Token Burn

Burn is not proof. Output is not victory. Accepted work that repeats is leverage.

today · in flight
387K active
12 sessions · spend 717K · Claude Code 387K
by project: <home> 387K
top session bcc4ee84 (<home>, 36K, —)
2026-09-15
as of 2026-09-15T13:00:15Z
Stupid button · 30m ago · gemma4:e4b · 3170t in / 717t out · 38.8s

Trend vs last week

What worked

What wasted tokens

Why the big number is big

No agent fan-out this window.

What needs a verdict

One contrarian observation

The <home> project has the largest waste volume at 2.9M (waste_active_h), yet its acceptance_ratio is 0.0 because it is unmeasurable — ran outside any git repo, so 0.0 is the meter failing to see the work, not a judgement on it.

---

Measurability caveat (generated, not model-authored): <home> (2.9M) ran outside any git repo. There is no diff to credit, so a 0.0 acceptance ratio there is the meter failing to see the work — not a judgement on it. Only ratios on measurable: true projects are verdicts.

Rollups — acceptance lane

Headline is accepted tokens (active lane, manual label wins over git auto-classification). Unsettled = committed-not-merged + open-loop. "Active" excludes cache replay; "spend" includes it.

Last 7 days
0 accepted
unsettled 6.5M · acceptance 0%
spend 155.5M · 162 sessions · Claude Code 8.6M / Codex 799K
Last 30 days
3.4M accepted
unsettled 69.1M · acceptance 4%
spend 1.74B · 749 sessions · Claude Code 48.1M / Codex 28.3M
Last 90 days
3.4M accepted
unsettled 138.1M · acceptance 2%
spend 3.94B · 839 sessions · Codex 92.5M / Claude Code 52.9M

Daily heatmap — last 60 days

Each cell = one UTC day, color intensity = log10(active tokens). Hover for date + counts.

LessMore· log-scale, exact lane
29.1M on 07-28

Top 10 days

DateActiveSpend SessionsTop projectOutcomes
2026-07-2829.1M1.09B22<home> (29.1M)?=22
2026-08-1822.3M554.5M38<home> (21.6M)?=43
2026-07-1615.7M522.1M23<home> (15.7M)?=23
2026-08-0611.1M362.9M27<home> (11.1M)?=27
2026-08-315.9M144.8M26las (5.8M)?=29
2026-08-195.6M205.7M27pal (2.3M)?=36
2026-09-085.1M47.8M28las (4.0M)no_repo=24 · open_loop=3 · committed=1 · PRs #21
2026-08-294.5M158.4M30las (1.7M)?=31
2026-08-304.2M72.4M25las (4.2M)?=25
2026-09-044.1M90.1M29las (2.3M)no_repo=28 · accepted=3 · open_loop=2 · PRs #17

By project — last 7 days

ProjectActive 
las5.7M
<home>2.9M
pal799K

By outcome — last 7 days

committed 2 #21 (OPEN)
open_loop 5
no_repo 156

Effectiveness — last 30 days

Where delegated work shipped (top) vs. where high burn never crossed an acceptance line (bottom). Bars: accepted · unsettled · waste. Normalized to the widest project in window.

Leverage — most accepted

ProjectAcceptedRatioMix
las2.3M8%
memory1.1M93%
pal00%
mainstay-av00%
pal/templari00%
Downloads00%

Waste candidates — lowest acceptance ratio (≥100K active)

ProjectAcceptedRatioMix
<home>00%
pal00%
mainstay-av00%
pal/dashboards00%
pal/templari00%
las2.3M8%

Needs validation — last 14 days (20 unsettled)

Sessions where auto-classification couldn't tell shipped work from waste. Highest-burn first. Manually label these with `label: "used"|"partial"|"redo"|"review"|"not_useful"` in token_burn.jsonl to override the auto verdict.

DateProjectSessionActiveAutocwd
2026-09-08las4b15a9974.0Mcommitted · #21 (OPEN).../las/.worktrees/mvp
2026-09-11las4b15a9973.0Mcommitted · #21 (OPEN).../las/.worktrees/mvp
2026-09-09las4b15a9972.7Mcommitted · #21 (OPEN).../las/.worktrees/mvp
2026-09-06las4b15a997913Kcommitted · #21 (OPEN).../las/.worktrees/mvp
2026-09-08pal01a07347872Kopen_loop.../pal
2026-09-05las4b15a997645Kopen_loop.../las/.worktrees/mvp
2026-09-11pal01a07347448Kopen_loop.../pal
2026-09-07pal01a07a8f192Kopen_loop.../pal
2026-09-07pal01a07347191Kopen_loop.../pal
2026-09-11pal01a0925e165Kopen_loop.../pal
2026-09-03las4b15a997165Kopen_loop.../las/.worktrees/mvp
2026-09-11pal01a0925f151Kopen_loop.../pal
2026-09-08pal01a07ec0106Kopen_loop.../pal
2026-09-08pal01a07fb193Kopen_loop.../pal
2026-09-05pal01a0734757Kopen_loop.../pal
2026-09-04mainstay-avd33e7f0830Kopen_loop.../mainstay-av
2026-09-04pald33e7f0817Kopen_loop.../pal
2026-09-11pal01a0925e17Kopen_loop.../pal
2026-09-11pal01a0888c17Kopen_loop.../pal
2026-09-05pal01a0728d13Kopen_loop.../pal

Recent events — last 30 rows

Latest enriched rows from the JSONL (sorted by date desc, active desc as tiebreaker). M = manually labeled.

DateToolProjectSessionActiveOutputOutcome
2026-09-15CC<home>bcc4ee8436K776no_repo
2026-09-15CC<home>4efe751e35K1Kno_repo
2026-09-15CC<home>b388517835K668no_repo
2026-09-15CC<home>86ef8a8535K944no_repo
2026-09-15CC<home>a47907ac34K786no_repo
2026-09-15CC<home>1fa0e32634K608no_repo
2026-09-15CC<home>fe72662334K456no_repo
2026-09-15CC<home>b587cdad32K954no_repo
2026-09-15CC<home>a3d49b4430K684no_repo
2026-09-15CC<home>ddc445d428K688no_repo
2026-09-15CC<home>5287705c28K674no_repo
2026-09-15CC<home>2bf881bb27K1Kno_repo
2026-09-14CC<home>87040a5336K1Kno_repo
2026-09-14CC<home>f11b5bf535K972no_repo
2026-09-14CC<home>83eefaca35K844no_repo
2026-09-14CC<home>3995e71135K776no_repo
2026-09-14CC<home>f0eb22b335K604no_repo
2026-09-14CC<home>84a2e5c535K632no_repo
2026-09-14CC<home>bd2313ad34K570no_repo
2026-09-14CC<home>89d4a38632K1Kno_repo
2026-09-14CC<home>89a569de32K1Kno_repo
2026-09-14CC<home>b34f50cd31K730no_repo
2026-09-14CC<home>21a6a90b31K666no_repo
2026-09-14CC<home>0c186f4831K550no_repo
2026-09-14CC<home>a02f173031K534no_repo
2026-09-14CC<home>b586aeab31K494no_repo
2026-09-14CC<home>cc5da68931K1Kno_repo
2026-09-14CC<home>3cc3b69930K906no_repo
2026-09-14CC<home>baefc19230K830no_repo
2026-09-14CC<home>086a912a30K748no_repo

Generated 2026-09-15 13:00 UTC from ~/ideas/pal/dashboards/token_burn.jsonl (931 rows). Sources: ~/.codex/sessions/ (exact), ~/.claude/projects/-home-khoward/ (exact). No estimate lane currently active.