inspector-profile-authoring

inspector-profile-authoring is a skill for Claude Code from tyunta/prefab-sentinel. It costs 57 tokens per session (1,371 once invoked), scanned A, original, MIT.

A Unity workflow for creating or repairing a project-local Inspector profile for a component or data asset. An Inspector profile describes the fields that should be exposed and is checked against the component’s serialized data.

In plain words
What is it for?
Use it to author or repair profiles, validate their structure, and verify that inspecting an object through the profile shows the expected fields.
Why use it?
It helps resolve missing, incomplete, or invalid profile diagnostics using evidence from the actual Unity component and its custom Inspector.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the prefab-sentinel plugin — 6 skills shipped together

Good fit Use it to author or repair profiles, validate their structure, and verify that inspecting an object through the profile shows the expected fields.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tyunta/prefab-sentinel/inspector-profile-authoring
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 tyunta/prefab-sentinel --skill inspector-profile-authoring
Clone the repo
git clone --depth 1 https://github.com/tyunta/prefab-sentinel

Made for: Claude Code.

Or install prefab-sentinel, the plugin that ships this one along with the rest of its 6 skills.

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 inspector-profile-authoring

README.md
[![agentmods](https://agentmods.dev/badge/skills/tyunta/prefab-sentinel/inspector-profile-authoring/github.svg)](https://agentmods.dev/skills/tyunta/prefab-sentinel/inspector-profile-authoring)
Your own site
<a href="https://agentmods.dev/skills/tyunta/prefab-sentinel/inspector-profile-authoring"><img src="https://agentmods.dev/badge/skills/tyunta/prefab-sentinel/inspector-profile-authoring/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 inspector-profile-authoring

Your own site · 80×15
<a href="https://agentmods.dev/skills/tyunta/prefab-sentinel/inspector-profile-authoring"><img src="https://agentmods.dev/badge/skills/tyunta/prefab-sentinel/inspector-profile-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,371 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 $0.00057 $0.01371
Opus 5 $0.00028 $0.00685
Sonnet 5 $0.00011 $0.00274
Haiku 4.5 $0.00006 $0.00137

Measured 9d ago against content hash 9e2702a26fed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

inspector-profile-authoring 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.

skills/inspector-profile-authoring/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Inspector profile authoring

Use this workflow to create or repair an inspector profile for a Unity component or ScriptableObject. It produces only a project-local declarative profile; it does not recreate a custom Inspector, execute profile content, or add a package-specific MCP endpoint.

Canonical inputs

  • Schema: prefab_sentinel/resources/inspector-profile.v1.schema.json
  • Starting template: prefab_sentinel/resources/inspector-profile.template.json
  • Raw authority: inspect_serialized_surface
  • Mechanical validation: validate_inspector_profile
  • Semantic verification: inspect_with_profile

Never copy the schema or template into this skill directory. The package resources are the single canonical definitions.

Trigger conditions

Apply this workflow when a response contains INSPECTOR_PROFILE_REQUIRED, INSPECTOR_PROFILE_INCOMPLETE, INSPECTOR_PROFILE_INVALID, or PROFILE_AUTHORING_REQUIRED. Also apply it when asked to create or repair an inspector profile from component source, a custom Inspector, a SerializedObject surface, or profile-validation diagnostics.

Evidence and confidence

Qualifying semantic evidence comes from runtime component or script source, an active custom Inspector, or an explicit binding. The current serialized surface proves that paths and types are mechanically valid; it does not prove what those fields mean.

High confidence requires complete qualifying semantic evidence and a current serialized surface that validates the mapping.

Source unavailability does not lower a complete active-custom-inspector mapping below high confidence.

Medium confidence requires qualifying semantic evidence that is strong but incomplete or conflicting. Record every unresolved point in the profile and affected view limitations.

Low confidence is reserved for field-name or shape inference when no qualifying semantic evidence is available. Record that inference and its uncertainty in limitations.

Mechanical validation never raises semantic confidence.

Read the full file on GitHub · 66 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. 9d ago First seen · 66 lines · 57 tokens per session scan A 9e2702a26fed

Subscribe to this mod's changes

inspector-profile-authoring is a skill published in the GitHub repository tyunta/prefab-sentinel (11 stars, last pushed 24d ago), licensed MIT. It adds 57 tokens to every session and 1,371 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.