dependabot-batch

A workflow for reviewing weekly Dependabot updates. Dependabot is a service that proposes updates to a project's third-party packages.

In plain words
What is it for?
Use it to assess low-risk dependency updates, test them together, create a replacement pull request, and close the Dependabot requests it replaces.
Why use it?
It filters for updates that have been available for at least 72 hours, checks their changes, and combines suitable ones into one tested pull request.

Command for Claude Code

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.

agentmods
npx agentmods add commands/skyhook-io/radar/dependabot-batch
Clone the repo
git clone --depth 1 https://github.com/skyhook-io/radar

Made for: Claude Code.

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,846 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00019 $0.01846
Opus 5 $0.00010 $0.00923
Sonnet 5 $0.00004 $0.00369
Haiku 4.5 $0.00002 $0.00185

Measured 2d ago against content hash a00f916a0d72, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dependabot-batch 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 2d 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/commands/dependabot-batch.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dependabot Batch

Replace Radar's open weekly Dependabot PRs with one evidence-backed dependency PR. Include only updates that have been published for at least 72 hours and look safe after upstream review and Radar-specific testing. Do not merge the resulting PR.

This command is end-to-end unless the user asks for an audit only or says not to create a PR. Creating the batch PR includes pushing its branch and closing only the Dependabot PRs it supersedes. It does not authorize merging, publishing, tagging, or changing release artifacts.

Non-negotiable gates

  • Measure soak from the target version's upstream publication time, never from the Dependabot PR creation time. Record the screening time in UTC. A version must be at least 72 hours old at that instant; do not round up or make exceptions without explicit user approval.
  • Apply the gate to the final resolved dependency graph, including transitive upgrades and newly introduced packages. A lockfile or module resolver can move beyond the version named in a PR.
  • Read the official release notes or changelog for every direct candidate across the complete old-to-new range. Review official release metadata and meaningful changes for every changed transitive dependency too. If notes are missing or vague, inspect the upstream compare/commit range; uncertainty raises risk rather than counting as evidence of safety.
  • Use primary sources: upstream releases, changelogs, compare views, issue trackers/security advisories, npm registry metadata, the Go module proxy, and GitHub tag/release metadata. Dependabot's summary and compatibility score are leads, not the review.
  • Do not execute lifecycle/install scripts from a candidate package before it clears the soak and review gates. npm install --package-lock-only --ignore-scripts or npm ci --ignore-scripts is appropriate while constructing/auditing the graph; run the repository's normal verification after the included set is approved.
  • Keep the batch dependency-only. If an update requires Radar source changes, a migration, or a speculative compatibility fallback, exclude it and explain the needed follow-up. Version-locked companion packages may move together when upstream requires it, but each resolved version must clear the same review and soak gates.
  • Preserve unrelated work. Start from current origin/main on a dedicated deps/dependabot-batch-YYYY-MM-DD branch, using a separate worktree when the current tree is dirty or in active use.

Read the full file on GitHub · 102 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. 2d ago First seen · 102 lines · 19 tokens per session scan A a00f916a0d72

Subscribe to this mod's changes

dependabot-batch is a command published in the GitHub repository skyhook-io/radar (3,204 stars, last pushed today), licensed Apache-2.0. It adds 19 tokens to every session and 1,846 once invoked, about $0.0001 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.