agents-at-scale-ark: Skill for Claude Code

.claude/skills/ark-dependabot-management/SKILL.md

ark-dependabot-management is a skill for Claude Code from mckinsey/agents-at-scale-ark. It costs 52 tokens per session (1,300 once invoked), scanned A, original, Apache-2.0.

A Git workflow for combining multiple Dependabot dependency-update pull requests into one integration branch and pull request.

In plain words
What is it for?
It is for checking stale Dependabot configuration, merging update branches, testing them together, and preparing one combined change.
Why use it?
It reduces repeated review and CI runs when many automated dependency updates arrive together.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is mckinsey/agents-at-scale-ark's own configuration. It tells Claude Code how to work on agents-at-scale-ark 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 agents-at-scale-ark configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mckinsey/agents-at-scale-ark. 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/mckinsey/agents-at-scale-ark/main/.claude/skills/ark-dependabot-management/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mckinsey/agents-at-scale-ark

Made for: Claude Code.

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 ark-dependabot-management

README.md
[![agentmods](https://agentmods.dev/badge/skills/mckinsey/agents-at-scale-ark/ark-dependabot-management/github.svg)](https://agentmods.dev/skills/mckinsey/agents-at-scale-ark/ark-dependabot-management)
Your own site
<a href="https://agentmods.dev/skills/mckinsey/agents-at-scale-ark/ark-dependabot-management"><img src="https://agentmods.dev/badge/skills/mckinsey/agents-at-scale-ark/ark-dependabot-management/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 ark-dependabot-management

Your own site · 80×15
<a href="https://agentmods.dev/skills/mckinsey/agents-at-scale-ark/ark-dependabot-management"><img src="https://agentmods.dev/badge/skills/mckinsey/agents-at-scale-ark/ark-dependabot-management.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,300 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 $0.00052 $0.01300
Opus 5 $0.00026 $0.00650
Sonnet 5 $0.00010 $0.00260
Haiku 4.5 $0.00005 $0.00130

Measured 8d ago against content hash d5ba7a5588f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ark-dependabot-management 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 8d 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/ark-dependabot-management/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ark Dependabot Management

Consolidate open Dependabot PRs into a single integration branch for unified review and merge.

Strategy

All open Dependabot PRs get merged into a single integration/dependabot branch which has one PR into main. This avoids CI churn from merging individual dependency bumps.

Pre-flight: Check for stale config

Before consolidating, verify all directories in .github/dependabot.yaml still exist:

yq '.updates[].directory // .updates[].directories[]' .github/dependabot.yaml | while read dir; do
  [ ! -d "$dir" ] && echo "STALE: $dir"
done

Remove stale entries before proceeding — they cause Dependabot workflow errors.

Consolidate Pull Requests

Preferred approach: Git merge

The fastest method is to merge each dependabot branch directly into a fix branch:

git checkout -b fix/build-consolidation origin/main

# For each dependabot PR branch:
git fetch origin <dependabot-branch>
git merge --no-edit origin/<dependabot-branch>

This is simpler than the GitHub API approach below, avoids needing --admin permissions, and lets you test all updates together locally before pushing.

Alternative approach: GitHub API

Use the API method when you need to keep individual PRs open for tracking, or when merging into the integration/dependabot branch.

Step 1: List open Dependabot PRs

gh pr list --repo mckinsey/agents-at-scale-ark --state open --author "app/dependabot" \
  --json number,title,headRefName --jq '.[] | "\(.number)\t\(.title)"'

Step 2: Check for existing integration branch and PR

EXISTING_PR=$(gh pr list --repo mckinsey/agents-at-scale-ark --state open \
  --head integration/dependabot --json number --jq '.[0].number // empty')

if [ -n "$EXISTING_PR" ]; then
  echo "Existing open PR: #${EXISTING_PR}"
fi

If no open PR exists, check if the branch exists and if there's a merged PR to reopen from:

BRANCH_EXISTS=$(gh api repos/mckinsey/agents-at-scale-ark/git/ref/heads/integration/dependabot \
  --jq '.object.sha' 2>/dev/null || echo "")

MERGED_PR=$(gh pr list --repo mckinsey/agents-at-scale-ark --state merged \
  --head integration/dependabot --json number --jq '.[0].number // empty')

Read the full file on GitHub · 158 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. 8d ago First seen · 158 lines · 52 tokens per session scan A d5ba7a5588f1

Subscribe to this mod's changes

ark-dependabot-management is a skill published in the GitHub repository mckinsey/agents-at-scale-ark (422 stars, last pushed 2d ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,300 once invoked, about $0.0003 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 2026-09-03.