LOCAL · OFFLINE · CLAUDE CODE + CODEX
Cadence reads the Claude Code and Codex logs already on your Mac and turns them into one offline dashboard: hours of your attention, hours of agent work, what actually shipped — and the leverage between them.
×6.8leverage · today
77 %first-pass
59 %5h window util
100 % offline by default loopback-only dashboard prompts never leave the box Python 3.11+ brew or pip
Up and reading in about 30 seconds
brew install lubosxyz/tap/cadencecadence scancadence servePrefer pip? pip install cadence-report · Python 3.11+ · Opens a local dashboard on your machine. No account required.
The dashboard
Attention → leverage → first-pass → shipped. Every view is rendered from your own logs, on your own machine.
01 — THE CHAIN
Attention is the scarce input. Cadence follows it through delegation and friction into shipped code.
Dynamics is your 5-hour billing-window utilization, read like a score marking — pianissimo under 20 %, piano, mezzo-forte, forte, fortissimo above 75 %. Tempo belongs to leverage: Largo under ×2 up to Prestissimo past ×50. sample data · jul 7 – 13
ATTENTION
65 h
10 min per merged PR
The hours you were actually at the keyboard with an agent.
LEVERAGE
×6.8
440 agent-h from your 65 h
Agent-hours per attention-hour; the multiplier your delegation earns.
FIRST-PASS
77 %
678 clean · 201 one fix · 1 loop
How often work landed without a rework loop.
SHIPPED
399 PRs
API-list reference $1.40 each
Git-authoritative merged PRs, net LOC, commits.
02 — THE SCORE
You on the top staff. Every agent session on a lane below. PRs, merges and rework loops marked where they happened. The strip underneath counts how many lanes were playing at once.
03 — TWO LEDGERS
Session logs tell you how you worked. Git tells you what shipped. Cadence keeps them in separate ledgers and bridges them on one page — every panel is chipped with its source.
CORRELATIONS — hours vs output per project · tokens vs shipped, daily · process and git heatmaps side by side
Two sources, two numbers, both kept: in the sample window the chain counts 399 merged PRs from PR metadata, while the git ledger counts the 277 merges it can see in the clones on this machine.
Act on the signal
The dashboard surfaces the patterns that are expensive to feel and hard to remember.
See where repeated correction consumed attention.
‖ rework loops, marked on the score and counted per range
Find tools and models taking a disproportionate share of tokens.
“Model spend outweighs outcomes”
Spot fragmented time across too many projects or concurrent sessions.
“Too much time is fragmenting into idle mini-sessions”
Track the cache-hit ratio before context spend quietly compounds.
“Cache hit ratio is below healthy range”
Compare a $200/mo Claude Max plan with API-list-cost equivalent usage and shipped output.
“Plan value cleared break-even”
4.75 projects
touched inside the same 5-hour billing window, on average — across 24 distinct projects in the range.
Spend less time reconstructing the week. Spend more time changing the next one.
04 — PLAN VALUE
Cadence imputes what your usage would cost at API list price and sets it against the plan you actually pay for.
Cadence uses your configured plan price — $200/mo Claude Max by default, or your own — and prices tokens at the providers' published list rates. Nothing is invented per token. sample data
CELEBRATE
Plan value cleared break-even: imputed usage was 11.94 × the configured plan cost.
WARNING
Model spend outweighs outcomes: claude-opus-4-8, 98.2 % of cost for 4.3 % of outcomes.
cache hit97.4 %
per merged PR at list$1.40
05 — EVERY DAY, EVERY MONDAY
The macOS companion starts the local dashboard, keeps it fresh, and taps you on the shoulder once a week.
Signed download ships with the public launch — the CLI works today.
06 — THE NETWORK BOUNDARY
Nothing on this page is a promise about a server. There is no server.
127.0.0.1 with a per-session token.~/.cache/cadence; delete it any time, Cadence rebuilds it.Three opt-in paths are the only ones that ever talk to the network: cadence publish (aggregates only) · cadence scan-github and scan-git --github (gh-backed PR metadata) · cadence backup (to a private repo you own).
07 — THE LEADERBOARD
Opt in with cadence publish and only aggregates leave the box: leverage and its tempo, first-pass rate, focus ratio, net LOC per active hour, PRs merged per week, ROI, unique projects, active days — plus the two totals behind them and the cohort you chose (country, industry, language, plan, agent). The board ranks the efficiency rates; the rest is context.
published only once ≥ 50 GitHub-verified builders are in this slice
| Rank | Builder | Leverage | First-pass % | Focus % |
|---|---|---|---|---|
| 1 | ●●●● held · podium | — | — | — |
| 2 | ●●●● held · podium | — | — | — |
| 3 | ●●●● held · podium | — | — | — |
| 4 | orbit·2a6e ✓ | ×22.6 Presto | 81 | 84 |
| 5 | nova·0f4c ✓ | ×14.2 Allegro | 76 | 79 |
| 6 | pine·8e31 ✓ | ×11.3 Allegro | 83 | 71 |
| 7 | sol·5d7b ✓ | ×9.4 Allegro | 74 | 80 |
| 8 | river·a12f ✓ | ×7.2 Andante | 79 | 68 |
League tierEmergingSteadyAscendantVanguardsample rows
08 — WHY NOT…
| Metric | Cadence | WakaTime | GitHub |
|---|---|---|---|
| Attention vs agent hours | ✓ yes | — no | — no |
| Leverage | ✓ yes | — no | — no |
| First-pass & rework loops | ✓ yes | — no | — no |
| 5h billing-window utilization | ✓ yes | — no | — no |
| Cache efficiency | ✓ yes | — no | — no |
| Plan ROI | ✓ yes | — no | — no |
| Active hours | ✓ yes | ✓ yes | ✓ yes |
| Net LOC | ✓ yes | ✓ yes | ✓ yes |
| Merged PRs | ✓ yes | — no | ✓ yes |
09 — TEAM
Profiles and devices roll up locally. Teams get aggregates without raw text — the same boundary, at scale.
Early access opens with the public launch.
10 — INSTALL
brew install lubosxyz/tap/cadencecadence scancadence serveor pip install cadence-report · Python 3.11+ · macOS companion ships with the public launchmacOS app from Releases