The tool that stops me drowning in my own tools

If you build automations long enough, you hit a problem nobody warns you about: you end up with too many tools.

I counted mine this week. 177 of them. Skills, agents, commands, plugins. Some live, some archived, some parked in reserve. At that scale the hard part stops being "can I build it" and becomes "which of these do I already have, and which is the right one for this job." You start losing more time rediscovering your own work than you ever spent building it. You rebuild things you forgot you had. You reach for the second-best tool because the good one slipped your mind.

So I stopped trusting my memory and built an index. Here is how it actually works.

One file is the source of truth. Every tool gets a single line in one register file: its name, what kind it is, its status (live, reserve, or archived), when I made it, and a one-line note on when to use it. Nothing lives only in my head.

The dashboard builds itself from that file. A small script reads the register and renders the searchable page in the screenshot below. I never hand-edit the dashboard. Change the index, the page regenerates. One source, always in sync.

Nothing is "done" until it is booked. My rule: a new tool is a booked tool. Building it is not finished until it has a row in the register and turns up in the search. That single rule is what stops the sprawl at the source.

A drift check keeps me honest. A script compares what is actually installed against the register and flags anything that slipped: a tool on disk with no row, a row whose tool is gone, or an archived tool that quietly came back to life.

Then I wire it into the day so it never rots:

1. Start of day. The drift check runs before I build anything. If the index and reality disagree, I hear about it first thing, and my usage stats refresh so the dashboard shows what I actually reached for lately.

2. End of day. The same check runs again as part of shutting down, and it blocks the wrap-up if anything is unregistered. Then everything backs up. The register cannot silently fall behind.

The payoff: before I build anything, I search the index and grab the best fit. I stopped rebuilding things I already had, and the whole map stays current without me having to think about it.

If your kit is growing faster than you can remember it, build the index before you build the next tool.

2 comments

The tool that stops me drowning in my own tools