Example output

Your scoring system,
documented for you.

When the agent inspects your repo it doesn't just write config — it produces this: a living document of every scored action, the journeys they form, and how the live economy tracks against your targets. Here's an example for a focus & habit app.

generated by streakline · agent source: focusflow/ · scoring v4 · updated 2026-06-27

Features & user actions

Three product areas were detected. Each user action maps to a scored event, with anti-gaming caps the agent inferred from how often the action can realistically happen.

Focus sessions

src/features/focus/
focus.session.completedFinished a timed focus block
+20
cap 5/day · cooldown 5m
focus.session.extendedAdded time to an active session
+5
cap 3/day

Reflections

src/features/journal/
reflection.savedWrote an end-of-day reflection
+15
cap 1/day
reflection.mood_taggedTagged a mood on a reflection
+3
cap 3/day

Routines

src/features/routines/
routine.finishedCompleted a full daily routine
+20
streak-eligible
routine.step_doneChecked off one routine step
+4
cap 12/day

A mapped journey

The agent stitches actions into the journeys your users actually take, and shows the score accumulating through the loop — including bonuses.

Opens app
score 0
focus.session
score 20
reflection.saved
score 35
routine.finished
score 55
streak bonus
score 63 · Lv2

How the economy behaves

Score progression for a typical user, and where points actually come from.

Cumulative score · first 30 days

Median user, with Level thresholds
Lv4Lv3Lv2Lv1 d0d15d30

Points by source

Share of total score awarded
focus.session 38%
routine.finished 27%
reflection.saved 19%
routine.step_done 11%
other 5%

Metrics vs target

The agent tracks the outcomes your economy is meant to drive, against the targets you set — and flags where a scoring change might help. This is what closes the loop on tuning.

Day-7 streak survival 47% / 50%
D30 retention 33% / 35%
Avg scored actions / day 3.6 / 4.0
Median time to Level 2 1.8d / 2.0d
Level-up rate (D14) 62% / 55%

Suggested change. Day-7 streak survival trails target. The agent proposes issuing the first freeze token at a 5-day streak instead of 7 — drafted as scoring v5 for your review.

Generate this for your app.

Point the agent at your repo and it produces this document — then keeps it live as your product and your numbers change.