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 skills add Logiiiii/unity-agent-skills --skill jahro-migrationgit clone --depth 1 https://github.com/Logiiiii/unity-agent-skillsWrote 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/skills/logiiiii/unity-agent-skills/jahro-migration)<a href="https://agentmods.dev/skills/logiiiii/unity-agent-skills/jahro-migration"><img src="https://agentmods.dev/badge/skills/logiiiii/unity-agent-skills/jahro-migration/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.
<a href="https://agentmods.dev/skills/logiiiii/unity-agent-skills/jahro-migration"><img src="https://agentmods.dev/badge/skills/logiiiii/unity-agent-skills/jahro-migration.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00074 | $0.02570 |
| Opus 5 | $0.00037 | $0.01285 |
| Sonnet 5 | $0.00015 | $0.00514 |
| Haiku 4.5 | $0.00007 | $0.00257 |
Grade A, and why
jahro-migration 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 9d 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.
This is a copy
100% identical to jahro-migration — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jahro Migration
Help users migrate from custom debug tools to Jahro. Analyze existing code, classify what to replace/keep/adapt, and generate migrated code incrementally.
Migration Decision Guide
When the user shares their existing debug code, classify each component:
| What are you migrating? | Jahro Replacement | Action |
|---|---|---|
IMGUI debug buttons (OnGUI + GUI.Button) |
[JahroCommand] + Visual Mode |
Replace — Visual Mode provides a better button UI |
| Canvas-based debug UI | [JahroCommand] + Visual Mode |
Replace — eliminates UI maintenance |
| Custom command parser (string → command) | [JahroCommand] + Text Mode |
Replace — Jahro handles parsing and type conversion |
| Cheat code system (dictionary/registry) | [JahroCommand] with groups |
Replace — typed parameters, auto-discovery |
| Custom Debug.Log wrapper | Remove or keep | Jahro intercepts Debug.Log automatically — wrapper often unnecessary |
| Performance HUD (FPS, memory overlay) | [JahroWatch] groups |
Replace — Watcher provides organized monitoring |
| File-based logger | Keep | Jahro doesn't write to files — keep if file logging is needed |
| Custom Inspector/Editor tools | Evaluate | May complement Jahro — keep if Editor-only tools |
| Analytics-based logging | Keep | Different purpose — Jahro is for debugging, not analytics |
Migration Workflow
- User shares existing debug code — ask to see the files or point to the classes
- Classify each component using the decision guide above
- Generate a migration plan: what to replace, what to keep, what to adapt, effort estimate
- Generate migrated code — file by file, side by side with original
- Support incremental migration — old and new can coexist
- VERIFY at each step — "Enter Play Mode, confirm migrated commands appear in Jahro"
Pattern: IMGUI Debug Menu → Jahro Commands
Before (IMGUI)
public class DebugMenu : MonoBehaviour
{
private bool showMenu;
void OnGUI()
{
if (GUI.Button(new Rect(10, 10, 100, 30), "Toggle"))
showMenu = !showMenu;
if (!showMenu) return;
if (GUI.Button(new Rect(10, 50, 150, 30), "God Mode"))
Player.GodMode = true;
if (GUI.Button(new Rect(10, 90, 150, 30), "Add 1000 Gold"))
Player.Gold += 1000;
if (GUI.Button(new Rect(10, 130, 150, 30), "Skip Level"))
LevelManager.SkipToNext();
GUI.Label(new Rect(10, 170, 200, 30), $"FPS: {1f/Time.deltaTime:F0}");
GUI.Label(new Rect(10, 200, 200, 30), $"Health: {Player.Health}");
}
}
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.
- 9d ago First seen · 279 lines · 74 tokens per session scan A f76c270d0a34
jahro-migration is a skill published in the GitHub repository Logiiiii/unity-agent-skills (3 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 2,570 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to jahro-migration, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
php-quality-tooling
Use when setting up PHPStan, Rector, or PHP-CS-Fixer on a non-Laravel PHP project, incl. CI wiring. Do NOT use for Laravel (Pint/Larastan), tests, or syntax.
think-in-code
Use when analyzing multiple files, auditing a codebase, scanning dependencies, or counting lines -- one Bash pipeline beats N sequential Read calls.
idea-sprint
Find and validate what to build in crypto. Use when the user asks "what should I build", "validate this idea", "is this worth building", "find me a startup idea", "crypto idea", or wants blunt feedback on a project concept before writing code.
pitch-deck
Build a pitch deck for a crypto project. Use when the user says "pitch deck", "demo day", "investor presentation", "grant application slides", "accelerator application", "help me pitch", or needs slides for a hackathon final.
hackathon
Prepare a winning hackathon submission. Use when the user says "hackathon submission", "submit to hackathon", "demo script", "demo video", "which track should I enter", "Colosseum", "help me win the hackathon", or asks about hackathon grants and Superteam Earn.
breaking-changes
Use when checking whether a Claude Code update breaks our plugin ecosystem — hooks, agent frontmatter, manifest schema, or skill format.