Sandeeprdy1729/timps-swarm
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.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit Sandeeprdy1729/timps-swarm/.claude ./rig-timps-swarm # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ curl -fsSL --create-dirs -o .claude/agents/timps-ab_testing_agent.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-ab_testing_agent.md $ curl -fsSL --create-dirs -o .claude/agents/timps-abdm_agent.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-abdm_agent.md $ curl -fsSL --create-dirs -o .claude/agents/timps-accessibility_tester.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-accessibility_tester.md $ curl -fsSL --create-dirs -o .claude/agents/timps-adr_writer.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-adr_writer.md $ curl -fsSL --create-dirs -o .claude/agents/timps-agent_composer.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-agent_composer.md $ curl -fsSL --create-dirs -o .claude/agents/timps-agent_marketplace_curator.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-agent_marketplace_curator.md $ curl -fsSL --create-dirs -o .claude/agents/timps-agri_commodity_forecaster.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-agri_commodity_forecaster.md $ curl -fsSL --create-dirs -o .claude/agents/timps-ai_safety_agent.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-ai_safety_agent.md $ curl -fsSL --create-dirs -o .claude/agents/timps-ai_workflow_orchestrator.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-ai_workflow_orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/timps-analytics_agent.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-analytics_agent.md $ curl -fsSL --create-dirs -o .claude/agents/timps-api_contract_auditor.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-api_contract_auditor.md $ curl -fsSL --create-dirs -o .claude/agents/timps-api_design_agent.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-api_design_agent.md $ curl -fsSL --create-dirs -o .claude/agents/timps-api_perf_profiler.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-api_perf_profiler.md $ curl -fsSL --create-dirs -o .claude/agents/timps-api_security_tester.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-api_security_tester.md $ curl -fsSL --create-dirs -o .claude/agents/timps-backup_sentinel.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-backup_sentinel.md $ curl -fsSL --create-dirs -o .claude/agents/timps-batch.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-batch.md $ curl -fsSL --create-dirs -o .claude/agents/timps-battery_analyst.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-battery_analyst.md $ curl -fsSL --create-dirs -o .claude/agents/timps-boilerplate_architect.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-boilerplate_architect.md $ curl -fsSL --create-dirs -o .claude/agents/timps-browser_automation.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-browser_automation.md $ curl -fsSL --create-dirs -o .claude/agents/timps-calendar_optimizer.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-calendar_optimizer.md $ curl -fsSL --create-dirs -o .claude/agents/timps-certificate_rotator.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-certificate_rotator.md $ curl -fsSL --create-dirs -o .claude/agents/timps-changelog_generator.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-changelog_generator.md $ curl -fsSL --create-dirs -o .claude/agents/timps-churn_predictor.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-churn_predictor.md $ curl -fsSL --create-dirs -o .claude/agents/timps-cli_tool_agent.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-cli_tool_agent.md $ curl -fsSL --create-dirs -o .claude/agents/timps-cloud_cost_auditor.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-cloud_cost_auditor.md $ curl -fsSL --create-dirs -o .claude/agents/timps-code_archaeology.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-code_archaeology.md $ curl -fsSL --create-dirs -o .claude/agents/timps-cold_email_sequence_writer.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-cold_email_sequence_writer.md $ curl -fsSL --create-dirs -o .claude/agents/timps-competitor_tracker.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-competitor_tracker.md $ curl -fsSL --create-dirs -o .claude/agents/timps-compliance_auditor.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-compliance_auditor.md $ curl -fsSL --create-dirs -o .claude/agents/timps-computer_use_agent.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-computer_use_agent.md $ curl -fsSL --create-dirs -o .claude/agents/timps-connect_tools.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-connect_tools.md $ curl -fsSL --create-dirs -o .claude/agents/timps-container_image_scanner.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-container_image_scanner.md $ curl -fsSL --create-dirs -o .claude/agents/timps-content_multiplier.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-content_multiplier.md $ curl -fsSL --create-dirs -o .claude/agents/timps-context_briefing.