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 jahro-console/unity-agent-skills --skill jahro-watchergit clone --depth 1 https://github.com/jahro-console/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/jahro-console/unity-agent-skills/jahro-watcher)<a href="https://agentmods.dev/skills/jahro-console/unity-agent-skills/jahro-watcher"><img src="https://agentmods.dev/badge/skills/jahro-console/unity-agent-skills/jahro-watcher/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/jahro-console/unity-agent-skills/jahro-watcher"><img src="https://agentmods.dev/badge/skills/jahro-console/unity-agent-skills/jahro-watcher.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 | $0.00065 | $0.01855 |
| Opus 5 | $0.00032 | $0.00928 |
| Sonnet 5 | $0.00013 | $0.00371 |
| Haiku 4.5 | $0.00006 | $0.00186 |
Grade A, and why
jahro-watcher 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- jahro-watcher — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jahro Watcher
Help users monitor game variables in real-time using Jahro's [JahroWatch] attribute system.
Workflow
- Analyze the user's code — identify fields/properties worth monitoring
- Generate correct
[JahroWatch]attributes - Add registration if needed (instance members require
RegisterObject) - VERIFY — "Enter Play Mode, open the Watcher tab, confirm values update"
Analyzing Code for Watcher Candidates
When the user shares a class, identify members worth monitoring:
Good candidates:
- Game state fields: health, score, level, currency, inventory counts
- Physics values: velocity, position, rotation (especially via properties wrapping Rigidbody)
- Performance metrics: FPS, memory, draw calls
- Enum state fields: game state, player state, AI state
- Key counters: enemy count, player count, item count
Skip these:
- Constants and readonly compile-time values
- Private implementation details that change every frame with no debugging value
- References to other objects (Transform, GameObject) — watch their properties instead
- Collections and dictionaries (arrays are supported, but dictionaries are not)
Suggest replacing Debug.Log polling:
If the user has Debug.Log($"Health: {health}") in Update(), recommend [JahroWatch] instead — it eliminates log spam and provides a clean real-time dashboard.
Attribute Syntax
[JahroWatch("Display Name", "GroupName", "Description for detail modal")]
Constructor: [JahroWatch(string name, string group, string description)]
All parameters are optional. Defaults: name = member name (leading _ stripped), group = "Default", description = "".
Complete example
using JahroConsole;
using UnityEngine;
public class PlayerController : MonoBehaviour
{
[JahroWatch("Health", "Player", "Current hit points")]
public float health = 100f;
[JahroWatch("Stamina", "Player", "Current stamina")]
public float stamina = 50f;
[JahroWatch("Position", "Player", "World position")]
public Vector3 Position => transform.position;
[JahroWatch("Velocity", "Player", "Movement velocity")]
public Vector3 Velocity => GetComponent<Rigidbody>().velocity;
[JahroWatch("Is Grounded", "Player", "Touching ground")]
public bool isGrounded;
void OnEnable() => Jahro.RegisterObject(this);
void OnDisable() => Jahro.UnregisterObject(this);
}
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.
- 10d ago First seen · 223 lines · 65 tokens per session scan A 24167383e3c1
jahro-watcher is a skill published in the GitHub repository jahro-console/unity-agent-skills (16 stars, last pushed 5mo ago), licensed MIT. It adds 65 tokens to every session and 1,855 once invoked, about $0.0003 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 skills, from other repositories
ui-click-debug
A Unity troubleshooting skill for UI elements that do not respond to clicks. It uses a runtime raycast, a test that shows which object receives a pointer event, to find obstructions or interaction settings.
error-diagnosis
A Unity troubleshooting skill for errors shown in the Unity Console, the editor window that displays messages and failures. It reads the error and nearby logs, then checks related code to identify the cause.
console-get-logs
Retrieve Unity Editor logs from the MCP plugin's LogCollector, optionally filtered by log type or time window. Useful for debugging and monitoring Editor activity.
editor-application-get-state
Return the current state of UnityEditor.EditorApplication — playmode, paused state, compilation state, and related flags.
console-clear-logs
Clear the MCP log cache (used by 'console-get-logs') and the Unity Editor Console window. Useful for isolating logs to a specific action by clearing the slate first.
profiler-start
Enable Unity's runtime profiler and open the Profiler window. Idempotent: calling when already enabled returns the current enabled state without error.