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.
curl -O https://raw.githubusercontent.com/kamiazya/whiteboard/main/.claude/skills/dependabot-review/SKILL.mdgit clone --depth 1 https://github.com/kamiazya/whiteboardWrote 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.
[](https://agentmods.dev/skills/kamiazya/whiteboard/dependabot-review)<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.
<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>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once 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 |
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.
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 theticketingskill. So nevergh issue createfor a migration/feature follow-up; file atmp/issues/<slug>.mdor aTaskCreateinstead. - 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 /
mainper 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 tofix:/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-mcpships its runtime deps. Prioritize runtime-scope bumps/alerts (they reach users AND gatepnpm 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:
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.
- 11d ago First seen · 177 lines · 120 tokens per session scan A 3e7c3357d93f
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…