Token Burn

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

today · in flight

444K active

13 sessions · spend 800K · Claude Code 444K
by project: <home> 444K
top session c80bcdb2 (<home>, 37K, —)

2026-09-12
as of 2026-09-12T13:00:18Z

Stupid button · 29m ago · gemma4:e4b · 3323t in / 810t out · 38.0s

Trend vs last week

Accepted tokens are DOWN 14.5M (-100.0%) vs last week.
Unsettled tokens are UP 11.8M (1128.0%) vs last week.
Waste tokens are DOWN 931K (-61.8%) vs last week.

What worked

No projects show any accepted token burn this week.

What wasted tokens

las shows a 0.0 acceptance ratio, and 10.6M of its unsettled tokens are in the las/.worktrees/mvp path.
pal shows a 0.0 acceptance ratio, and 2.3M of its unsettled tokens are in the pal path.
The <home> project has 574K in waste tokens, but this is unmeasurable as it ran outside any git repo.

Why the big number is big

No agent fan-out this window.

What needs a verdict

las + 4b15a997 + 2026-09-08 + las/.worktrees/mvp + 4.0M: suggested_verdict is "review" (PR open — work in flight).
las + 4b15a997 + 2026-09-11 + las/.worktrees/mvp + 3.0M: suggested_verdict is "review" (PR open — work in flight).
las + 4b15a997 + 2026-09-09 + las/.worktrees/mvp + 2.7M: suggested_verdict is "review" (PR open — work in flight).
las + 4b15a997 + 2026-09-06 + las/.worktrees/mvp + 913K: suggested_verdict is "review" (PR open — work in flight).
pal + 01a07347 + 2026-09-08 + pal + 872K: suggested_verdict is "review" (open_loop, 872K burn — worth looking).
pal + 01a07347 + 2026-09-11 + pal + 448K: suggested_verdict is "not_useful" (open_loop, 448K burn — small miss).
pal + 01a07a8f + 2026-09-07 + pal + 192K: suggested_verdict is "not_useful" (open_loop, 192K burn — small miss).
pal + 01a07347 + 2026-09-07 + pal + 191K: suggested_verdict is "not_useful" (open_loop, 191K burn — small miss).

One contrarian observation

The <home> project has 574K in waste_active_h, but this is unmeasurable because it is noted as "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> (574K) 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 12.8M · acceptance 0%

spend 229.9M · 165 sessions · Claude Code 11.2M / Codex 2.3M

Last 30 days

14.5M accepted

unsettled 64.8M · acceptance 18%

spend 1.90B · 750 sessions · Claude Code 53.1M / Codex 28.3M

Last 90 days

14.5M accepted

unsettled 151.0M · acceptance 9%

spend 4.48B · 865 sessions · Codex 97.4M / Claude Code 70.2M

Daily heatmap — last 60 days

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

LessMore· log-scale, exact lane

Top 10 days

Date	Active	Spend	Sessions	Top project	Outcomes
2026-07-28	29.1M	1.09B	22	<home> (29.1M)	?=22
2026-08-18	22.3M	554.5M	38	<home> (21.6M)	?=43
2026-07-16	15.7M	522.1M	23	<home> (15.7M)	?=23
2026-08-06	11.1M	362.9M	27	<home> (11.1M)	?=27
2026-08-12	7.7M	116.0M	9	dreamweaver (6.5M)	?=11
2026-08-31	5.9M	144.8M	26	las (5.8M)	no_repo=24 · open_loop=3 · accepted=2 · PRs #18
2026-08-19	5.6M	205.7M	27	pal (2.3M)	?=36
2026-09-08	5.1M	47.8M	28	las (4.0M)	no_repo=24 · open_loop=3 · committed=1 · PRs #21
2026-08-29	4.5M	158.4M	30	las (1.7M)	?=31
2026-08-30	4.2M	72.4M	25	las (4.2M)	no_repo=24 · accepted=1 · PRs #18

By project — last 7 days

Project	Active
las	10.6M
pal	2.3M
<home>	574K

By outcome — last 7 days

committed 4 #21 (OPEN)

open_loop 10

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

Project	Accepted	Ratio
las	13.4M	47%
memory	1.1M	64%
pal	0	0%
mainstay-av	0	0%
pal/templari	0	0%
Downloads	0	0%

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

Project	Accepted	Ratio	Mix
<home>	0	0%
pal	0	0%
mainstay-av	0	0%
dreamweaver	0	0%
pal/dashboards	0	0%
tmp	0	0%

Needs validation — last 14 days (24 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.

