Civitai Correctness Review — Development agent for Claude Code
Reviews a feature segment in the main Civitai Next.js app (src/) for safety gaps — authorization scoping, money paths, PII exposure, NSFW/browsing-level gating, and the failure paths around them.
How to install Civitai Correctness Review
Installs to ~/.claude/agents/civitai-civitai-civitai-correctness-review.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/civitai/civitai/HEAD/.claude/agents/civitai-correctness-review.md -o ~/.claude/agents/civitai-civitai-civitai-correctness-review.md Restart Claude Code, or start a new session, for it to be picked up.
What Civitai Correctness Review does
name: civitai-correctness-review description: Reviews a feature segment in the main Civitai Next.js app (src/) for safety gaps — authorization scoping, money paths, PII exposure, NSFW/browsing-level gating, and the failure paths around them. Use before calling a segment done, alongside civitai-reuse-review, civitai-perf-review, civitai-test-review and civitai-intent-review. tools: Read, Grep, Glob, Bash
Safety review — main Civitai app (`src/`)
**Scope is `src/` and the packages it i
Alternatives in Development
- Idor Hunter — IDOR / BOLA specialist (H1 #55, OWASP API1:2023) 812 ★
- Policy Agent — Creates secure Pundit authorization policies with comprehensive RSpec tests and scope restrictions 652 ★
- Operator Core — AUTHORIZATION: All targets are LOCAL LAB/CTF environments 121 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Civitai Intent Review
Scores a feature segment in the main Civitai Next.js app (src/) against the intent doc for the work — did the
Civitai Perf Review
Reviews a feature segment in the main Civitai Next.js app (src/) for production performance — N+1 queries, uni
Adtech Privacy Reviewer
US adtech / web-tracking privacy-litigation pre-implementation reviewer. Specialises in the wave of US class-a
Invest Gate
Returns PASS/FAIL per INVEST letter for a given issue body, with one-line reasoning per criterion. Invoke when
Spgr Agent Feature Flag
Governs every feature flag from definition through staged rollout to mandatory cleanup, and owns the entitleme
Compliance Judge
Truth Tribunal judge — PII, N1-N4b levels, format rules, confidentiality
Related Skills
Multi Agent Protocol
A four-party collaboration protocol for running AI agent teams on real work — auditable authorization, durable
Yotta Security Testing
YuanCe (元测) — disciplined authorization-first security-testing methodology for AI agents: four-stage web secur
Civitai MCP Ultimate
Ultimate MCP server for Civitai API — search models, browse top images with prompts, download LoRAs/Checkpoint