config-audit/knowledge
Kjell Tore Guttormsen e861e63a7b feat(knowledge): model + effort routing enter the register, dated [skip-docs]
C1: two entries the optimization lens can cite for the model/effort axis,
both read out of the primary sources in this session rather than from the
plan's 2026-07-14 summary of them.

Verifying corrected the plan's own numbers: effort is settable in SIX
places, not five (/effort, the /model slider, --effort,
CLAUDE_CODE_EFFORT_LEVEL, settings effortLevel, skill/subagent
frontmatter), the default is high on every supporting model EXCEPT Opus
4.7 (xhigh), and the level count is model-dependent (Opus 4.6 and Sonnet
4.6 have no xhigh).

- BP-MODEL-001: subagent `model` defaults to `inherit`, so a subagent
  that names no model costs what the session costs; the documented pin
  is overridable by CLAUDE_CODE_SUBAGENT_MODEL and per-invocation model
- BP-MODEL-002: effort is an axis separate from model choice, and higher
  is not universally better (`max` "may show diminishing returns and is
  prone to overthinking")
- both carry the 2026-07-07 model/effort blog as a corroborating source
  with a real `published` date, so B1's evidence-age rule has teeth:
  measured stale with reasons ['evidence-age'] at a reference date 378
  days past publication while their verified stamps are pristine. The
  docs pages themselves get NO published date — they carry none, and
  guessing one in the field whose whole job is dating evidence is the
  lie the rule exists to catch
- new blanket guard: every corroborating source must carry a parseable
  published date. Without it newestEvidenceMs() returns null and the
  entry stays green on evidence of any age — a silent hole. Seen red
  against its own defect before it was trusted
- knowledge-refresh-cli's stale branch no longer expires on every new
  entry: its reference date has to sit after every `verified` stamp, was
  bumped once for BP-SUB-001 and would have needed a third bump now, so
  it moves to a date no stamp can reach

Register 14 -> 16 entries. Frozen v5.0.0 snapshots untouched (no scanner
output changes); suite 1579/0.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NKjojcdYYiCQP5AudUyQ5e
2026-08-10 04:36:09 +02:00
..
anti-patterns.md fix(mcp-config-validator): remove invented trust field (verify-first) 2026-06-18 14:22:56 +02:00
best-practices.json feat(knowledge): model + effort routing enter the register, dated [skip-docs] 2026-08-10 04:36:09 +02:00
cache-telemetry-recipe.md fix(tokens): refresh stale "Opus 4.7" framing to model-neutral + Opus 4.8 anchor 2026-06-18 15:27:36 +02:00
claude-code-capabilities.md release: v5.4.0 — plugin-hygiene & settings-validation hardening 2026-06-19 22:32:38 +02:00
configuration-best-practices.md fix(tokens): refresh stale "Opus 4.7" framing to model-neutral + Opus 4.8 anchor 2026-06-18 15:27:36 +02:00
feature-evolution.md docs(knowledge): refresh corpus to Opus 4.8 era (CC 2.1.114->181 Batch 3) 2026-06-18 13:35:00 +02:00
gap-closure-templates.md fix(mcp-config-validator): remove invented trust field (verify-first) 2026-06-18 14:22:56 +02:00
hook-events-reference.md docs(knowledge): refresh corpus to Opus 4.8 era (CC 2.1.114->181 Batch 3) 2026-06-18 13:35:00 +02:00
prompt-cache-patterns.md release: v5.3.0 — permission-rule & plugin-hygiene hardening (DIS/CML/PLH) 2026-06-19 20:45:29 +02:00