Token Burn

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

today · in flight
0 active
13 sessions · spend 0 · Claude Code 0
by project: <home> 0
top session 103ed8a5 (<home>, 0, —)
2026-09-05
as of 2026-09-05T12:55:22Z
Stupid button · 23m ago · gemma4:e4b · 3378t in / 860t out · 145.3s

Trend vs last week

What worked

What wasted tokens

Why the big number is big

A subagent spawn forks its parent, so the child starts holding the parent's whole transcript and the same conversation is charged once per fork, on every turn. The root 01a04b01-5edc involved 6 threads, 3 forks, and a max depth of 1, charging 33.8M. The agents involved were Chandrasekhar, Faraday, Harvey, James, and Pascal.

What needs a verdict

One contrarian observation

The <home> project shows 1.1M in waste tokens, but its acceptance_ratio of 0.0 is due to it being 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> (1.1M) 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
14.5M accepted
unsettled 330K · acceptance 91%
spend 397.4M · 162 sessions · Claude Code 15.4M / Codex 601K
Last 30 days
16.2M accepted
unsettled 75.9M · acceptance 17%
spend 2.72B · 743 sessions · Claude Code 68.5M / Codex 26.9M
Last 90 days
16.2M accepted
unsettled 158.5M · acceptance 9%
spend 5.25B · 881 sessions · Codex 96.6M / Claude Code 81.5M

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
2026-08-0616.5M592.1M51<home> (12.0M)?=58
2026-07-1615.7M522.1M23<home> (15.7M)?=23
2026-08-127.7M116.0M25dreamweaver (6.5M)?=27
2026-08-086.1M358.6M27dreamweaver (3.0M)?=37
2026-08-076.0M352.8M28<home> (4.1M)?=35
2026-08-315.9M144.8M26las (5.8M)no_repo=24 · open_loop=3 · accepted=2 · PRs #18
2026-06-155.9M132.6M9<home> (5.9M)?=9
2026-08-195.6M205.7M27pal (2.3M)?=36

By project — last 7 days

ProjectActive 
las13.5M
<home>1.1M
memory1.1M
pal74K
pal/templari61K
mainstay-av30K

By outcome — last 7 days

accepted 8 #17 (MERGED), #19 (MERGED), #18 (MERGED)
open_loop 7
no_repo 161

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
las15.0M86%
memory1.1M52%
mainstay-av00%
pal00%
pal/templari00%
templari00%

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

ProjectAcceptedRatioMix
<home>00%
dreamweaver00%
pal00%
mainstay-av00%
pal/placeholders00%
pal/dashboards00%

Needs validation — last 14 days (21 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
2026-08-29mainstay-av5af22ad71.6Mopen_loop.../mainstay-av/docs/entity
2026-08-28lasd33e7f08689Kopen_loop.../las
2026-09-03las4b15a997165Kopen_loop.../las/.worktrees/mvp
2026-08-24lasd33e7f08146Kopen_loop.../las
2026-08-23pald33e7f0868Kopen_loop.../pal
2026-08-31pal/templarid33e7f0861Kopen_loop.../pal/templari
2026-09-04mainstay-avd33e7f0830Kopen_loop.../mainstay-av
2026-08-24mainstay-avd33e7f0828Kopen_loop.../mainstay-av/apps/worker
2026-08-24pald33e7f0827Kopen_loop.../pal
2026-08-24templarid33e7f0827Kopen_loop.../templari
2026-09-01pal5af22ad724Kopen_loop.../pal
2026-08-23memoryd33e7f0823Kopen_loop/home/khoward/.claude/projects/-home-khoward/memory
2026-08-31pal5af22ad723Kopen_loop.../pal
2026-09-04pald33e7f0817Kopen_loop.../pal
2026-08-23pal/memoryd33e7f0814Kopen_loop.../pal/memory
2026-08-23pal/templarid33e7f0811Kopen_loop.../pal/templari
2026-08-31pald33e7f0810Kopen_loop.../pal
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
2026-09-05CC<home>103ed8a500no_repo
2026-09-05CC<home>19f6220600no_repo
2026-09-05CC<home>5379f2b800no_repo
2026-09-05CC<home>7a0b538b00no_repo
2026-09-05CC<home>97304b4600no_repo
2026-09-05CC<home>9dd2c1b100no_repo
2026-09-05CC<home>9de36c2500no_repo
2026-09-05CC<home>a6fdaac700no_repo
2026-09-05CC<home>dbdc142a00no_repo
2026-09-05CC<home>e707ee4b00no_repo
2026-09-05CC<home>eb6d512400no_repo
2026-09-05CC<home>f65545cb00no_repo
2026-09-04CClas4b15a9971.3M107Kaccepted #17
2026-09-04CCmemoryd33e7f081.1M52Kaccepted
2026-09-04CClasd33e7f081.0M80Kaccepted #17
2026-09-04Codex<home>01a04b01353K25Kno_repo
2026-09-04Codex<home>01a06bbe144K5Kno_repo
2026-09-04Codex<home>01a06bbe103K6Kno_repo
2026-09-04CC<home>d33e7f0838K19Kno_repo
2026-09-04CCmainstay-avd33e7f0830K15Kopen_loop
2026-09-04CCpald33e7f0817K6Kopen_loop
2026-09-04CC<home>023bc3d700no_repo
2026-09-04CC<home>1d1aabf100no_repo
2026-09-04CC<home>23068ad800no_repo
2026-09-04CC<home>273f3c9700no_repo
2026-09-04CC<home>40611dd800no_repo
2026-09-04CC<home>4484c91300no_repo
2026-09-04CC<home>505bdaf800no_repo
2026-09-04CC<home>55fd977300no_repo
2026-09-04CC<home>56880df500no_repo

Generated 2026-09-05 12:55 UTC from ~/ideas/pal/dashboards/token_burn.jsonl (1009 rows). Sources: ~/.codex/sessions/ (exact), ~/.claude/projects/-home-khoward/ (exact). No estimate lane currently active.