Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →hashgraph-online/usage-kernel
Use the six Codex Usage Tracker tools for exact local usage facts, bounded exploration, allowance observations, and evidence timelines.
Passed 7 of 13 test cases with the skill, and 6 of 13 without it.
and 1 more in the full report
4 fixed8 passed either way8 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
I need to examine thread consumption metrics alongside financial credit costs. I ran a top threads query and got back two result items. Which item should I pull credit pricing from?
| Checked | Without skill | With skill |
|---|---|---|
| Uses result item 2 specifically for cost and credit metrics | Missed | Passed |
The instructions your model reads when the skill loads.
Use the tracker as a factual local data plane. The tools return exact or explicitly graded facts; the model owns inference, explanation, and recommendations.
Use the three-step loop scope → batch → evidence:
usage_query whenever the question maps
to a curated template or a known typed request. The result carries its
generation, grade, history coverage, and cache state. Call usage_status
only when the query reports an absent or insufficiently fresh index, or
when the user explicitly asks about operational state. A committed
generation remains queryable while refresh is active or recommended. When
the needed fields are unfamiliar, set include_guidance=true on the same
usage_query call that carries the first batch; use an empty batch only for
standalone capability discovery.usage_query call. Its arguments always wrap
one or more query requests in the requests array. Execute a curated
server-side template with
{"requests":[{"template":"<name>"}]}; for the common thread leaderboard
use {"requests":[{"template":"top_threads"}]}. Templates query the
hydrated snapshot and report its coverage; refresh complete history only
when the user asks. For same five ranked threads, use result 1 for
labels, selectors, totals, shares, and token classes; use result 2 only for
cost/credits. Do not query again unless user asks for evidence. Use
{"requests":[{"template":"weekly_drivers"}]} for the latest indexed
seven-day thread leaderboard,
{"requests":[{"template":"week_over_week"}]} for that window versus the
immediately preceding seven days, and
{"requests":[{"template":"latest_incremental_change"}]} for the active
generation's inserted calls and leading affected thread. These templates
derive their anchors from the committed snapshot; do not discover dates or
generation numbers first. Use
{"requests":[{"template":"model_effort"}]} for model/effort mix and
{"requests":[{"template":"tools"}]} for structural tool facts. Do not repeat a
successful curated template or request guidance after it returns rows.
Supply parameters only when the selected template requires them.
Otherwise send only the typed dataset, operation, dimensions, measures,
filters, and limits needed for the question. Do not copy or reconstruct atest cases passed, vs 6 / 13 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.