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-context_briefing.md $ curl -fsSL --create-dirs -o .claude/agents/timps-context_switcher.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-context_switcher.md $ curl -fsSL --create-dirs -o .claude/agents/timps-contract_reviewer.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-contract_reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/timps-cost_optimizer.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-cost_optimizer.md $ curl -fsSL --create-dirs -o .claude/agents/timps-court_case_summarizer.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-court_case_summarizer.md $ curl -fsSL --create-dirs -o .claude/agents/timps-data_pipeline.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-data_pipeline.md $ curl -fsSL --create-dirs -o .claude/agents/timps-data_wrangler.md https://raw.githubusercontent.com/Sandeeprdy1729/timps-swarm/main/.claude/agents/timps-data_wrangler.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| timps-swarm env: ANTHROPIC_API_KEY, GEMINI_API_KEY, GROQ_API_KEY, OLLAMA_HOST, OPENAI_API_KEY | local / custom | 2.5k |
Subagents (80)
| timps_ab_testing_agent model: sonnet | Design A/B tests with Welch's t-test power analysis and GrowthBook configuration. Use the `timps_ab_testing_agent` MCP tool to perform this task. Do not answer directly — delegate to this sub-agent. |
| timps_abdm_agent model: sonnet | Implement ABHA enrollment, HIP/HIU flows, FHIR R4 bundles, and consent workflows (India ABDM). Use the `timps_abdm_agent` MCP tool to perform this task. Do not answer directly — delegate to this sub-a |
| timps_accessibility_tester model: sonnet | 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 `timps_accessibility_tester` MCP tool to perform thi |
| timps_adr_writer model: sonnet | Turn a technical decision into a Michael Nygard-style Architecture Decision Record: context, options matrix, decision, consequences, and a rendered Markdown file. Use the `timps_adr_writer` MCP tool t |
| timps_agent_composer model: sonnet | Generate a new fully-functional Python agent file from a natural-language description. Use the `timps_agent_composer` MCP tool to perform this task. Do not answer directly — delegate to this sub-agent |
| timps_agent_marketplace_curator model: sonnet | 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 `timps_agent_marketplac |
| timps_agri_commodity_forecaster model: haiku | Forecast Indian agri-commodity prices (mandi arrivals, MSP, weather, festival demand). Returns direction, confidence, and a hedge recommendation for farmers / FPOs / traders. Use the `timps_agri_commo |
| timps_ai_safety_agent model: sonnet | Audit LLM applications against OWASP LLM Top 10 (LLM01-LLM10) with mitigations. Use the `timps_ai_safety_agent` MCP tool to perform this task. Do not answer directly — delegate to this sub-agent. |
| timps_ai_workflow_orchestrator model: sonnet | Turn a plain-English multi-step workflow into executable code for LangGraph, Temporal, or Claude-Flow — plus a Mermaid diagram and tests. Use the `timps_ai_workflow_orchestrator` MCP tool to perform t |
| timps_analytics_agent model: sonnet | Set up PostHog/Mixpanel/Amplitude event tracking, funnels, and dashboards. Use the `timps_analytics_agent` MCP tool to perform this task. Do not answer directly — delegate to this sub-agent. |
| timps_api_contract_auditor model: haiku | 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 `timps_api_contract_audito |
| timps_api_design_agent model: sonnet | 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 genera |
| timps_api_perf_profiler model: sonnet | Profile an API from access logs / traces — p50/p95/p99 by endpoint, slow query, N+1 detection, and concrete optimisations. Use the `timps_api_perf_profiler` MCP tool to perform this task. Do not answe |
| timps_api_security_tester model: sonnet | 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 `timps_ |
| timps_backup_sentinel model: haiku | 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 |
| timps_batch model: haiku | 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: 'a |
| timps_battery_analyst model: haiku | 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 `timps_battery_a |
| timps_boilerplate_architect model: haiku | Scaffold a new project: folder structure, stub files, setup commands. Supports any language or framework — describe what you're building. Use the `timps_boilerplate_architect` MCP tool to perform this |
| timps_browser_automation model: sonnet | Generate Playwright E2E tests with page objects, fixtures, and CI config. Use the `timps_browser_automation` MCP tool to perform this task. Do not answer directly — delegate to this sub-agent. |
| timps_calendar_optimizer model: sonnet | 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 `timps_calendar_optimizer` MC |
| timps_certificate_rotator model: sonnet | Check TLS certificate expiry for all hosts found in config files. Warns 30 days before expiry and generates certbot renewal commands. Use the `timps_certificate_rotator` MCP tool to perform this task. |
