636 that install into Cursor. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.
Agent Cursor
Code search agent for exploring any codebase. Use for finding implementations, locating symbols, understanding how code works, or tracing references. Prefer over Bash/Read for exploratory codebase search.
Agent Cursor
Mirage and assumption detector for plans. Verify plan claims match the codebase before implementation; triggers on verify assumptions or detect mirages in plan.
Agent Cursor
Read-only codebase discovery. Use for mapping files, symbols, usages, and dependencies. Triggers on find relevant files, map usages of, or explore codebase structure.
Agent Cursor
Adversarial plan auditor before implementation. Use for architecture, security, dependencies, rollback, and cold-start executability of the first 3 plan tasks.
Agent Cursor
Archetype: Precise, test-driven implementer. Named for the craft tradition of Dr. Dobb's Journal — code that works, proven by tests, no surprises.
Agent Cursor
Motto: "Code that's easy to prove correct is code that works".
Agent Cursor
PeopleTools and PeopleSoft platform expert. Use proactively for questions about Application Designer, records, pages, PeopleCode, Application Engine, Integration Broker, effective dating, metadata tables (PSRECDEFN, PSPNLFIELD, etc.), security model, Process Scheduler, or any PeopleSoft architecture.
Agent Cursor
Design and product context authority for Huntable CTI Studio. Responds to getdesigncontext and similar requests from ui-designer and other agents. Use proactively when any agent requests design context, brand guidelines, or design system details.
Agent Cursor
An agent guide for investigating and fixing software bugs. It covers reading error messages, identifying the type of failure, tracing the cause, proposing code changes, and suggesting tests.
Agent Cursor
An automated code-review guide for examining pull requests and code quality. A pull request is a proposed code change that others review before it is merged.
Agent Cursor
A code-refactoring role focused on improving existing code while keeping its behavior unchanged. Refactoring means restructuring code to make it easier to read, test, and maintain.
Agent Cursor
Validates completed work by exercising implementations, running relevant tests, and reporting what passes versus what remains incomplete.
Agent Cursor
A simple hello world subagent for testing and verification. This subagent demonstrates basic subagent structure and can be invoked to verify subagents work correctly.
Agent Cursor
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent Cursor
Compare two outputs WITHOUT knowing which skill produced them.
Agent Cursor
Evaluate expectations against an execution transcript and outputs.
Agent Cursor
A background notifier that checks which work areas may be affected when a core principle is added or a major document changes. It records follow-up alignment checks in a shared to-do file.
Agent Cursor
An independent analysis agent that combines five or more pending fragments into an existing L1 knowledge document. It proposes where each fragment belongs and drafts wording that matches the document.
Agent Cursor
An automated reviewer that extracts reusable lessons from logs of tasks involving a cognitive knowledge system.
naimax/agent-harness-reference
Agent Cursor
A read-only coding agent that reviews changed files against the task requirements. It reports whether the work is ready, needs changes, or is rejected.
naimax/agent-harness-reference
Agent Cursor
A coding agent that implements tasks described in `project/docs/tasks`. It writes only in `project/src` and must run tests before marking work complete.
Agent Cursor
A coordinator for setting up a shared automation hub and its client. It discovers the project’s memory and target setup, then selects specialists for planning, packaging, and testing.
Agent Cursor
Валидирует субагентов и граф связей: frontmatter, unique names, registry sync, vague descriptions, broken calls/calledBy. Use when before delivering new agent to user, or after integration. Do NOT use when only writing files (→ t-800-factory-builder) or prompt-only QA without graph/registry (→ t-800-prompt-auditor).
Agent Cursor
Лид сборочного конвейера T-800. Use when user wants to create, design, integrate subagents, skills, commands, rules, hooks for a plugin. Requires t-800-scout and t-800-brain-lead first. Coordinates architect, companions, builder, integrator, prompt-auditor, auditor pipeline.