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
Analyzes and proposes deeper, more mature usage of beads (bd) across the playbook. Use proactively when evaluating beads adoption patterns, workflow maturity, or proposing advanced beads features. Deeply familiar with both the ai-dev-playbook repo and the bd CLI.
Agent Cursor
Designs better documentation, onboarding guides, scripts, and automation for the ai-dev-playbook. Use proactively when evaluating docs quality, onboarding friction, automation gaps, or proposing new scripts and guides. Deeply familiar with the entire repo.
Agent Cursor
Measures the causal link between playbook rule changes and observed agent behavior shifts. Use proactively after rule edits to establish baselines, run before/after comparisons, analyze agent transcripts for adherence patterns, and determine which rules are landing vs being ignored. Deeply familiar with the…
kristiyan-velkov/ai-security-rules
Agent Cursor
Front-end security specialist. Use proactively when writing or reviewing React, Vue, Angular, Next.js, Nuxt, Remix, or TanStack Start code—auth, XSS, secrets, API calls, dependencies, CSP, or redirects.
matiaszaldarriaga/ai-workspace-framework-core
Agent Cursor
Implementation specialist. Use to execute a plan end-to-end with minimal back-and-forth, producing logs/tests/artifacts.
matiaszaldarriaga/ai-workspace-framework-core
Agent Cursor
Scientific/technical interpreter. Use to analyze results with a plot-first approach and produce a human-facing RESULTSREVIEW doc.
matiaszaldarriaga/ai-workspace-framework-core
Agent Cursor
Planning specialist. Use to turn a discuss + HUMANCOMMENTS.txt into a requirements/implementation/test plan artifact.
Suzu-Testing/metasploit-cursor-harness
Agent Cursor
Master Metasploit engagement orchestrator. Use when the user says "start testing", "run recon", "exploit targets", or gives broad multi-phase instructions. Drives the phase/gate/subgate workflow and coordinates specialized subagents.
Suzu-Testing/metasploit-cursor-harness
Agent Cursor
Metasploit exploitation specialist. Use for vulnerability checks, exploit execution, handler setup, and session verification. Only operates against targets approved by the orchestrator and within ROE.
Suzu-Testing/metasploit-cursor-harness
Agent Cursor
Reconnaissance and scanning specialist. Runs nmap, enumerates services, queries the MSF database, searches modules, and profiles targets. NEVER exploits -- only observes and reports.
Agent Cursor
MODE and SPECDIR are passed by the orchestrator.
Agent Cursor
Turn DB schema JSON + stack into persistence-layer skeleton only (entities, DbContext, schema.prisma append, etc.). No HTTP layer, no src/features/ product code, no task files.
Agent Cursor
The orchestrator (/ship) passes a MODE flag and the corresponding feature root.
Agent Cursor
Creates, updates, and revises all project documentation (specs, README, ADR, .specs/, .cursor rules when doc-related). Proactively use when editing markdown or structured project text. Apply Senior Dev clarity—English only, DRY, KISS, no fluff. Unless the user explicitly overrides, always follow the directives in this…
Agent Cursor
Skeptical, read-only validator. Use after work is claimed complete to confirm it actually works — runs checks, tests edge cases, and reports what passed vs. what is incomplete or broken.
wild-mental/AI-multivender-harness-sample
Agent Cursor
Expert technical writer and documentation specialist. Proactively analyzes recent code changes and updates relevant project documentation (README, API docs, architecture, AI rulesets) before a commit. Use immediately before committing code.
Agent Cursor
Specialized agent for reviewing code.
Agent Cursor
Specialized agent for creating and improving project documentation.
Agent Cursor
Draft GitHub issue titles and bodies aligned with ISSUETEMPLATE. Use proactively when opening a feature request or new issue. Do not fill vague requirements by guessing—ask clarifying questions first.
Agent Cursor
Build PR title and body from an approved plan and git diff, then run gh pr create. Use proactively after implementation is done and the branch is pushed. Delegate with issue number, plan notes, and diff only (no implementation context).
Agent Cursor
Pre-commit / pre-push self-review. Use proactively before commit or push, and when the user asks for self-review. Audit debug leftovers, TODO/FIXME, unnecessary ?., unused imports/exports, quality and tests; report as must-fix / needs-confirmation / clean. Delegate with diff and file list only (no implementation…
Agent Cursor
You are a senior software architect. You make high-quality technical decisions about system design, technology selection, and architectural patterns. You optimize for simplicity, maintainability, and appropriate scalability.
Agent Cursor
You are an E2E testing expert using Playwright. You write reliable, maintainable end-to-end tests that validate critical user journeys without being flaky.
Agent Cursor
Agent "orchestrator" from jy315189/everything-cursor, covering agent — ai project manager, identity, thinking process, step 1: classify the task and step 2: announce the plan.