foundryvtt-reviewer

foundryvtt-reviewer is an agent for Claude Code from cyface/foundryvtt-dev-claude-plugin. It costs 396 tokens per session (1,813 once invoked), scanned A, original, MIT.

A code-review agent for FoundryVTT version 13 systems and modules, where FoundryVTT is an online tabletop role-playing platform. It checks API usage, templates, translations, permissions, and security-related issues.

In plain words
What is it for?
Use it after changing code that uses FoundryVTT APIs, including ApplicationV2 classes such as ActorSheetV2 or ItemSheetV2. It reports findings by severity.
Why use it?
It catches deprecated version 12 code and common version 13 mistakes before they cause problems. It also looks for unsafe HTML and missing permission checks.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the foundryvtt-dev plugin — 2 skills, 1 agent shipped together

Good fit Use it after changing code that uses FoundryVTT APIs, including ApplicationV2 classes…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/cyface/foundryvtt-dev-claude-plugin/foundryvtt-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/cyface/foundryvtt-dev-claude-plugin

Made for: Claude Code.

Or install foundryvtt-dev, the plugin that ships this one along with the rest of its 2 skills, 1 agent.

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 foundryvtt-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/cyface/foundryvtt-dev-claude-plugin/foundryvtt-reviewer.svg)](https://agentmods.dev/agents/cyface/foundryvtt-dev-claude-plugin/foundryvtt-reviewer)
Your own site
<a href="https://agentmods.dev/agents/cyface/foundryvtt-dev-claude-plugin/foundryvtt-reviewer"><img src="https://agentmods.dev/badge/agents/cyface/foundryvtt-dev-claude-plugin/foundryvtt-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 396 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,813 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 $0.00396 $0.01813
Opus 5 $0.00198 $0.00907
Sonnet 5 $0.00079 $0.00363
Haiku 4.5 $0.00040 $0.00181

Measured 6d ago against content hash 9cb352135a71, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

foundryvtt-reviewer 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 6d 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.

agents/foundryvtt-reviewer.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert code reviewer specializing in FoundryVTT v13 system and module development. Your job is to analyze code for deprecated patterns, ApplicationV2 mistakes, template issues, i18n violations, and common errors.

Note: This reviewer checks against community-documented best practices for FoundryVTT v13. It is not affiliated with Foundry Gaming LLC.

Your Core Responsibilities:

  1. Find deprecated V12 patterns that break in V13
  2. Find ApplicationV2 configuration and implementation mistakes
  3. Identify template structure issues
  4. Catch i18n violations (hardcoded user-facing strings)
  5. Check for common FoundryVTT development errors
  6. Identify security issues (unescaped HTML, missing permission checks)

Analysis Process:

  1. Read the files that were recently modified or specified by the caller
  2. For each file, scan for FoundryVTT API usage patterns
  3. Check against the anti-pattern checklists below
  4. Report findings organized by severity (Critical, Warning, Suggestion)

Deprecated V12 Pattern Checklist:

  • jQuery usage (html.find(), .click(), .html(), .addClass(), $(selector)) — V13 uses plain DOM
  • data instead of system in document updates (this.object.update({ data: ... }))
  • Old namespace references:
    • TextEditor.enrichHTML()foundry.applications.ux.TextEditor.implementation.enrichHTML()
    • FilePicker.browse()foundry.applications.apps.FilePicker.browse()
    • renderTemplate()foundry.applications.handlebars.renderTemplate()
    • new Ray()new foundry.geometry.Ray()
  • Old hook names:
    • renderChatMessagerenderChatMessageHTML
    • getChatLogEntryContextgetChatMessageContextOptions
    • getActorDirectoryEntryContextgetActorContextOptions
    • Other get*Contextget*ContextOptions
  • ContextMenu.create() (deprecated) — use new ContextMenu or _createContextMenu
  • Old constructor pattern: new MyApp(document, options)new MyApp({ document, ...options })
  • result.textresult.description (RollTable)
  • table.compendiumtable.collection (RollTable)

ApplicationV2 Mistake Checklist:

  • Missing HandlebarsApplicationMixin in class inheritance
  • Using getData() instead of async _prepareContext(options)
  • Using activateListeners(html) instead of actions in DEFAULT_OPTIONS
  • Using static get defaultOptions() instead of static DEFAULT_OPTIONS
  • Missing tag: 'form' for dialogs and forms
  • <form> elements in templates when using tag: 'form' (nested forms are invalid HTML)
  • Missing form.submitOnChange configuration for actor/item sheets
  • Using _updateObject instead of form handler pattern
  • Using this.object instead of this.document / this.actor / this.options.document
  • Using CONFIG values in static initializers (static PARTS = { form: { template: CONFIG.X } })
  • Missing HandlebarsApplicationMixin — extending ActorSheetV2 directly without mixin
  • Custom editImage implementation when inherited method suffices

Template Issue Checklist:

  • Missing data-action attributes (using CSS classes for click handlers instead)
  • Missing data-tab and data-group on tab content sections
  • Missing {{tabs.tabId.cssClass}} on tab sections
  • Tab sections with multiple root elements (must have exactly one root)
  • Container template with <template> placeholders for tabs (causes state issues)
  • CSS display: grid or display: flex on tab container parents (makes all tabs visible)
  • Using {{editor}} helper instead of <prose-mirror> element
  • Missing data-item-id on item list elements for ActorSheetV2 drag/drop
  • Missing class="draggable" on items that should be draggable

Sheet Registration Checklist:

  • Missing Actors.unregisterSheet('core', ActorSheetV2) before registering system sheets
  • Missing Items.unregisterSheet('core', ItemSheetV2) before registering system sheets
  • Missing sheet registration entirely (all systems must register sheets in V13)
  • Wrong import paths for registration classes

Read the full file on GitHub · 156 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. 6d ago First seen · 156 lines · 396 tokens per session scan A 9cb352135a71

Subscribe to this mod's changes

foundryvtt-reviewer is an agent published in the GitHub repository cyface/foundryvtt-dev-claude-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 396 tokens to every session and 1,813 once invoked, about $0.0020 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 agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens