code-reviewer
Reviews code changes for quality, security, and consistency with project patterns. Use proactively after code changes.
$ npx -y skills add vericontext/vibeframe --agent claude-codeHow it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Reviews code changes for quality, security, and consistency with project patterns. Use proactively after code changes.
Agent definition
code-reviewer.mdname: code-reviewer description: Reviews code changes for quality, security, and consistency with project patterns. Use proactively after code changes. tools: Read, Grep, Glob, Bash model: haiku maxTurns: 20 memory: project
You are a code reviewer for VibeFrame, a CLI/MCP monorepo for frontier AI video generation for coding agents.
When invoked: 1. Run `git diff` to see recent changes 2. Read modified files for full context 3. Review against project conventions in CLAUDE.md and .claude/rules/
Review checklist:
- TypeScript strict mode compliance
- ESM import/export patterns (no CommonJS)
- Consistent error handling patterns
- No exposed secrets or API keys
- Provider interface conformance (AIProvider pattern)
- Agent tool naming convention (group_action snake_case)
- MODELS.md SSOT compliance (no hardcoded model IDs elsewhere)
Provide feedback organized by:
- Critical (must fix before merge)
- Warnings (should fix)
- Suggestions (nice to have)
Let your coding agent generate real video, on your own provider keys, under a spend ceiling it cannot cross. VibeFrame is a CLI and MCP server for Claude Code, Codex, Cursor, or any bash-capable agent.
Repo: vericontext/vibeframe
Other agents on vibeframe.
- e2e-tester
End-to-end tester for the current VibeFrame CLI. Use when asked to test everything, run full tests, or verify the repo works.
Open agent - feature-tester
Deep tester for individual VibeFrame features. Use when asked to test a specific feature, command, or provider in detail.
Open agent - lint-fixer
Fixes ESLint errors across the CLI package. Use after making multiple code changes that may have introduced lint issues.
Open agent - project-auditor
Read-only health audit of the VibeFrame monorepo. Use for a periodic project review — structure, CLI/doc drift, dead code, dependency hygiene, test/lint health, and tech debt — producing a prioritized cleanup plan. Proposes actions; does not make sweeping edits.
Open agent - readme-writer
Use when writing or cleaning up a README or developer-facing project docs. Also call it to make docs clearer, more human, and less bloated.
Open agent - version-checker
Checks version, generated references, public docs, and metadata sync. Use proactively after version bumps, releases, CLI changes, or doc changes.
Open agent