Token Burn

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

today · in flight

2.1M active

14 sessions · spend 21.7M · Claude Code 2.1M
by project: las 1.6M · <home> 459K
top session 4b15a997 (las, 1.6M, —)

2026-09-16
as of 2026-09-16T12:55:09Z

Stupid button · 24m ago · gemma4:e4b · 3172t in / 757t out · 44.6s

Trend vs last week

Accepted tokens dropped by 3.4M (-100.0%) vs last week.
Unsettled tokens dropped by 4.6M (-46.2%) vs last week.
Waste tokens increased by 2.7M (268.1%) vs last week.

What worked

No projects show any accepted active burn this week.

What wasted tokens

las: 0.0 acceptance ratio.
<home>: 0.0 acceptance ratio. This is unmeasurable — ran outside any git repo, so 0.0 is the meter failing to see the work, not a judgement on it.
pal: 0.0 acceptance ratio.
The largest waste volume is in <home> at 3.7M (waste_active_h).
The next largest waste volume is in las at 4.6M (unsettled_active_h).

Why the big number is big

No agent fan-out this window.

What needs a verdict

las + 4b15a997 + 2026-09-11 + las/.worktrees/mvp + 3.0M: suggested_verdict is "review" because "PR open — work in flight".
las + 4b15a997 + 2026-09-16 + las/.worktrees/mvp + 1.6M: suggested_verdict is "review" because "PR open — work in flight".
pal + 01a07347 + 2026-09-11 + pal + 448K: suggested_verdict is "not_useful" because "open_loop, 448K burn — small miss".
pal + 01a0925e + 2026-09-11 + pal + 165K: suggested_verdict is "not_useful" because "open_loop, 165K burn — small miss".
pal + 01a0925f + 2026-09-11 + pal + 151K: suggested_verdict is "not_useful" because "open_loop, 151K burn — small miss".
pal + 01a0925e + 2026-09-11 + pal + 17K: suggested_verdict is "not_useful" because "open_loop, 17K burn — small miss".
pal + 01a0888c + 2026-09-11 + pal + 17K: suggested_verdict is "not_useful" because "open_loop, 17K burn — small miss".

One contrarian observation

The <home> project shows a massive 3.7M in waste_active_h but its acceptance_ratio is 0.0 due to it being unmeasurable.

---

Measurability caveat (generated, not model-authored): <home> (3.7M) 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 5.4M · acceptance 0%

spend 97.3M · 162 sessions · Claude Code 8.3M / Codex 799K

Last 30 days

3.4M accepted

unsettled 67.2M · acceptance 4%

spend 1.72B · 747 sessions · Claude Code 50.2M / Codex 25.1M

Last 90 days

3.4M accepted

unsettled 139.7M · acceptance 2%

spend 3.96B · 839 sessions · Codex 92.5M / Claude Code 55.4M

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
2026-08-31	5.9M	144.8M	26	las (5.8M)	?=29
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)	?=25
2026-09-04	4.1M	90.1M	29	las (2.3M)	no_repo=28 · accepted=3 · open_loop=2 · PRs #17

By project — last 7 days

Project	Active
las	4.6M
<home>	3.7M
pal	799K

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

Project	Accepted	Ratio
las	2.3M	8%
memory	1.1M	93%
pal	0	0%
mainstay-av	0	0%
pal/templari	0	0%
Downloads	0	0%

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

Project	Accepted	Ratio
<home>	0	0%
pal	0	0%
mainstay-av	0	0%
pal/dashboards	0	0%
pal/templari	0	0%
las	2.3M	8%

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.

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
2026-09-16	las	4b15a997	1.6M	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
2026-09-05	pal	01a07347	57K	open_loop	.../pal
2026-09-04	mainstay-av	d33e7f08	30K	open_loop	.../mainstay-av
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

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
2026-09-16	CC	las	4b15a997	1.6M	37K	committed #21
2026-09-16	CC	<home>	a89743e6	36K	1K	no_repo
2026-09-16	CC	<home>	cbc99b9c	36K	938	no_repo
2026-09-16	CC	<home>	fdd108ac	36K	826	no_repo
2026-09-16	CC	<home>	fa261137	36K	752	no_repo
2026-09-16	CC	<home>	1260d1db	36K	722	no_repo
2026-09-16	CC	<home>	ea67c5bc	36K	672	no_repo
2026-09-16	CC	<home>	9d3c3a93	35K	604	no_repo
2026-09-16	CC	<home>	00d50af9	35K	532	no_repo
2026-09-16	CC	<home>	8b570a41	35K	496	no_repo
2026-09-16	CC	<home>	f9ad4127	35K	786	no_repo
2026-09-16	CC	<home>	6086d1ea	35K	704	no_repo
2026-09-16	CC	<home>	905a49c7	35K	684	no_repo
2026-09-16	CC	<home>	7f50714f	34K	484	no_repo
2026-09-15	CC	<home>	c5b73649	36K	952	no_repo
2026-09-15	CC	<home>	f1c2b87a	36K	946	no_repo
2026-09-15	CC	<home>	25b14cc9	36K	828	no_repo
2026-09-15	CC	<home>	bcc4ee84	36K	776	no_repo
2026-09-15	CC	<home>	16afd928	35K	704	no_repo
2026-09-15	CC	<home>	4efe751e	35K	1K	no_repo
2026-09-15	CC	<home>	b3885178	35K	668	no_repo
2026-09-15	CC	<home>	4d6f2cd4	35K	1K	no_repo
2026-09-15	CC	<home>	86ef8a85	35K	944	no_repo
2026-09-15	CC	<home>	488a6900	35K	934	no_repo
2026-09-15	CC	<home>	c5d59336	35K	810	no_repo
2026-09-15	CC	<home>	c5d61782	35K	722	no_repo
2026-09-15	CC	<home>	f2cde86e	34K	594	no_repo
2026-09-15	CC	<home>	318787b8	34K	516	no_repo
2026-09-15	CC	<home>	a47907ac	34K	786	no_repo
2026-09-15	CC	<home>	1fa0e326	34K	608	no_repo

Generated 2026-09-16 12:55 UTC from ~/ideas/pal/dashboards/token_burn.jsonl (932 rows). Sources: ~/.codex/sessions/ (exact), ~/.claude/projects/-home-khoward/ (exact). No estimate lane currently active.