unity-finishing-branch

unity-finishing-branch is a skill for Claude Code from sonereraslan/local-marketplace. It costs 125 tokens per session (1,732 once invoked), scanned A, original, MIT.

A checklist for completing a Unity development branch before merging it or creating a pull request. Unity is a game-development engine, so the checks include its scenes, prefabs, builds, tests, and editor state.

In plain words
What is it for?
Use it when finishing a Unity feature branch to run verification, resolve failures, choose a merge or pull-request path, and clean up the branch.
Why use it?
It verifies that the branch is ready to integrate and catches Unity-specific problems that ordinary code checks may overlook.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the superunity plugin — 11 skills, 1 command, 4 agents, 2 hooks shipped together

Good fit Use it when finishing a Unity feature branch to run verification, resolve failures, choose a merge or pull-request path, and clean up the branch.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add sonereraslan/local-marketplace
Claude Code
/plugin install superunity

Made for: Claude Code.

Or install superunity, the plugin that ships this one along with the rest of its 11 skills, 1 command, 4 agents, 2 hooks.

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 unity-finishing-branch

README.md
[![agentmods](https://agentmods.dev/badge/skills/sonereraslan/local-marketplace/unity-finishing-branch/github.svg)](https://agentmods.dev/skills/sonereraslan/local-marketplace/unity-finishing-branch)
Your own site
<a href="https://agentmods.dev/skills/sonereraslan/local-marketplace/unity-finishing-branch"><img src="https://agentmods.dev/badge/skills/sonereraslan/local-marketplace/unity-finishing-branch/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 unity-finishing-branch

Your own site · 80×15
<a href="https://agentmods.dev/skills/sonereraslan/local-marketplace/unity-finishing-branch"><img src="https://agentmods.dev/badge/skills/sonereraslan/local-marketplace/unity-finishing-branch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,732 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 $0.00125 $0.01732
Opus 5 $0.00063 $0.00866
Sonnet 5 $0.00025 $0.00346
Haiku 4.5 $0.00013 $0.00173

Measured 12d ago against content hash 1b182d3cb1c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

unity-finishing-branch 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.

plugins/superunity/skills/unity-finishing-branch/SKILL.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Finishing a Development Branch (Unity)

Overview

Guide completion of Unity development work through full verification, then present clear integration options.

Core principle: Verify everything → Present options → Execute choice → Clean up.

Announce at start: "Using superunity:unity-finishing-branch to complete this work."

The Process

Step 1: Run Full Unity Verification

Before presenting any options, complete the full superunity:unity-verification checklist.

This is not optional. The checklist covers compile, test runner (EditMode + PlayMode), determinism, Console clean, domain reload, static leak control, serialized field migration, scene/Prefab integrity, performance sanity, build verification, API contract, regression surface, and requirements.

If verification was run earlier in this session, it must be re-run on the current HEAD commit. Do not rely on earlier results. Any commit since the last run could have introduced a regression.

If any verification step fails:

Verification failed at Step [N]: [description of failure]

[Show evidence — test output, Console error, or failing requirement]

Cannot proceed with merge or PR until resolved.
Use superunity:unity-systematic-debugging to investigate.

Stop. Do not proceed to Step 2.

If all verification steps pass: Continue to Step 2.

Step 2: Unity Pre-Merge Checklist

Run these final checks before presenting integration options:

  • All .meta files committed alongside every new file and folder
  • No Debug.Log statements left in committed production code
  • No compile warnings from new code left unexplained
  • No [Ignore] attributes on tests
  • No unintended changes in ProjectSettings/ (especially Input, Tags & Layers, Physics)
  • No Library/, Temp/, or Obj/ files staged
  • Branch is ahead of base — no divergence that would cause unexpected conflicts
  • Confirm working on feature branch — not on main or master
git status              # confirm clean working tree — check for Library/Temp/Obj
git diff --name-only HEAD origin/<base>  # confirm no unintended ProjectSettings changes
git log --oneline -5    # confirm commit history looks correct
git branch              # confirm not on main/master

Read the full file on GitHub · 206 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 206 lines · 125 tokens per session scan A 1b182d3cb1c4

Subscribe to this mod's changes

unity-finishing-branch is a skill published in the GitHub repository sonereraslan/local-marketplace (2 stars, last pushed 4mo ago), licensed MIT. It adds 125 tokens to every session and 1,732 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

build-game-changelog

Design, implement, backfill, audit, and release in-game changelogs with contiguous versioning, deployment provenance, menu-state navigation, accessible toggle, close, and Escape behavior, and responsive release-ledger UI. Use when Codex needs to add or revise a changelog or version screen in a game, reconstruct…

MengTo/Skills · 100 tokens

writing-modpack-changelog

Use when cutting a modpack release. Creates /docs/release-changelog.md if absent; appends a new version section with grouped changes. Triggers - 'cut a release', 'release notes', 'changelog', 'v1.2.3 changes', 'what changed since last version'.

hashgraph-online/awesome-codex-plugins · 69 tokens

release

Automate Godot MCP Native plugin and CLI release. Bumps versions, runs tests, builds packages, creates GitHub Release draft.

yurineko73/Godot-MCP-Native · 29 tokens

Install PuerTS for Unity

Guide for downloading and installing PuerTS UPM packages into a Unity project — covers version selection, package dependencies, download/extract and git URL installation methods, and Editor Assistant setup.

Tencent/puerts · 44 tokens

releasing-godot-prompter

Use when cutting a GodotPrompter release or bumping its version — the version-bump sequence, tag-triggered workflow, and the marketplace manifests that must follow.

jame581/GodotPrompter · 44 tokens

flame-harness-build

Phase 8 — bootstrap signing credentials, generate fastlane config from templates, and build + upload signed IPA (TestFlight) and AAB (internal track).

tjdrhs90/flutter-flame-harness · 38 tokens