Date	Project	Session	Active	Auto	cwd
2026-09-08	las	4b15a997	4.0M	committed · #21 (OPEN)	.../las/.worktrees/mvp
2026-09-11	las	4b15a997	3.0M	committed · #21 (OPEN)	.../las/.worktrees/mvp
2026-09-09	las	4b15a997	2.7M	committed · #21 (OPEN)	.../las/.worktrees/mvp
2026-09-06	las	4b15a997	913K	committed · #21 (OPEN)	.../las/.worktrees/mvp
2026-09-08	pal	01a07347	872K	open_loop	.../pal
2026-09-05	las	4b15a997	645K	open_loop	.../las/.worktrees/mvp
2026-09-11	pal	01a07347	448K	open_loop	.../pal
2026-09-07	pal	01a07a8f	192K	open_loop	.../pal
2026-09-07	pal	01a07347	191K	open_loop	.../pal
2026-09-11	pal	01a0925e	165K	open_loop	.../pal
2026-09-03	las	4b15a997	165K	open_loop	.../las/.worktrees/mvp
2026-09-11	pal	01a0925f	151K	open_loop	.../pal
2026-09-08	pal	01a07ec0	106K	open_loop	.../pal
2026-09-08	pal	01a07fb1	93K	open_loop	.../pal
2026-08-31	pal/templari	d33e7f08	61K	open_loop	.../pal/templari
2026-09-05	pal	01a07347	57K	open_loop	.../pal
2026-09-04	mainstay-av	d33e7f08	30K	open_loop	.../mainstay-av
2026-09-01	pal	5af22ad7	24K	open_loop	.../pal
2026-08-31	pal	5af22ad7	23K	open_loop	.../pal
2026-09-04	pal	d33e7f08	17K	open_loop	.../pal
2026-09-11	pal	01a0925e	17K	open_loop	.../pal
2026-09-11	pal	01a0888c	17K	open_loop	.../pal
2026-09-05	pal	01a0728d	13K	open_loop	.../pal
2026-08-31	pal	d33e7f08	10K	open_loop	.../pal

Recent events — last 30 rows

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

Date	Tool	Project	Session	Active	Output	Outcome
2026-09-12	CC	<home>	c80bcdb2	37K	2K	no_repo
2026-09-12	CC	<home>	2010a596	36K	1K	no_repo
2026-09-12	CC	<home>	bee278af	35K	800	no_repo
2026-09-12	CC	<home>	ba806488	35K	726	no_repo
2026-09-12	CC	<home>	127e381d	35K	678	no_repo
2026-09-12	CC	<home>	df7d0bc4	35K	666	no_repo
2026-09-12	CC	<home>	06e2843b	35K	530	no_repo
2026-09-12	CC	<home>	b82a1c61	35K	500	no_repo
2026-09-12	CC	<home>	98e587dd	35K	456	no_repo
2026-09-12	CC	<home>	11b4ab2c	34K	938	no_repo
2026-09-12	CC	<home>	77ab2d73	33K	562	no_repo
2026-09-12	CC	<home>	3a5ea22e	30K	770	no_repo
2026-09-11	CC	las	4b15a997	3.0M	100K	committed #21
2026-09-11	Codex	pal	01a07347	448K	8K	open_loop
2026-09-11	Codex	pal	01a0925e	165K	12K	open_loop
2026-09-11	Codex	pal	01a0925f	151K	6K	open_loop
2026-09-11	CC	<home>	ba7dbf94	34K	808	no_repo
2026-09-11	CC	<home>	e1d40db2	34K	682	no_repo
2026-09-11	CC	<home>	4523bf83	32K	792	no_repo
2026-09-11	CC	<home>	2061f6cd	31K	872	no_repo
2026-09-11	CC	<home>	84572c99	30K	634	no_repo
2026-09-11	Codex	pal	01a0925e	17K	176	open_loop
2026-09-11	Codex	pal	01a0888c	17K	489	open_loop
2026-09-11	CC	<home>	00313680	0	0	no_repo
2026-09-11	CC	<home>	10967d76	0	0	no_repo
2026-09-11	CC	<home>	1a262f90	0	0	no_repo
2026-09-11	CC	<home>	1b843c82	0	0	no_repo
2026-09-11	CC	<home>	1ea7e496	0	0	no_repo
2026-09-11	CC	<home>	21f7ef87	0	0	no_repo
2026-09-11	CC	<home>	250be392	0	0	no_repo

Generated 2026-09-12 13:00 UTC from ~/ideas/pal/dashboards/token_burn.jsonl (973 rows). Sources: ~/.codex/sessions/ (exact), ~/.claude/projects/-home-khoward/ (exact). No estimate lane currently active.