enable-renovate-automerge

enable-renovate-automerge is a skill for Claude Code, Codex from Netcracker/qubership-ai-packages. It costs 69 tokens per session (1,499 once invoked), scanned A, original, Apache-2.0.

A setup guide for Renovate, a tool that opens dependency-update pull requests, to merge them automatically after the right GitHub checks pass.

In plain words
What is it for?
Use it to configure Renovate automerge, choose the exact required GitHub checks, and combine several test jobs into one required CI check.
Why use it?
It prevents automatic merges from relying on weak checks that do not run the real tests or style checks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to configure Renovate automerge, choose the exact required GitHub checks, and combine several test jobs into one required CI check.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/netcracker/qubership-ai-packages/enable-renovate-automerge
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 Netcracker/qubership-ai-packages --skill enable-renovate-automerge
Clone the repo
git clone --depth 1 https://github.com/Netcracker/qubership-ai-packages

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin enable-renovate-automerge/plugin install enable-renovate-automerge 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 enable-renovate-automerge

README.md
[![agentmods](https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/enable-renovate-automerge/github.svg)](https://agentmods.dev/skills/netcracker/qubership-ai-packages/enable-renovate-automerge)
Your own site
<a href="https://agentmods.dev/skills/netcracker/qubership-ai-packages/enable-renovate-automerge"><img src="https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/enable-renovate-automerge/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 enable-renovate-automerge

Your own site · 80×15
<a href="https://agentmods.dev/skills/netcracker/qubership-ai-packages/enable-renovate-automerge"><img src="https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/enable-renovate-automerge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,499 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.
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 $0.00069 $0.01499
Opus 5 $0.00034 $0.00749
Sonnet 5 $0.00014 $0.00300
Haiku 4.5 $0.00007 $0.00150

Measured 12d ago against content hash a1285379ee44, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

enable-renovate-automerge 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 12d 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.

agent-packages/enable-renovate-automerge/.apm/skills/enable-renovate-automerge/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Enable Renovate automerge

Turn on Renovate automerge for a repository so dependency PRs merge themselves once CI is green — without lowering the bar for what "green" means.

Automerge is only as safe as the checks that gate it. The work here is mostly about the gate: making sure a green PR means real tests and style checks ran and passed, and registering exactly those checks as required. Flipping automerge: true is the last and smallest step.

Apply this whether you configure one repository or sweep several: run the steps per repository.

Policy (read first)

  • Automerge only behind a real gate. A green merge must mean tests (and style, where present) actually ran and passed. Never enable it where the only required checks are a PR-title linter, Conventional Commits, or a Docker-build smoke test.
  • Renovate only. Dependabot has no platform-side automerge, so it is out of scope here; note it and move on, or treat migration to Renovate as separate work.
  • Verify check names, don't guess them. A required status check matches the check-run name GitHub reports exactly, and reusable workflows report a compound <caller-job> / <inner-job> name.

Step 1. Confirm the prerequisites

  • Bot is Renovate. Look for renovate.json, .github/renovate.json, or a renovate key in package.json. If the repository runs Dependabot (.github/dependabot.yml) instead, stop and report it as out of scope.

  • You have admin. Editing rulesets and repository settings needs it:

    gh api repos/<owner>/<repo> --jq .permissions
    

    Without admin, prepare the changes as a PR plus a written ruleset instruction for the org owner instead of applying them.

  • A real PR-triggered check exists. List the workflows that run on pull_request and find the jobs that run actual tests or style checks — not title validation, not a bare Docker build. If none exist, there is nothing to gate on: stop and report it. Creating a test workflow is separate work, out of scope here.

Read the full file on GitHub · 164 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. 12d ago First seen · 164 lines · 69 tokens per session scan A a1285379ee44

Subscribe to this mod's changes

enable-renovate-automerge is a skill published in the GitHub repository Netcracker/qubership-ai-packages (4 stars, last pushed 3d ago), licensed Apache-2.0. It adds 69 tokens to every session and 1,499 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 2026-08-31.