Umbraco.Automate: Skill for Claude Code

.claude/skills/ops-branching/SKILL.md

ops-branching is a skill for Claude Code from umbraco/Umbraco.Automate. It costs 119 tokens per session (2,312 once invoked), scanned A, original, MIT.

A private branch-management workflow for a repository. It starts work branches, opens pull requests, and merges them according to the repository's branch model.

In plain words
What is it for?
Use it to start a correctly based work branch, open a pull request, or merge an existing pull request without needing to know the repository's internal branch names.
Why use it?
It keeps branch bases and merge strategies in one place so different workflows do not make conflicting assumptions about how changes should be integrated.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is umbraco/Umbraco.Automate's own configuration. It tells Claude Code how to work on Umbraco.Automate 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 Umbraco.Automate configures →

Reuse

Borrowing it

Nothing to install: this file belongs to umbraco/Umbraco.Automate. 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/umbraco/Umbraco.Automate/v18/dev/.claude/skills/ops-branching/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/umbraco/Umbraco.Automate

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 ops-branching

README.md
[![agentmods](https://agentmods.dev/badge/skills/umbraco/umbraco.automate/ops-branching/github.svg)](https://agentmods.dev/skills/umbraco/umbraco.automate/ops-branching)
Your own site
<a href="https://agentmods.dev/skills/umbraco/umbraco.automate/ops-branching"><img src="https://agentmods.dev/badge/skills/umbraco/umbraco.automate/ops-branching/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 ops-branching

Your own site · 80×15
<a href="https://agentmods.dev/skills/umbraco/umbraco.automate/ops-branching"><img src="https://agentmods.dev/badge/skills/umbraco/umbraco.automate/ops-branching.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,312 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 $0.00119 $0.02312
Opus 5 $0.00060 $0.01156
Sonnet 5 $0.00024 $0.00462
Haiku 4.5 $0.00012 $0.00231

Measured 10d ago against content hash 5ce9c2faf47e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ops-branching 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 10d 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/ops-branching/SKILL.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ops-branching

The repo's branch model lives here and nowhere else. Before this capability existed, base-branch knowledge lived in four places — a config schema, a detection skill, the merge loop's own resolve-and-compare, and a forge operation that deferred back to the detection skill. They drifted. Collapsing them into one owner is the point of this skill.

Visibility: supporting primitive. A service (ops-integrate, ops-release, ops-change) may call it. A framework loop must never call it directly — if a loop holds a branch name, this capability has failed.

The privacy rule

The integration branches, the release base and the merge strategy never leave this skill. There is no resolve-base, no merge-strategy, and no classify-pr. A caller says "merge this PR" and reads back what happened; it does not ask "what is the base?" and then compare.

Why it is worth the inconvenience: the moment a caller can read the base, two callers can disagree about it, and the drift is back. An outcome cannot drift.

Command-only. Every action below does something. This skill answers no questions.

Invocation

ops-branching <action> '<context-json>'
Action Context Returns
merge { pr } { ok, merged, merge_commit, refused, line }
open-pr { branch, line, title, body } { ok, pr_number, url }
start-branch { line, slug } { ok, branch }

An absent context is {}. Reject any other action — do not guess. All three are idempotent: see each action.

All GitHub work goes through github-ops by operation name. This skill decides what and onto what; github-ops owns how.

What it knows, privately

Resolve these once per invocation, and never return them:

  1. The live lines — from ops-repo-meta · lines. Read it every time; never cache it. A major-version cutover adds a line, and no engine change may be needed for that.
  2. The branch model is fixed: versioned-gitflow. Do not detect it, and do not improvise if a branch is missing — a live line that has no vN/dev and vN/main pair is a configuration error to report, not a gap to guess around. See CONTRIBUTING.md for the full branch model.
  3. The integration branches — a SET, not a branch. vN/dev, one per live line. Every base check is set membership. With v18 and v17 live there are two legitimate bases, and equality against one of them would flag the other as wrong-base.
  4. The release basesvN/main, one per live line.
  5. The merge strategy — merge-commit, always. This is where this repo departs from the engine default, which squashes normal PRs. Do not squash anything:

Read the full file on GitHub · 169 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. 10d ago First seen · 169 lines · 119 tokens per session scan A 5ce9c2faf47e

Subscribe to this mod's changes

ops-branching is a skill published in the GitHub repository umbraco/Umbraco.Automate (5 stars, last pushed 2d ago), licensed MIT. It adds 119 tokens to every session and 2,312 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.

Related

Other skills, from other repositories

prowler-commit

Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.

prowler-cloud/prowler · 33 tokens

gh-auth-isolation

Safely manage multiple GitHub identities (EMU + personal) in agent workflows.

github/gh-aw · 20 tokens

comet-github

A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.

rpamis/comet · 72 tokens

github-skill

Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.

zeenie-ai/OpenCompany · 51 tokens

re0-merge

Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…

LilMGenius/paperthin · 70 tokens

nvca-chart-release

Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.

NVIDIA/nvcf · 61 tokens