Token Burn

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

today · in flight

468K active

13 sessions · spend 824K · Claude Code 468K
by project: <home> 468K
top session cd8257fb (<home>, 36K, —)

2026-09-24
as of 2026-09-24T13:00:30Z

Stupid button · 29m ago · gemma4:e4b · 2276t in / 348t out · 56.7s

Trend vs last week

Unsettled volume dropped by 4.7M (-88.1%) vs last week.
Waste increased by 596K (12.0%) vs last week.
Accepted volume shows no prior-window comparison.

What worked

No projects show any accepted active burn.

What wasted tokens

The <home> directory shows 0.0 acceptance ratio. Note: UNMEASURABLE — ran outside any git repo, so 0.0 is the meter failing to see the work, not a judgement on it. It accounts for 5.6M in waste.
The pal project shows 0.0 acceptance ratio. It accounts for 0 in waste.

Why the big number is big

No agent fan-out this window.

What needs a verdict

pal + 01a0cd8d + 2026-09-23 + pal + 479K: suggested_verdict is "not_useful". Reason: open_loop, 479K burn — small miss.
pal + 01a07347 + 2026-09-23 + pal + 159K: suggested_verdict is "not_useful". Reason: open_loop, 159K burn — small miss.

One contrarian observation

The <home> directory generated 5.6M in waste while having an acceptance ratio of 0.0, which is attributed to being unmeasurable.

---

Measurability caveat (generated, not model-authored): <home> (5.6M) 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 638K · acceptance 0%

spend 18.6M · 158 sessions · Claude Code 5.6M / Codex 638K

Last 30 days

0 accepted

unsettled 37.4M · acceptance 0%

spend 849.0M · 732 sessions · Claude Code 42.6M / Codex 5.3M

Last 90 days

0 accepted

unsettled 130.5M · acceptance 0%

spend 3.71B · 842 sessions · Codex 87.6M / Claude Code 53.4M

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	21.2M	527.5M	12	<home> (21.0M)	?=14
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
2026-09-08	5.1M	47.8M	28	las (4.0M)	?=28
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)	?=33
2026-09-11	3.9M	69.9M	30	las (3.0M)	no_repo=24 · open_loop=5 · committed=1 · PRs #21

By project — last 7 days

Project	Active
<home>	5.6M
pal	638K

By outcome — last 7 days

open_loop 2

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	Mix
pal	0	0%
las	0	0%
memory	0	0%
mainstay-av	0	0%
pal/templari	0	0%
<home>	0	0%

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

Project	Accepted	Ratio	Mix
las	0	0%
pal	0	0%
<home>	0	0%
mainstay-av	0	0%
memory	0	0%

Needs validation — last 14 days (9 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
2026-09-11	las	4b15a997	3.0M	committed · #21 (OPEN)	.../las/.worktrees/mvp
2026-09-16	las	4b15a997	1.6M	committed · #21 (OPEN)	.../las/.worktrees/mvp
2026-09-23	pal	01a0cd8d	479K	open_loop	.../pal
2026-09-11	pal	01a07347	448K	open_loop	.../pal
2026-09-11	pal	01a0925e	165K	open_loop	.../pal
2026-09-23	pal	01a07347	159K	open_loop	.../pal
2026-09-11	pal	01a0925f	151K	open_loop	.../pal
2026-09-11	pal	01a0925e	17K	open_loop	.../pal
2026-09-11	pal	01a0888c	17K	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
2026-09-24	CC	<home>	717cc406	36K	1K	no_repo
2026-09-24	CC	<home>	e81dedde	36K	800	no_repo
2026-09-24	CC	<home>	880622ff	36K	808	no_repo
2026-09-24	CC	<home>	37012f9f	36K	798	no_repo
2026-09-24	CC	<home>	d394c4fd	36K	774	no_repo
2026-09-24	CC	<home>	5fcc5ffe	36K	762	no_repo
2026-09-24	CC	<home>	052c3a1d	36K	728	no_repo
2026-09-24	CC	<home>	7e281b0b	36K	704	no_repo
2026-09-24	CC	<home>	60577568	36K	692	no_repo
2026-09-24	CC	<home>	8649212b	36K	660	no_repo
2026-09-24	CC	<home>	7a3ee18c	36K	620	no_repo
2026-09-24	CC	<home>	c6a0038b	36K	590	no_repo
2026-09-23	Codex	pal	01a0cd8d	479K	3K	open_loop
2026-09-23	Codex	pal	01a07347	159K	17K	open_loop
2026-09-23	CC	<home>	cfcc3870	37K	2K	no_repo
2026-09-23	CC	<home>	ffe185e6	36K	1K	no_repo
2026-09-23	CC	<home>	0ffe6769	36K	1K	no_repo
2026-09-23	CC	<home>	ff5e4b03	36K	1K	no_repo
2026-09-23	CC	<home>	c70c56a1	36K	950	no_repo
2026-09-23	CC	<home>	7538d5ae	36K	936	no_repo
2026-09-23	CC	<home>	b3aac828	36K	924	no_repo
2026-09-23	CC	<home>	6d0125de	36K	826	no_repo
2026-09-23	CC	<home>	2f8f088d	36K	852	no_repo
2026-09-23	CC	<home>	5d6c082d	36K	768	no_repo
2026-09-23	CC	<home>	6459f2e8	36K	758	no_repo
2026-09-23	CC	<home>	1fb58060	36K	760	no_repo
2026-09-23	CC	<home>	a42d1863	36K	744	no_repo
2026-09-23	CC	<home>	bb1f34a4	36K	728	no_repo
2026-09-23	CC	<home>	c05b66d8	36K	514	no_repo
2026-09-23	CC	<home>	54809d59	36K	670	no_repo

Generated 2026-09-24 13:00 UTC from ~/ideas/pal/dashboards/token_burn.jsonl (911 rows). Sources: ~/.codex/sessions/ (exact), ~/.claude/projects/-home-khoward/ (exact). No estimate lane currently active.