> The complete Setup Score scoring rubric, published so you can score
> yourself by hand or check our arithmetic. This is the file the product
> actually uses.

# Scoring rubric: the 100-point Claude setup maturity score

Read by the insight-report generator (Phase 1), the pack's own scoreboard,
and later the benchmark (post-MVP). One rubric, two modes, stated honestly.

## The scale

| Band | Score | Reads as |
|---|---|---|
| Ad hoc | 0 to 20 | Chats from scratch; nothing persists between sessions |
| Emerging | 21 to 40 | Some saved prompts or notes; no durable system |
| Systematic | 41 to 60 | Operating manual and project context exist; memory partial |
| Compounding | 61 to 80 | Memory, rituals and first skills in daily use |
| Productised | 81 to 100 | Workflows encoded, automated where safe, deployable to others |

Category weights (must always sum to 100 before renormalisation):
foundation 26, memory-context 24, skills 12, integrations 12,
productisation 18, advanced 8.

**Renormalisation**: when personalisation excludes a category (for example
productisation when `productisation_intent != yes`), the remaining categories
scale to 100: `score = raw x (100 / included_weights_sum)`, rounded to the
nearest integer. The report states which categories were excluded and why.

## Mode A: interview-estimated (the insight report)

Computed from profile fields alone; self-report, so the report gives the
BAND plus a range of plus or minus one band boundary, never a false-precision
single number, and says plainly: "estimated from your answers; the pack's
audit runbooks verify it on your machine."

Per-category evidence rows; each row scores its listed points if the profile
supports it, 0 if not, and half if partial or unclear.

**Foundation (26)**
- Global CLAUDE.md exists and is a real operating manual: 8
  (global_claude_md present with summary; else session habits imply one: 4)
- Per-project context exists: 6 (project_claude_md_count >= 1, or
  project_context_files == yes)
- Workspace under version control or deliberate sync: 3
- Account situation understood; if multiple, continuity practised: 3
  (accounts == multiple with no governance_flag confusion: full)
- Baseline sanity (settings known, skills folder exists): 6
  (skills_installed not unavailable: half; count >= 1: full)

**Memory-context (24)**
- Session-end habit persists knowledge: 10
  (session_end_habit: nowhere 0, notes 3, files 5, claude_md 7, system 10)
- Context re-established from files, not re-explaining: 8
- Long-term archive of decisions exists in any form: 6

**Skills (12)**
- Any skill or reusable encoded workflow installed: 6
  (skills_installed >= 1, or working_today includes a saved reusable prompt: 3)
- A recurring deliverable runs the same way every time: 6
  (working_today has 1 or more genuinely recurring entries)

**Integrations (12)**
- Core tools connected to Claude at all: 6
  (share of core_tools with a connection: none 0, some 3, most 6)
- Ownership and auth known per connection: 6
  (credential_hygiene described with locations: full; secrets seen in
  chats: 0 on this row regardless)

**Productisation (18)** (excluded unless productisation_intent == yes)
- A workflow named and deployable in principle: 6 (next_candidate or
  productisation target named)
- Any runbook, intake or checklist already written down: 6
- A first customer identified: 6

**Advanced (8)**
- Sub-agents, scheduled runs or headless use in practice: 8
  (reported real use: full; aware but unused: 2)

## Mode B: audit-verified (after the pack runs)

The pack's audit runbooks each end in a findings report with the category's
rubric applied on evidence (the v0 kit pattern). The verified score is the
sum of those evidence-scored criteria across the category audits, under the
same category-inclusion and renormalisation rules as Mode A. The pack's
scoreboard separately sums ticked tasks' points; that number is pack
progress, not the verified score, and completing a task is not the same
measurement as proving a maturity condition. Rule carried from the kit:
anything not determinable is scored 0 and marked "unavailable", never
guessed.

## Top-gaps selection (for the insight report)

Rank categories by points lost (weight minus scored), take the top three,
and for each name: the gap in plain language, what it costs day to day, and
which pack runbooks address it (ids only; the fixes themselves stay in the
pack). Never name fixes' contents in the report.