Agent
Agent "injection-attacker" from morodomi/dev-crew, covering detection targets, sql injection, command injection, framework detection patterns and dangerous patterns.
Agent
Agent "injection-attacker" from morodomi/dev-crew, covering detection targets, sql injection, command injection, framework detection patterns and dangerous patterns.
Agent
A code-review agent that checks how easy software is to read, understand, and change. It uses Martin Fowler’s “code smells,” which are common patterns that often make code harder to maintain.
Agent
Agent "observability-reviewer" from morodomi/dev-crew, covering focus, output, ブロッキングスコア基準, correctness-reviewer との分担(dedup ルール) and memory.
Agent
A helper agent that detects recurring patterns in an AI coding session and evaluates how reliable those patterns are.
Agent
A code-review agent focused on runtime performance: how efficiently code works, how much memory it uses, and whether concurrent operations are safe. N+1 queries are repeated database or API calls caused by processing items one at a time.
Agent
A product-review agent that checks a proposal for user value, cost versus expected benefit, priority, acceptance criteria, and stakeholder impact. It returns a blocking score and labels issues as critical, important, or optional.
Agent
A security reconnaissance agent that examines a codebase to map routes and API endpoints, identify its frameworks, database, and authentication setup, and rank likely attack points. Reconnaissance means collecting information before a security audit.
Agent
A worker agent for the RED phase of test-driven development (TDD), a method where tests are written before the code they check. It receives test cases and project context, then creates tests that should initially fail.
Agent
Agent "refactorer" from morodomi/dev-crew, covering refactorer, input, example input, output and workflow.
Agent
A reliability reviewer for checking whether software can handle failures in external services without spreading the problem.
Agent
Agent "review-briefer" from morodomi/dev-crew, covering review briefer, 入力, 出力形式, review brief and change summary.
Agent
Agent "sca-attacker" from morodomi/dev-crew, covering detection targets, osv api integration, http execution, version resolution strategy and fallback strategy.
Agent
A security-review agent that checks software for unsafe input handling, login and permission mistakes, database or browser-injection risks, and exposed confidential data.
Agent
A read-only adviser that challenges product-manager decisions as a devil's advocate during review stages. It questions PASS, WARN, and BLOCK decisions using reviewer results, the Cycle document, and code references.
Agent
A security agent that looks for server-side request forgery, where an application is tricked into sending network requests chosen or partly controlled by a user. It checks source code for dangerous request patterns, cloud metadata addresses, and unsafe URL schemes.
Agent
A static-analysis agent for finding server-side template injection (SSTI), a flaw where user-controlled text is treated as template code on the server. It checks patterns in Blade, Jinja2, Twig, ERB, and EJS applications.
Agent
Agent "sync-plan" from morodomi/dev-crew, covering sync-plan, input, output, workflow and step 1: read plan file.
Agent
A test-code review agent that looks for common test problems, including fragile setup, unclear intent, hidden dependencies, duplication, and tests that affect one another.
Agent
A usability reviewer that checks how an interface feels and works for people, including accessibility, navigation, consistency, and error handling. It returns a blocking score and categorized issues.
Agent
A static-analysis security agent for finding WordPress-specific weaknesses in source code without running the site.
Agent
Agent "xss-attacker" from morodomi/dev-crew, covering detection targets, framework detection patterns, dangerous patterns, dom xss dangerous patterns and stored xss detection patterns.
Agent
A security-review agent that uses static analysis, examining source code without running it, to detect XML External Entity vulnerabilities. These flaws can let crafted XML read files, make network requests, or consume excessive resources.
Skill Claude CodeCodex
Skill "kickoff" from morodomi/dev-crew, covering progress checklist, 禁止事項, workflow, step 1: read plan file and step 2: generate cycle doc.
Hook
Runs after a tool call finishes for Edit, Write and Bash tool calls, executing observe.sh via bash. From morodomi/dev-crew.