Token Burn

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

today · in flight
714K active
14 sessions · spend 7.2M · Claude Code 714K
by project: las 689K · <home> 19K · pal/templari 4K
top session d33e7f08 (las, 689K, —)
2026-08-28
as of 2026-08-28T13:00:18Z
Stupid button · 29m ago · gemma4:e4b · 3337t in / 838t out · 119.3s

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 160 sessions but 0.0 acceptance ratio, with the note: "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> (892K) 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 4.6M · acceptance 0%
spend 90.5M · 161 sessions · Claude Code 5.5M / Codex 47K
Last 30 days
8.7M accepted
unsettled 131.3M · acceptance 5%
spend 7.17B · 668 sessions · Claude Code 131.1M / Codex 36.2M
Last 90 days
8.7M accepted
unsettled 282.4M · acceptance 3%
spend 11.73B · 798 sessions · Claude Code 211.0M / Codex 107.3M

Daily heatmap — last 60 days

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

LessMore· log-scale, exact lane
34.5M on 07-28

Top 10 days

DateActiveSpend SessionsTop projectOutcomes
2026-07-2834.5M1.78B42<home> (29.6M)?=45
2026-08-0124.5M1.57B10payday (6.1M)?=20
2026-07-1623.3M797.0M24<home> (16.3M)?=27
2026-07-3123.1M2.10B9payday (8.1M)?=34
2026-08-1822.3M554.5M38<home> (21.6M)no_repo=38 · accepted=5 · PRs #27
2026-07-3019.4M645.3M26payday (16.5M)?=31
2026-07-2118.3M337.5M2<home> (9.1M)?=4
2026-08-0616.5M592.1M51<home> (12.0M)?=58
2026-07-2911.2M118.2M25payday (10.8M)?=27
2026-07-2410.3M401.9M2las (5.9M)?=4

By project — last 7 days

ProjectActive 
mainstay-av3.6M
<home>892K
las835K
pal97K
Downloads83K
templari27K
memory23K
pal/templari14K
pal/memory14K
ideas2K

By outcome — last 7 days

committed 1 #17 (OPEN)
open_loop 13
no_repo 163

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
pal4.6M51%
pal/dashboards1.7M100%
las1.4M45%
memory606K39%
pal/templari427K97%
mainstay-av00%

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

ProjectAcceptedRatioMix
dreamweaver00%
<home>00%
payday00%
panacea-ai00%
mainstay-av00%
pal/placeholders00%

Needs validation — last 14 days (22 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
2026-08-24mainstay-av5af22ad71.8Mopen_loop.../mainstay-av/docs/entity
2026-08-22mainstay-av5af22ad71.8Mopen_loop.../mainstay-av/docs/entity
2026-08-21pal5af22ad71.4Mopen_loop.../pal
2026-08-28lasd33e7f08689Kcommitted · #17 (OPEN).../las
2026-08-20pal5af22ad7476Kopen_loop.../pal
2026-08-17pal83ba2858388Kopen_loop.../pal
2026-08-21mainstay-av5af22ad7233Kopen_loop.../mainstay-av/docs/entity
2026-08-24lasd33e7f08146Kopen_loop.../las
2026-08-23pald33e7f0868Kopen_loop.../pal
2026-08-16panacea-ai83ba285853Kopen_loop.../panacea-ai
2026-08-16dreamweaver83ba285841Kopen_loop.../dreamweaver
2026-08-24mainstay-avd33e7f0828Kopen_loop.../mainstay-av/apps/worker
2026-08-24pald33e7f0827Kopen_loop.../pal
2026-08-24templarid33e7f0827Kopen_loop.../templari
2026-08-19dreamweaver5af22ad725Kopen_loop.../dreamweaver
2026-08-23memoryd33e7f0823Kopen_loop/home/khoward/.claude/projects/-home-khoward/memory
2026-08-23pal/memoryd33e7f0814Kopen_loop.../pal/memory
2026-08-23pal/templarid33e7f0811Kopen_loop.../pal/templari
2026-08-15memory83ba28586Kopen_loop/home/khoward/.claude/projects/-home-khoward/memory
2026-08-28pal/templarid33e7f084Kopen_loop.../pal/templari
2026-08-28pald33e7f082Kopen_loop.../pal
2026-08-23ideasd33e7f082Kopen_loop/home/khoward/ideas

Recent events — last 30 rows

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

DateToolProjectSessionActiveOutputOutcome
2026-08-28CClasd33e7f08689K8Kcommitted #17
2026-08-28Codex<home>01a0462420K1Kno_repo
2026-08-28CC<home>d33e7f0819K8Kno_repo
2026-08-28Codex<home>01a0462514K2Kno_repo
2026-08-28Codex<home>01a0462513K800no_repo
2026-08-28CCpal/templarid33e7f084K892open_loop
2026-08-28CCpald33e7f082K786open_loop
2026-08-28CC<home>1baede9800no_repo
2026-08-28CC<home>1d3ae78200no_repo
2026-08-28CC<home>23cf70c900no_repo
2026-08-28CC<home>54d3dad400no_repo
2026-08-28CC<home>707e745c00no_repo
2026-08-28CC<home>a604787500no_repo
2026-08-28CC<home>aac7209900no_repo
2026-08-28CC<home>bb46d30300no_repo
2026-08-28CC<home>d117989f00no_repo
2026-08-28CC<home>d20c12d500no_repo
2026-08-28CC<home>d3202d2000no_repo
2026-08-28CC<home>f43b9fd700no_repo
2026-08-27CC<home>0d50397000no_repo
2026-08-27CC<home>267a3c4000no_repo
2026-08-27CC<home>27e041fa00no_repo
2026-08-27CC<home>2d3282eb00no_repo
2026-08-27CC<home>51fcbda200no_repo
2026-08-27CC<home>569df9d900no_repo
2026-08-27CC<home>5e678fc800no_repo
2026-08-27CC<home>6993516100no_repo
2026-08-27CC<home>7d18896100no_repo
2026-08-27CC<home>871b5fb300no_repo
2026-08-27CC<home>912c1bd900no_repo

Generated 2026-08-28 13:00 UTC from ~/ideas/pal/dashboards/token_burn.jsonl (989 rows). Sources: ~/.codex/sessions/ (exact), ~/.claude/projects/-home-khoward/ (exact). No estimate lane currently active.