Monitor .aget/evolution/ directory health. Validates file counts, naming conventions, disk usage, and returns health status with alerts on anomalies.
SkillScore78Maintained
Automatic
◆DevOps & SRE pack
Last verified 8/18/2026
What it changes
Passed 16 of 20 test cases with the skill, and 6 of 20 without it.
Without skill30%
With skill78%
Checks it passed that the model alone missed
Includes a section for File Counts
Includes a section for Index Status
Identifies 10MB to 25MB as the WARN status range
and 13 more in the full report
11 fixed7 passed either way5 still failing0 broke
Pass-rate lift
+48 pp
Tokens
+16%
Agent turns
0%
Response time
-52%
Model gemini-3.6-flashMeasured 8/18/2026v118 of 23 cases passed with skill · 20 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 11
Prompt
What are the file count boundaries for `.aget/evolution/` health classification? Specify the upper limit for OK status, the WARN range, and when CRITICAL is triggered.
What was checked, without and with the skill
Checked
Without skill
With skill
Identifies under 500 files as the threshold for OK status
Missed
Passed
Identifies over 750 files as triggering CRITICAL status
Missed
Passed
case-09 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md127 linessingle file
/aget-check-evolution
Monitor the health of the .aget/evolution/ directory by checking file counts, types, naming conventions, and disk usage.
Purpose
Provide self-diagnostic capability for AGET agents to assess their evolution directory health without supervisor intervention.
Execution
When invoked, perform these checks:
1. File Inventory
# Count total files
find .aget/evolution -type f | wc -l
# Count by extension
find .aget/evolution -type f -name "*.md" | wc -l
find .aget/evolution -type f -name "*.json" | wc -l
find .aget/evolution -type f ! -name "*.md" ! -name "*.json" | wc -l
Create research projects with context-aware scaffolding. Reads AGET identity, searches prior work, pre-populates Due Diligence. Use when starting any formal AGET project.