mem_tried
Record failed approaches to prevent future agents from repeating the same mistakes. Saves debugging time by surfacing negative knowledge in future briefings.
Instructions
Record a FAILED approach so future agents don't repeat the same mistake.
USE THIS IMMEDIATELY when you try something and it doesn't work. This is the most valuable type of negative knowledge — it saves hours of debugging for future agents working on the same codebase.
Auto-validated (no approval cycle). Surfaced FIRST in future get_briefing calls so it's impossible to miss.
PARAMETERS: what — short title of what you tried (e.g. 'importing X with ESM dynamic import') why_failed — the exact error or reason it failed instead — what to do instead (the correct approach) scope — team (default) | personal paths — source files where the issue lives
RETURNS: { id, file_path, action: 'created' }
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| tags | No | Tags for filtering | |
| what | Yes | Brief description of the approach that was tried | |
| paths | No | Anchor file paths this applies to | |
| scope | No | Visibility scope. Defaults to personal — EXCEPT when a one-shot `sensor` is attached: an enforced lesson is team truth (the sensor must travel to every machine and CI), so it defaults to team. Pass scope explicitly to override. | |
| author | No | Author handle or email | |
| module | No | Module name (required when scope=module) | |
| sensor | No | ONE-SHOT loop close: validate and attach a sensor in the same call (equivalent to a follow-up propose_sensor). Validated against HEAD — silent on current code, fires on the bad example. If rejected, the attempt is still saved and the verdict tells you how to revise. | |
| instead | No | What to use or do instead (recommended alternative) | |
| why_failed | Yes | Why it failed or why it should NOT be used |