Moderation Auditor — Security agent for Claude Code
Runs the full Yandex moderation audit on ONE game build (debugcheck static checks + runtime probes A-G + validators) and returns a structured report.
How to install Moderation Auditor
Installs to ~/.claude/agents/nioris-project-forge-moderation-auditor.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Nioris/project-forge/HEAD/.claude/agents/moderation-auditor.md -o ~/.claude/agents/nioris-project-forge-moderation-auditor.md Restart Claude Code, or start a new session, for it to be picked up.
What Moderation Auditor does
name: moderation-auditor description: Runs the full Yandex moderation audit on ONE game build (debugcheck static checks + runtime probes A-G + validators) and returns a structured report. READ-ONLY — never edits game files. Use for pre-submission audits, and spawn several in parallel to audit multiple games at once. Also valid as an Agent Team teammate. model: sonnet tools: Read, Bash, Grep, Glob contract: moderation-auditor
Moderation Auditor — аудит одной игры перед подачей в Яндекс
Alternatives in Security
- Dr Audit — Sub-agent prompt: audit Decision Records in an implementation-plan.md for canonical form and reference resolut 432 ★
- Runtime Bug Audit — Find runtime bugs and error handling issues 80 ★
- Scope Audit — SCOPE audit orchestrator — single entry point for the full audit pipeline 54 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
God Security Auditor
Adversarial security reviewer. Walks the OWASP Top 10 against the real code paths, probes where it can, checks
Audit Learning Agent
Analyzes past audit logs, detects patterns, and returns a structured retro for the orchestrator to write. Read
Seraph
Static security audit of a repo's code and config (exposed secrets, missing authorisation, injection surfaces,
Keymaker
One-off technical SEO audit of a live page or site (meta, semantics, Core Web Vitals, structured data, sitemap
Cavet Security
Runs a cavet security scan for the given scope and phase, triages every finding, and returns the CLI's structu
Ferrox A11y Auditor
Post-change WCAG 2.1 AA audit of implemented frontend surfaces. Static rules with file:line evidence plus an o
Related Skills
Web Clone
Methodology + executable probes for faithfully cloning any website (static / React / WebGL / WordPress) — real
Toolward
Security auditor for AI agent extensions — MCP servers, skills, plugins, connectors. Finds prompt injection, t
Universal Debug Mode Skill
Evidence-driven debugging skill for AI agents: generate competing hypotheses, instrument with isolated runtime