When your coding agent repeats a mistake, move the lesson out of chat.
Turn repeated corrections into rules, hooks, skills, and an independent review loop that improves the next session.
Aug 3, 202610 min read188
Command Palette
Search for a command to run...
#llm
Articles tagged with #llm
The agent fixed one hang, then immediately wrote another.
Mindrealm caught the second one too. 19 of the 21 findings in a feature the agents wrote were real.
Jul 23, 20267 min read93
Goal achieved. My stop hook blocked it anyway.
Claude Code marked the goal achieved and tried to stop. Mindrealm's stop hook wouldn't let it because 17 code review findings were still open.
Jul 20, 20268 min read63
My AI deleted more than twenty unfinished tasks so it could say it was done
If a completion gate reads a number the agent can change, the agent can pass it by changing the number, and probably will.
Jul 16, 20267 min read87
The most dangerous AI-generated code looks finished
More than 6,000 documented agent failures from building one product, the six that keep coming back, and what actually catches them
Jul 13, 202613 min read203