Install any skill in seconds. Free to start, no credit card required.
Get Started Free →boshu2/toil-mining
Mine caller-supplied usage history for
Passed 17 of 21 test cases with the skill, and 7 of 21 without it.
and 10 more in the full report
12 fixed7 passed either way4 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
We need to extract recent human requests from Codex JSONL logs `/logs/session-1.jsonl` and `/logs/session-2.jsonl` between 2026-07-12T00:00:00Z and 2026-07-16T00:00:00Z. What specific CLI invocation should be used to perform this deterministic extraction?
| Checked | Without skill | With skill |
|---|---|---|
| Invokes `skills/toil-mining/scripts/recent_human.py` with explicit `--since` and `--until` parameters. | Missed | Passed |
The instructions your model reads when the skill loads.
Mine explicitly supplied session, shell, RTK, or CASS history without modifying the sources. The result is evidence for a caller; this skill does not file work, schedule automation, or mutate a tracker.
Each candidate must contain a measured count, source references, confidence in the clustering, pain evidence, and the smallest plausible automation shape. Separate observations from recommendations.
A cluster qualifies as toil only above a measured floor: at least three occurrences in the supplied window, each resolvable to a source reference. Two occurrences are a coincidence; a vivid memory of "doing this constantly" with one resolvable instance is an anecdote. The named failure mode is salience mining — ranking by how annoying the last occurrence felt rather than by count, which surfaces yesterday's irritation over the quiet weekly drain.
test cases passed, vs 7 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.