Best used with an AI agent

40+ live apps, open data APIs, MCP servers, and 200+ guides - more than anyone wants to click through. Point your AI here and it reads the whole map and does the work: finds the tool, pulls the data, runs the analysis, and hands you the links.

Here for the open-source code? Your agent finds the right repo for you - and can even clone and deploy it.

Prefer to explore on your own? Go right ahead.

Paste this to Claude Code, Codex, or any AI agent:
Go to tigzig.com and read tigzig.com/llms.txt. It is a practitioner toolkit - 40+ analytics apps, open no-auth data APIs, MCP servers, open-source repos (github.com/amararun), and 200+ build guides. Help me [your task]. Surface the exact links; where there is an API or MCP, call it directly; and if I want to self-host, find the repo and help me deploy it.

Claude Code Was Getting Dumber. Stopped It from Auto-Spawning Sub-Agents. Performance Came Back Instantly.

Published: April 15, 2026

A few weeks back Opus 4.6 went from god-level to painful. Rework loops, same mistakes repeated, context getting lost. Then I noticed what was happening. It was auto-spawning sub-agents for everything. Every new task - straight to a sub-agent - which was doing sloppy work. And when the sub-agent reported back 'Done' it just passed on the message...no validation, no checking, just messenger.

I mean as soon as I gave it a task...it just dumped on a sub-agent(s) and sat back doing god knows what.

Claude confirmed that's as per its system instructions too - it is supposed to auto spawn agents.

Maybe the main agent wasn't instructing properly. Maybe the sub-agent was a Haiku. I didn't debug further. Just tried 2 simple things:

1. CLAUDE.md global rule: zero agents without my express authorization

2. Every conversation starts with the same instruction - no agent delegation unless I approve or expressly ask for it

Performance came back instantly.

I still use sub-agents - for repetitive downloads, bulk front-end tasks, simpler UI changes. But I set up the process with the Opus 4.6 first, validate it, then have it delegate to sub-agent. Main agent has the context. Sub-agent is labor.

And the last week or two...it seems to have become even more intelligent...and human like...