160 specialist AI agents for Claude Code, Cursor & Codex — one npm install puts them all into your IDE as MCP tools and parallel sub-agents. Local-first, BYOK, works offline with Ollama.
Agent Claude Code
Design A/B tests with Welch's t-test power analysis and GrowthBook configuration. Use the timpsabtestingagent MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
Agent Claude Code
Implement ABHA enrollment, HIP/HIU flows, FHIR R4 bundles, and consent workflows (India ABDM). Use the timpsabdmagent MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
Agent Claude Code
Audit a frontend (HTML / React / Vue) for WCAG 2.2 AA & AAA issues — colour contrast, ARIA, keyboard nav, focus order, screen reader hints. Use the timpsaccessibilitytester MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
Agent Claude Code
Turn a technical decision into a Michael Nygard-style Architecture Decision Record: context, options matrix, decision, consequences, and a rendered Markdown file. Use the timpsadrwriter MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
Agent Claude Code
Generate a new fully-functional Python agent file from a natural-language description. Use the timpsagentcomposer MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
Agent Claude Code
Curate the best AI agent / MCP / LLM-tool marketplaces and recommend picks by use-case. Tracks pulse.mcp.run, glama.ai, mcp.so, OpenAI GPT Store, Claude tool directory. Use the timpsagentmarketplacecurator MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
Agent Claude Code
Forecast Indian agri-commodity prices (mandi arrivals, MSP, weather, festival demand). Returns direction, confidence, and a hedge recommendation for farmers / FPOs / traders. Use the timpsagricommodityforecaster MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
Agent Claude Code
Audit LLM applications against OWASP LLM Top 10 (LLM01-LLM10) with mitigations. Use the timpsaisafetyagent MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
Agent Claude Code
Turn a plain-English multi-step workflow into executable code for LangGraph, Temporal, or Claude-Flow — plus a Mermaid diagram and tests. Use the timpsaiworkfloworchestrator MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
Agent Claude Code
Set up PostHog/Mixpanel/Amplitude event tracking, funnels, and dashboards. Use the timpsanalyticsagent MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
Agent Claude Code
Diff two API specs (OpenAPI/AsyncAPI) and flag breaking changes, deprecations, and safe additions. Returns a semver recommendation and a migration guide for clients. Use the timpsapicontractauditor MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
Agent Claude Code
API Design Agent — generates a complete OpenAPI 3.1 spec (YAML) from a natural-language description. Enforces REST/GraphQL best practices, versioning strategy, and consistent naming BEFORE code generation starts. Returns the spec + a design rationale document. Use the timpsapidesignagent MCP tool to perform this task.…
Agent Claude Code
Profile an API from access logs / traces — p50/p95/p99 by endpoint, slow query, N+1 detection, and concrete optimisations. Use the timpsapiperfprofiler MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
Agent Claude Code
Run an OWASP API Security Top-10 (2023) audit against an OpenAPI spec or live endpoint — broken auth, BOLA, mass assignment, rate-limit, SSRF, injection — with a runnable test harness. Use the timpsapisecuritytester MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
Agent Claude Code
Audit backup health: Time Machine last backup time, all local git repos with uncommitted/unpushed changes, large files on Desktop/Documents not tracked by git or cloud. Returns a risk score and backup script. Use the timpsbackupsentinel MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
Agent Claude Code
Intelligently decompose a bulk task into parallel sub-tasks, execute them concurrently, and return a single aggregated result. Use this to do the same operation across many files at once. Examples: 'add tests for all handlers', 'review all API endpoints', 'add docstrings to every Python file', 'find flaky tests across…
Agent Claude Code
Identify battery drainers. Reads battery %, health cycle count, and ranks processes by CPU usage (proxy for energy drain). Generates kill commands for the top energy vampires. Use the timpsbatteryanalyst MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
Agent Claude Code
Scaffold a new project: folder structure, stub files, setup commands. Supports any language or framework — describe what you're building. Use the timpsboilerplatearchitect MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
Agent Claude Code
Generate Playwright E2E tests with page objects, fixtures, and CI config. Use the timpsbrowserautomation MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
Agent Claude Code
Re-design a noisy calendar: time-block deep work, batch meetings, protect maker time, add commute/exercise buffers, and emit an ICS patch and a focus-mode script. Use the timpscalendaroptimizer MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
Agent Claude Code
Check TLS certificate expiry for all hosts found in config files. Warns 30 days before expiry and generates certbot renewal commands. Use the timpscertificaterotator MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
Agent Claude Code
Generate a Conventional Commits changelog from commit history, PRs, and issues; supports semver bump recommendation. Use the timpschangeloggenerator MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
Agent Claude Code
Score accounts/users for churn risk from behavioural signals, build a survival-curve forecast, segment at-risk cohorts, and recommend save plays per segment. Use the timpschurnpredictor MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
Agent Claude Code
Generate Click/Cobra/Commander CLI tools with shell completions and release workflows. Use the timpsclitoolagent MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: