unity-executing-plans

unity-executing-plans is a skill for Claude Code from sonereraslan/local-marketplace. It costs 98 tokens per session (1,479 once invoked), scanned A, original, MIT.

A step-by-step workflow for carrying out implementation plans in Unity, a game-development environment. It groups work into batches, checks compilation and tests, and saves changed Unity assets.

In plain words
What is it for?
Use it to implement a Unity feature plan in small batches, verify each logical code change, run tests, save scenes and other assets, and prepare the completed work for branch finishing.
Why use it?
It helps prevent long runs of unverified changes in projects where code compilation and the Unity Editor can take time or reload unexpectedly. It also adds review points so concerns can be addressed before more work continues.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

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

Good fit Use it to implement a Unity feature plan in small batches, verify each logical code change, run tests, save scenes and other assets, and prepare the completed work for branch finishing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sonereraslan/local-marketplace/unity-executing-plans
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 sonereraslan/local-marketplace --skill unity-executing-plans
Clone the repo
git clone --depth 1 https://github.com/sonereraslan/local-marketplace

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-executing-plans

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sonereraslan/local-marketplace/unity-executing-plans"><img src="https://agentmods.dev/badge/skills/sonereraslan/local-marketplace/unity-executing-plans.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,479 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 $0.00098 $0.01479
Opus 5 $0.00049 $0.00740
Sonnet 5 $0.00020 $0.00296
Haiku 4.5 $0.00010 $0.00148

Measured 10d ago against content hash e56a1c1fe078, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

unity-executing-plans 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.

plugins/superunity/skills/unity-executing-plans/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Executing Unity Plans

Overview

Load plan, review critically, execute tasks in batches, report for review between batches. Unity projects have compile cycles and Editor reloads — account for these in pacing. Ensure all modified Assets (Scenes, Prefabs, ScriptableObjects) are explicitly saved to disk before reporting.

Core principle: Batch execution with checkpoints for architect review. Verify compilation after every logical code unit.

Announce at start: "Using the unity-executing-plans skill to implement this plan."

Execution Flow

  1. Confirm a dedicated feature branch exists (never execute on main/master)
  2. Load and review plan — raise concerns if any
  3. If concerns, discuss with user before proceeding
  4. Execute batch (3-5 tasks depending on complexity)
  5. Verify compilation + run tests
  6. Report results to user
  7. Wait for user feedback — apply changes if needed
  8. If more tasks remain, repeat from step 4
  9. When all tasks complete, invoke superunity:unity-finishing-branch

Step 1: Load and Review Plan

  1. Prerequisite: Confirm a dedicated feature branch exists. If on main/master, stop and create or switch to a feature branch before proceeding.
  2. Read plan file from docs/plans/
  3. Review critically — identify questions or concerns:
    • Are file paths valid for this project's structure?
    • Do referenced packages exist in Packages/manifest.json?
    • Are assembly definitions set up for test folders?
    • Does the plan match the project's existing patterns?
  4. If concerns: Raise them with user before starting
  5. If no concerns: Create task list and proceed

Step 2: Execute Batch

Default: 3-5 tasks depending on complexity

For each task:

  1. Mark as in_progress
  2. Follow each step exactly (plan has bite-sized steps)
  3. After a logical code unit is completed (not necessarily every single line change), wait for Unity to recompile and verify no errors
  4. Run verifications as specified (EditMode/PlayMode tests)
  5. Stage files as you go — confirm .meta files are included in staged changes. Do NOT commit per task; commit once when the feature is complete.
  6. If the feature affects runtime systems (Update loops, physics, spawning, UI refresh), briefly validate in Play Mode and check:
    • No excessive GC allocations
    • No unexpected spikes in Profiler
    • No error spam in Console during runtime
  7. If Prefabs or Scenes were modified:
    • Confirm no unintended overrides
    • Ensure scene is saved intentionally
    • Verify no missing serialized references
  8. Mark as completed

Read the full file on GitHub · 157 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 · 157 lines · 98 tokens per session scan A e56a1c1fe078

Subscribe to this mod's changes

unity-executing-plans is a skill published in the GitHub repository sonereraslan/local-marketplace (2 stars, last pushed 4mo ago), licensed MIT. It adds 98 tokens to every session and 1,479 once invoked, about $0.0005 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