mirror of
https://github.com/kuhyx/testsAndMisc.git
synced 2026-11-12 19:30:55 +01:00
Krzysztof kuhy Rudnicki
11aea86920
Answers "what is billed on every turn regardless of use" by measurement instead of recall, which is the part earlier audits kept getting wrong. A surface is reported dead only when unused in BOTH windows. One earlier audit's seven-day dead list included six servers that had been used within thirty days, so a single window is not evidence. Shares are weighted with cache-read weight 0.1, so a cached surface is not billed as though it were re-read in full each turn. Verified by running it, not just by tests: the report renders over 44,311 turns, putting rules/ at 4,907 tokens (1.77%), MEMORY.md at 4,312 (1.55%), memories/ at 3,758 (1.35%), skill descriptions at 3,279 (1.18%) and CLAUDE.md at 2,057 (0.74%), with per-MCP 7d/30d call counts behind each verdict. The files were found untracked in the tree from an earlier session; every module is already under the 250-line cap, so nothing needed splitting, and the package was already at 100% branch coverage, so nothing needed new tests. This lands the instrument only -- no surface is unregistered on its say-so. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| explanations | ||
| superpowers | ||
| agent-harness-evaluation-2026-08-18.md | ||
| app-split-recipes.md | ||
| device-owner-wipe-checklist.md | ||
| dns-filtering-parked.md | ||
| kcov-under-report.md | ||
| mcp-shortlist.html | ||
| python-split-recipes.md | ||
| shared-checkout-safety.md | ||
| shell-split-harness.md | ||
| shell-split-recipes.md | ||
| shell-split-verification.md | ||
| syncyomi-restore-runbook.md | ||