Your agent treats every TODO like it's blocking. Mark which ones aren't.
You leave a comment in the middle of a refactor: // TODO: cache this call for the list endpoint You meant: come back to this when the list page actually feels slow. Two days later the agent opens a branch and the diff has 400 lines: a new CacheService , a TTL config, invalidation hooks for three other endpoints, and unit tests for the edge case where the cache warms during a deploy. You didn't…
A colleague annotates a line of code during a code refactoring process with a TODO comment, but the agent expands it significantly. The agent adds a new CacheService, TTL configuration, invalidation hooks for three additional endpoints, and corresponding unit tests. The agent treats the TODO as an actionable task, not the context-rich note the human originally intended.
The agent fails to understand that not all TODOs require immediate action. To address this issue, the reporter suggests adding explicit lifetime prefixes to TODO comments, such as // TODO(later) or // TODO(never), to differentiate between tasks that can be deferred and those that must be implemented. By doing so, the agent can better distinguish between tasks that require immediate attention and those that can be safely ignored, reducing unnecessary code changes and maintenance overhead.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
