Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →athola/agent-expenditure
Tracks per-agent token usage and flags waste in parallel dispatch.
Passed 20 of 23 test cases with the skill, and 7 of 23 without it.
and 16 more in the full report
14 fixed6 passed either way2 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
A 2-agent dispatch for log parsing completed. Both agents had unique findings, proportional expenditure, zero duplication, and 2 agents were necessary. Shared-file conflict runtime was 0%. Provide the exit criteria recommendation statement.
| Checked | Without skill | With skill |
|---|---|---|
| States the recommendation that dispatch was efficient. | Passed | Passed |
| Includes the 0% coordination overhead percentage in the recommendation. | Missed | Passed |
The instructions your model reads when the skill loads.
Dispatching more agents does not always help. Coordination overhead grows with agent count:
| Agent Count | Expected Overhead | Guidance |
|---|---|---|
| 1-3 | Negligible | Dispatch freely |
| 4-5 | 10-15% | Acceptable; plan first |
| 6-8 | 20-30% | Monitor closely |
| 9+ | 30%+ | Likely counterproductive |
Coordination overhead is measured as shared-file conflicts: concurrent Read/Write operations on the same file by different agents, as a percentage of total agent runtime.
After parallel agent runs, evaluate:
test cases passed, vs 7 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.