Kjell Tore Guttormsen
8376dab83f
Fase 4 token-opt, Item 1 of gap-review NEXT STEP #2. The prompt-cache pattern corpus + TOK scanner were frozen at an "Opus 4.7" framing after CC shipped Opus 4.8 (default, 2.1.154) and Fable 5 (2.1.170). Model-era facts re-verified against the official changelog cache before editing. The patterns are properties of prompt-caching, not of any model, so mechanic text is now model-neutral with a single "current default: Opus 4.8" anchor — preventing a re-freeze at the next model bump. - rename knowledge/opus-4.7-patterns.md -> prompt-cache-patterns.md (git mv, history preserved); 6 reference sites updated - TOK scanner: line-318 finding text (human-facing) made model-neutral; header + cache-prefix-scanner + CLI comments refreshed - configuration-best-practices.md body + footnote 4.7 -> 4.8 - human-facing docs: commands/{tokens,help,manifest}.md, project CLAUDE.md, README, docs/scanner-internals.md - gap-matrix row marked DONE; future Items 2/3 retargeted to new filename Failing-test-first (Iron Law): +2 knowledge staleness guards (era-anchor + no-refreeze) +1 scanner assertion (no stale model anchor in finding text). Suite 853 -> 856 green; zero snapshot drift; self-audit A(97) PASS. CHANGELOG / v5 plan / ratified gap-plan keep historical opus-4.7-patterns refs (correct record of past state). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Ter3E2JSi1Khgmuf2kady8
3.9 KiB
Prompt-Cache Configuration Patterns
Token-efficiency patterns for current Claude Code (defaults to Opus 4.8; Fable 5 is the top-capability model). Detection IDs map to TOK scanner findings. Sources: research/01-opus-47-features-token-efficiency.md (Topic 1), research/04-prompt-caching-patterns.md (Topic 4). Patterns verified 2026-04-19; model-era anchor refreshed 2026-06-18.
Current Claude Code defaults to Opus 4.8 (Fable 5 is the top-capability model). On these models the cost ceiling per turn is high and both the context window and prompt-cache window are large, so cache reuse and tool-schema discipline are the dominant levers for keeping a session affordable. These patterns are properties of prompt-caching itself, not of any single model — they are structural and detectable statically by reading config files without running a session. Cache hit-rate measurement requires runtime telemetry and is explicitly out of scope.
| # | Pattern | Detection (ID) | Severity | Fix |
|---|---|---|---|---|
| 1 | Cache-breaking volatile top-of-file content in CLAUDE.md (timestamps, session ids, rolling activity logs above stable content) | CA-TOK-001 | medium | Move volatile sections to the bottom of CLAUDE.md, or extract to an @import-ed file that lives outside the prompt-cache prefix. Keep the first 30 lines stable across turns. |
| 2 | Redundant tool/permission declarations in settings.json (e.g., both "Read" and "Read(**)", duplicate Bash matchers, overlapping glob patterns) |
CA-TOK-002 | low | Deduplicate the permissions.allow and permissions.deny arrays. Prefer the most specific entry that still grants the intended access. Each duplicate entry inflates the tool-schema payload sent on every turn. |
| 3 | Deep @import chain in CLAUDE.md (more than 2 hops, e.g., A → B → C → D) |
CA-TOK-003 | medium | Flatten the chain to ≤ 2 hops. Each @import boundary fragments the prompt-cache prefix; deeply chained imports defeat caching for the deepest content even when it never changes. |
The v4 sonnet-era signature pattern was removed in v5 F5 — too noisy and not actionable. Hotspots ranking and per-pattern findings cover the same ground with concrete, file-anchored signal.
Detection notes
- Pattern 1 (cache-breaking) is detected by inspecting the first ~30 lines
of CLAUDE.md for tokens that look volatile: literal
{timestamp},{uuid},{date},{session}placeholders, or runs of ISO-timestamp-prefixed lines. The scanner does not attempt to verify cache-hit rate; it flags the shape of content that empirically defeats prompt-cache reuse. - Pattern 2 (redundant tools) is detected by flattening the
permissions.allowandpermissions.denyarrays and looking for entries that are strict subsets of broader entries (e.g.,Bash(npm test)whenBash(*)is also present), or exact duplicates. - Pattern 3 (deep imports) uses the existing IMP scanner's chain depth as the input — anything > 2 hops triggers TOK-003 as well as the IMP finding.
Threshold calibration
All thresholds in this catalogue are structural — derived from the
existing estimateTokens(bytes, kind) heuristic in
scanners/lib/active-config-reader.mjs:29-39. They are intentionally
conservative until Topic 3 (token-cost model) research is complete. When
Topic 3 lands, severities for patterns 1–3 will be re-tuned.
The estimateTokens heuristic uses ~4 bytes per token for markdown content,
which is conservative but unverified against an authoritative tokenizer.
All token counts surfaced by the TOK scanner carry an implicit ±20%
uncertainty band.
Severity Scale
| Severity | Meaning |
|---|---|
| medium | Materially inflates token cost per turn (cache miss, schema bloat) |
| low | Detectable inefficiency that compounds across long sessions |
| info | Informational signal — no action required, may indicate room for optimisation |