| timps_changelog_generator model: sonnet | Generate a Conventional Commits changelog from commit history, PRs, and issues; supports semver bump recommendation. Use the `timps_changelog_generator` MCP tool to perform this task. Do not answer di |
| timps_churn_predictor model: sonnet | 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 `timps_churn_predictor` MCP tool t |
| timps_cli_tool_agent model: sonnet | Generate Click/Cobra/Commander CLI tools with shell completions and release workflows. Use the `timps_cli_tool_agent` MCP tool to perform this task. Do not answer directly — delegate to this sub-agent |
| timps_cloud_cost_auditor model: sonnet | Scan Terraform configs for waste (over-provisioned instances, missing deletion protection) and check AWS CLI for idle resources. Use the `timps_cloud_cost_auditor` MCP tool to perform this task. Do no |
| timps_code_archaeology model: sonnet | Analyse git history to build an AST import graph, risk map, and tribal knowledge document. Use the `timps_code_archaeology` MCP tool to perform this task. Do not answer directly — delegate to this sub |
| timps_cold_email_sequence_writer model: sonnet | Write a 5-7 step cold-outreach email sequence for a persona + offer, with subject A/B variants, social proof, objection handling, and a reply-promise CTA. Spam-safe. Use the `timps_cold_email_sequence |
| timps_competitor_tracker model: haiku | Monitor competitors for pricing changes, new features, job postings, and public sentiment. Returns a competitive intelligence brief. Use the `timps_competitor_tracker` MCP tool to perform this task. D |
| timps_compliance_auditor model: sonnet | Map a codebase + infra config against SOC 2 / ISO 27001 / HIPAA / PCI-DSS / GDPR controls; produce an evidence pack and gap report. Use the `timps_compliance_auditor` MCP tool to perform this task. Do |
| timps_computer_use_agent model: sonnet | Plan a GUI / computer-use task and emit OS-specific step scripts (cliclick / xdotool / PowerShell) with safety approval gates. Pairs with the runtime computer_use tools. Use the `timps_computer_use_ag |
| timps_connect_tools model: haiku | Auto-configure TIMPS Swarm as an MCP server in every AI coding tool installed on this machine (Cursor, Windsurf, GitHub Copilot, Cline, Continue, Aider, Goose, OpenCode, Gemini CLI, and more). Use --d |
| timps_container_image_scanner model: sonnet | Scan a container image / Dockerfile for CVEs, misconfigurations, and supply-chain risk. Wraps trivy/grype/syft when present; falls back to static analysis of the Dockerfile. Use the `timps_container_i |
| timps_content_multiplier model: haiku | Transform a long-form technical post into multiple short-form formats: tweet thread, LinkedIn post, changelog entry, docs blurb, and HN title. Use the `timps_content_multiplier` MCP tool to perform th |
| timps_context_briefing model: haiku | Get a 3-sentence resumption briefing from the Context Keeper: what you were working on, current state (uncommitted changes, broken tests), and recommended next step. Use when the user says 'what was I |
| timps_context_switcher model: haiku | Analyse current work context: active apps, estimated browser tabs, current git branch and recent commits. Identifies distraction apps and generates a focus-mode script to quit them. Use the `timps_con |
| timps_contract_reviewer model: sonnet | Review a contract (MSA, NDA, SaaS, vendor agreement) for red-flags: indemnification, liability caps, IP, data, termination, SLAs. Returns a clause-by-clause scorecard and a redline. Use the `timps_con |
| timps_cost_optimizer model: sonnet | Estimate monthly/annual cloud cost for an architecture and generate a prioritised list of savings optimisations. Use the `timps_cost_optimizer` MCP tool to perform this task. Do not answer directly — |
| timps_court_case_summarizer model: sonnet | Summarise a court judgment / order: bench, facts, issues, holdings, reasoning, ratio, and citations in a structured brief. For legal research, not legal advice. Use the `timps_court_case_summarizer` M |
| timps_data_pipeline model: sonnet | Design dbt/Airflow/Prefect/Dagster ETL/ELT pipelines with monitoring and lineage. Use the `timps_data_pipeline` MCP tool to perform this task. Do not answer directly — delegate to this sub-agent. |
| timps_data_wrangler model: haiku | Clean and normalise messy data: CSV, JSON, PDF extracts, copy-pasted tables. Returns cleaned records, a quality score, and SQL insert hint. Use the `timps_data_wrangler` MCP tool to perform this task. |
Similar rigs
rtk-ai/rtk
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Orchestrator 2.6k tok · · Q0
Yeachan-Heo/oh-my-claudecode
Teams-first Multi-agent orchestration for Claude Code
Orchestrator 14.5k tok · · Q3
davila7/claude-code-templates
Open-source registry and CLI for Claude Code components: agents, commands, skills, hooks, MCPs, settings and mods
Orchestrator 27.6k tok · · Q24
alirezarezvani/claude-skills
380 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 380+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, complian
Orchestrator 48.5k tok · · Q23