooks.

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 dependabot-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/kamiazya/whiteboard/dependabot-review/github.svg)](https://agentmods.dev/skills/kamiazya/whiteboard/dependabot-review)
Your own site
<a href="https://agentmods.dev/skills/kamiazya/whiteboard/dependabot-review"><img src="https://agentmods.dev/badge/skills/kamiazya/whiteboard/dependabot-review/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 dependabot-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/kamiazya/whiteboard/dependabot-review"><img src="https://agentmods.dev/badge/skills/kamiazya/whiteboard/dependabot-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,709 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 pass 7 Sept 2026
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 $0.00120 $0.02709
Opus 5 $0.00060 $0.01354
Sonnet 5 $0.00024 $0.00542
Haiku 4.5 $0.00012 $0.00271

Measured 11d ago against content hash 3e7c3357d93f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

dependabot-review 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 11d 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/dependabot-review/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dependabot-review (whiteboard)

Triage Dependabot PRs by semver level + ecosystem and safely merge them, and keep the security-alert backlog clearing. The dependabot-triage workflow does the read-only analysis (classify + changelog + repo-impact + CI + adversarial "safe to merge?" + alert coverage); this skill is the integrator's execution loop — judgement + merge mechanics.

How this repo differs from a generic dependabot flow

Read these before applying the reference playbook — they change several steps:

  • NO GitHub Issues. This project uses native Tasks (live board) + tmp/issues/ (durable private backlog) — see the ticketing skill. So never gh issue create for a migration/feature follow-up; file a tmp/issues/<slug>.md or a TaskCreate instead.
  • Single integrator owns git/CI/merge. The main session merges; there is no team of reviewers approving on GitHub. Merges go to the working branch / main per the push model.
  • release-please reads merged commits. Dependabot already titles PRs chore(deps): bump … / chore(deps-dev): … — keep that on squash merge so release-please classifies them as no-bump chores. Do not rewrite the title to fix:/feat:.
  • The CI gate is verify (.github/workflows/ci.yml): pnpm audit --prod --audit-level=high → validate-skills → noConsole → typecheck → test → stdio/template/packaged smokes → build → web-app smokes. A prod high+ vuln BLOCKS merge via that audit step. dev-only vulns do not.
  • npm-published artifact. @kamiazya/whiteboard-mcp ships its runtime deps. Prioritize runtime-scope bumps/alerts (they reach users AND gate pnpm audit --prod) over dev-only ones.
  • Local pre-push gate (lefthook) runs typecheck + mcp-node + noconsole before push; CI is authoritative. For the post-merge verification run, see Step 5.

Load-bearing runtime deps (extra scrutiny)

These ship in the published package and/or anchor a cross-process contract — read the changelog even for a minor, and run the relevant smoke after merging:

Read the full file on GitHub · 177 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. 11d ago First seen · 177 lines · 120 tokens per session scan A 3e7c3357d93f

Subscribe to this mod's changes

dependabot-review is a skill published in the GitHub repository kamiazya/whiteboard (6 stars, last pushed today), licensed Apache-2.0. It adds 120 tokens to every session and 2,709 once invoked, about $0.0006 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.