Cluster 06 · Axis I

Working with Claude

Prompts, hooks, skills versus rules.

06 · WORKING WITH CLAUDEA prompt change with exactly zero effect

We changed the sampling and added negative examples to a local model's entity-extraction prompt. Same 2.15 entities per file, same 43 kept. And the rule we had suggested would have deleted 18 real concepts. The constraint was not in the prompt.

1 Nov 2026
06 · WORKING WITH CLAUDENothing to migrate

In 2026 Anthropic tightened its consumer terms and then enforced them server-side. Tools built on subscription tokens broke. Team Brain had nothing to change, not because anyone foresaw it, but because the shortcut was never taken.

1 Nov 2026
06 · WORKING WITH CLAUDESend the question, not the pixels

Remote computer use spent five full screenshots to learn that a window was black. One local call to our own vision model answered the question in a sentence, without the image leaving the machine. Local won on cost, speed, privacy and usefulness at once.

1 Nov 2026
06 · WORKING WITH CLAUDEStore a rule as the situation that triggers it

Retrieved by its own wording, a behavioural rule came back 1 time in 5. Stored as the situations it should fire in, 10 of 10. And where the trick stops working.

1 Nov 2026
06 · WORKING WITH CLAUDEThe infinite session broke on 4 September

Michal: 'it felt like one infinite session, then it stopped.' One commit had removed the only line that loaded the continuity file. The file was still written before every compaction, and never read after. Three Claude Code hook details decided the fix.

1 Nov 2026
06 · WORKING WITH CLAUDEThe secret scanner that caught 1 of 9

A commit hook had been checking every commit for leaked credentials for months. Tested against nine real credential shapes, it caught one. A pattern in its own list could never match, and the error went to /dev/null.

1 Nov 2026