meta-sentinel
Design security boundaries, hooks, permissions, and rollback rules for Meta_Kim agents.
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
1,623 agents across 643 plugins.
Design security boundaries, hooks, permissions, and rollback rules for Meta_Kim agents.
Coordinate the Meta_Kim agent team, quality gates, and final synthesis across the other meta agents.
Apply atomic per-finding code fixes triggered by code-review output. 3-tier verify (re-read → syntax-check → fallback). Defers logic-bug fixes to humans.
Use when producing a structured map of a codebase — tech stack, architecture, conventions, and entry points — for downstream phases to consume.
Review individual marketing-copy pieces for tone, clarity, CTA strength, and conversion fundamentals. Trigger per piece pre-publish.
Reviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to…
Analyzes biome.jsonc configurations and provides recommendations for optimization, compatibility, and best practices
Use this agent when the user encounters "CORS errors", "browser upload fails", "access-control-allow-origin", "CORS policy blocked", or needs CORS…
Guides TDD workflow for Symfony projects using Pest PHP or PHPUnit. Drives strict RED-GREEN-REFACTOR cycles with proper test isolation, Foundry factories, and…
Verify built or fixed work end-to-end before any pass, completion, or workflow-advance claim, and classify proof work for latency telemetry.
Fresh read-only review of a saved plan when the router needs an anti-anchoring codebase check before plan finalization.
Create a saved execution plan or decision RFC when implementation work needs an agreement-first artifact before execution.
Delegate quick read-only CODEBASE exploration to Cursor. Use to answer questions about the current repository ("where is X handled?", "how does Y flow?",…
Delegate read-only EXTERNAL web/documentation research to Cursor. Use when the user wants current library/API/docs research, "what's the current way to…", or…
Delegate a SPECIFIC, well-defined implementation task or plan step to OpenCode in agent mode on claude-opus-4-8. OpenCode is the fast lane for mechanical…
Creates spatial learning experiences that teach computing concepts through Minecraft builds, designs guided build methodology, and develops the Amiga Corner…
Audits markdown documentation for completeness, accuracy, broken links, stale content, terminology consistency, and required sections. Read-only analysis with…
Flight operations controller for the Unit Circle Laboratory. Manages the milestone execution pipeline — spawns work, monitors progress, handles errors,…
Use this agent when an MSP operations lead, service manager, or technician wants to identify repetitive ticket patterns in SuperOps.ai that should be automated…
Use this agent when an MSP engineer, service manager, or cloud lead needs a read-only Azure operations investigation — resource health triage, cost and Azure…
Use this agent when an MSP needs a portfolio-wide read on whether backup jobs are actually succeeding across whatever backup/BCDR tools are connected — missed…
**Note: The current year is 2026.** Use this when assessing the recency of Slack discussions.
This agent should be used when the arn-code-report skill needs to diagnose Arness workflow issues in the current session, or when the arn-code-init skill needs…
This agent should be used when invoked by the arn-code-plan or arn-code-pick-issue skills to verify that a previously-written specification still aligns with…
This agent should be used when the arn-code-plan skill needs to generate or revise an implementation plan from a Arness specification and codebase patterns.…
審查程式碼品質、正確性和專案慣例遵循情況。發現錯誤、提供改進建議, 並確保程式碼符合專案標準。 使用時機範例: - "審查這個新功能的程式碼品質" - "檢查是否有潛在的錯誤或問題" - "確認程式碼遵循專案慣例" - "提供改進建議"
簡化和優化程式碼以提升清晰度、一致性和可維護性,同時保持原有功能不變。預設專注於最近修改的程式碼,除非另有指示。
深入調查程式碼庫,定位問題相關程式碼,識別多個可能原因並評估可能性。 基於 problem-analyzer 提供的調查方向,系統化地搜尋程式碼庫,找出所有可能導致問題的程式碼位置。 使用時機: - "調查這個問題在程式碼庫中的可能位置" - "搜尋與這個錯誤相關的程式碼" - "找出所有可能導致這個問題的程式碼"…
Expert in Highcharts for creating professional, interactive charts with minimal code. Specializes in Highcharts Core (60+ chart types), Stock…
Expert in Jupyter Notebook and JupyterLab for interactive computing, data analysis, machine learning experimentation, and reproducible research. Specializes in…
Expert in Python data engineering, ETL pipelines, and production data systems. Specializes in modern data pipeline architecture, Pandas/Polars/PySpark, Apache…
Unity-aware git operations — LFS configuration, merge strategies for binary assets, .meta file hygiene, branch naming, .gitattributes maintenance.
Quick validation pass — checks code against Unity rules without deep reasoning. Haiku-powered for speed.
Handles Unity version upgrades, render pipeline migration (Built-in to URP/HDRP), API migration from deprecated APIs, and package version upgrades. Reads…
Used by the deep-audit orchestrator. Do not invoke directly. Audits a codebase for security vulnerabilities — hardcoded secrets, injection risks, unsafe…
Update and optimize project documentation to reflect recent changes and improve AI agent usability. Use when user asks to "update documentation", "sync docs…
You are a specialist in Railway.app platform deployments, with deep expertise in multi-environment configurations, infrastructure provisioning, and…
Specialized agent for creating comprehensive form systems and managing application routing. Handles form validation, multi-step flows, file uploads, submission…
Specialized agent for creating and maintaining modern web applications with React, TypeScript, and Bootstrap integration. Focuses on responsive design,…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic