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.
npx agentmods add commands/thearcforge/uniclaude/adopt-skillsgit clone --depth 1 https://github.com/TheArcForge/UniClaudeWrote 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.
[](https://agentmods.dev/commands/thearcforge/uniclaude/adopt-skills)<a href="https://agentmods.dev/commands/thearcforge/uniclaude/adopt-skills"><img src="https://agentmods.dev/badge/commands/thearcforge/uniclaude/adopt-skills.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00016 | $0.01863 |
| Opus 5 | $0.00008 | $0.00932 |
| Sonnet 5 | $0.00003 | $0.00373 |
| Haiku 4.5 | $0.00002 | $0.00186 |
Grade A, and why
adopt-skills 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are helping the user adopt UniClaude's Unity development rules into their CLAUDE.md configuration.
UniClaude Unity Skills
Below is the Unity guidance that ships with UniClaude. This is the content to be adopted:
These rules apply when working in a Unity project with UniClaude installed.
Unity Rules
- Threading: Unity API calls must happen on the main thread. Never use
Task.Run(),ThreadPool, or background threads for Unity API calls. - Serialization: Use
[SerializeField]for private fields. Add[System.Serializable]to nested classes/structs. Properties are never serialized.publicfields serialize by default — prefer[SerializeField] privateinstead. - Domain Reload: Static fields reset when scripts recompile. Use
[InitializeOnLoad]or[InitializeOnEnterPlayMode]to re-initialize. UseSessionState(session-scoped) orEditorPrefs(persistent) for Editor state that must survive reloads. - Lifecycle: Execution order is
Awake->OnEnable->Start. Do not assumeStarthas run insideOnEnable. Clean up subscriptions and resources inOnDisable/OnDestroy. - Unity Null: Unity overloads
== nullfor destroyed objects. Never useis nulloris not null— these bypass the overload and return incorrect results for destroyed objects. - Editor vs Runtime: Editor-only code must be in an
Editor/assembly definition or guarded with#if UNITY_EDITOR. Never referenceUnityEditornamespace from runtime assemblies. - Assembly Definitions: Required for packages. They control compilation order and reference visibility. Editor-only asmdefs must have platform set to Editor only.
MCP Tool Priority
Before modifying any Unity asset, scene, prefab, or component through file edits, check if a UniClaude MCP tool can do it directly. MCP tools handle undo registration, correct serialization, and domain reload batching — file edits do not.
If you need a Unity Editor action and are not sure which tool handles it, describe what you need and ask the user — do not guess with file edits.
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.
- 5d ago First seen · 168 lines · 16 tokens per session scan A 012c2a95fdd9
adopt-skills is a command published in the GitHub repository TheArcForge/UniClaude (51 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 1,863 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
test-suite
Run comprehensive test suite with coverage analysis.
pull-repos
Pull all repos (parent + marketplace clones + configured project repos).
security-scan
Run security audit on codebase.
assemble-team
Assemble a pre-built agent team for parallel work - review, feature, debug, cross-platform, full-stack, or research.
run
Execute prompt(s) from ./prompts/ with automatic archiving - for structured prompt-based work.
standardize-claude-md
Add missing toolkit sections (Related Global Rules, Quick Start) to existing CLAUDE.md.