dependabot-prs

dependabot-prs is a skill for Claude Code from ryanb/dotfiles. It costs 13 tokens per session (1,005 once invoked), scanned A, original, MIT.

A workflow for reviewing and merging open pull requests created by Dependabot. Dependabot is a service that opens pull requests to update a project’s dependencies, which are external libraries the project uses.

In plain words
What is it for?
Use it to list open Dependabot pull requests, review each one with a separate coding agent, and merge suitable updates. It stops when no matching pull requests are open.
Why use it?
It organizes dependency-update reviews and applies repository-specific preferences before deciding what to merge.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions subagents.

Good fit Use it to list open Dependabot pull requests, review each one with a separate coding agent, and merge suitable updates. It stops when no matching pull requests are open.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ryanb/dotfiles/dependabot-prs
About the project

ryanb/dotfiles is a collection of command-line configuration files for macOS, centered on Zsh and related tools such as Git, Ruby, Rails, and IRB. It is for developers who want to customize their terminal with commands, completions, prompts, and fuzzy-finding workflows. Its catalogue skills and plugin provide coding-agent workflows built into the same setup.

ryanb/dotfiles · 2,400 stars · on GitHub

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 ryanb/dotfiles --skill dependabot-prs
Clone the repo
git clone --depth 1 https://github.com/ryanb/dotfiles

Made for: Claude Code.

Its marketplace also offers this one on its own, as the plugin dependabot-prs — /plugin install dependabot-prs after adding the marketplace above.

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-prs

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/ryanb/dotfiles/dependabot-prs"><img src="https://agentmods.dev/badge/skills/ryanb/dotfiles/dependabot-prs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,005 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 $0.00013 $0.01005
Opus 5.5 $0.00005 $0.00402
Sonnet 5.5 $0.00003 $0.00201
Haiku 4.5 $0.00001 $0.00101

Measured 1mo ago against content hash f29c1b31ac28, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dependabot-prs 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 1mo 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-prs/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dependabot PR Review and Merge

Follow these steps:

1. Load per-repo preferences

Read ~/.claude/dependabot-prs.json (if it exists) and look up the current repo's entry:

config="$HOME/.claude/dependabot-prs.json"
repo=$(gh repo view --json nameWithOwner --jq .nameWithOwner)
preferences=""
if [ -f "$config" ]; then
  preferences=$(jq -r --arg repo "$repo" '.[$repo] // empty' "$config")
fi

The file maps owner/repo to freeform instructions, e.g.:

{
  "ryanb/core-gem": "Only handle PRs with the javascript label."
}

If $preferences is non-empty, apply those instructions throughout the rest of the steps — for example, filtering the PR list, narrowing what to merge, or changing the merge strategy.

2. List open Dependabot PRs

Run gh pr list --author "dependabot[bot]" --state open to get all open Dependabot PRs.

If there are no open PRs, tell the user and stop.

3. Review each PR in a sub-agent

For each PR, launch a sub-agent (Agent tool, subagent_type: general-purpose and model: sonnet; run them in parallel) to review it. Each sub-agent should:

  1. Get the PR details: gh pr view <number> --json title,body,url,statusCheckRollup,mergeable
  2. Check if all CI checks passed (all statusCheckRollup entries have conclusion "SUCCESS")
  3. Determine if this is a multi-dependency PR (e.g. a grouped Dependabot update bumping several packages at once). Check the PR title and body — grouped PRs typically list multiple packages.
  4. Read the changelog/release notes in the PR body for anything surprising:
    • Breaking changes or deprecations
    • Dropped support for language/framework versions this codebase uses
    • New behaviors that could cause issues (e.g. new errors being raised)
    • Security fixes worth highlighting
  5. For multi-dependency PRs, check each dependency individually against the codebase:
    • Search the codebase for direct usage of the package (imports, require calls, config references)
    • For each dependency, assess whether the version bump could introduce breaking changes based on the semver increment and release notes
    • Note which dependencies are directly used vs. transitive (less risky)
    • Report each dependency's safety status separately
  6. Return a summary with: PR number and URL, title, CI status (pass/fail) and the build URL Step 4 links it to — detailsUrl for GitHub Actions checks, targetUrl for external ones like Buildkite, whether it's safe to merge, whether it's a multi-dependency PR, per-dependency safety status (for multi-dependency PRs), and any concerns

Read the full file on GitHub · 92 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. 1mo ago First seen · 92 lines · 13 tokens per session scan A f29c1b31ac28

Subscribe to this mod's changes

dependabot-prs is a skill published in the GitHub repository ryanb/dotfiles (2,400 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 1,005 once invoked, about $0.0001 per session on Opus 5.5. 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

pr

Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.

Yeachan-Heo/oh-my-claudecode · 47 tokens

merge-batch

Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.

diegosouzapw/OmniRoute · 46 tokens

otto-pr-review-loop

Run Polly and OCR on a PR until all findings settle.

omnigent-ai/omnigent · 17 tokens

engram-branch-pr

PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.

Gentleman-Programming/engram · 37 tokens

verify-behavior

Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…

nicknisi/dotfiles · 68 tokens

github-contributor

A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.

daymade/claude-code-skills · 105 tokens