Token Burn

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

today · in flight

465K active

13 sessions · spend 821K · Claude Code 465K
by project: <home> 465K
top session 3ef4a144 (<home>, 36K, —)

2026-09-26
as of 2026-09-26T13:00:09Z

Stupid button · 28m ago · gemma4:e4b · 2274t in / 369t out · 63.3s

Trend vs last week

Unsettled is DOWN 974K (-60.4%) vs last week.
Waste is DOWN 117K (-2.0%) vs last week.
Accepted shows no prior-window comparison.

What worked

No projects show any accepted burn this week.

What wasted tokens

The <home> project shows 0.0 acceptance ratio. Its acceptance_note states: "UNMEASURABLE — ran outside any git repo, so 0.0 is the meter failing to see the work, not a judgement on it". This accounts for the 5.6M waste.
The pal project shows 0.0 acceptance ratio.
The largest waste volume is in <home> at 5.6M.

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 pal project has 637K in unsettled tokens, despite having 0.0 acceptance ratio, suggesting a significant commitment of unmerged work.

---

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 38.4M · acceptance 0%

spend 852.0M · 732 sessions · Claude Code 44.4M / Codex 5.3M

Last 90 days

0 accepted

unsettled 131.4M · acceptance 0%

spend 3.71B · 842 sessions · Codex 87.6M / Claude Code 55.1M

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)	?=30

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%
<home>	0	0%
pal	0	0%
mainstay-av	0	0%
memory	0	0%

Needs validation — last 14 days (3 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
2026-09-16	las	4b15a997	1.6M	committed · #21 (OPEN)	.../las/.worktrees/mvp
2026-09-23	pal	01a0cd8d	479K	open_loop	.../pal
2026-09-23	pal	01a07347	159K	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
2026-09-26	CC	<home>	3ef4a144	36K	944	no_repo
2026-09-26	CC	<home>	25de6a5c	36K	906	no_repo
2026-09-26	CC	<home>	a7a1f150	36K	820	no_repo
2026-09-26	CC	<home>	579e6840	36K	798	no_repo
2026-09-26	CC	<home>	cdf07fbc	36K	694	no_repo
2026-09-26	CC	<home>	5064bd8f	36K	670	no_repo
2026-09-26	CC	<home>	4a617052	36K	644	no_repo
2026-09-26	CC	<home>	419b8f77	36K	606	no_repo
2026-09-26	CC	<home>	b7f2127c	36K	574	no_repo
2026-09-26	CC	<home>	31b22860	36K	506	no_repo
2026-09-26	CC	<home>	3add83e1	36K	488	no_repo
2026-09-26	CC	<home>	8fc59614	36K	840	no_repo
2026-09-25	CC	<home>	717b8991	36K	1K	no_repo
2026-09-25	CC	<home>	67710a09	36K	1K	no_repo
2026-09-25	CC	<home>	d3f6dc65	36K	1K	no_repo
2026-09-25	CC	<home>	6de5f7aa	36K	1K	no_repo
2026-09-25	CC	<home>	5b98672d	36K	914	no_repo
2026-09-25	CC	<home>	27e83734	36K	1K	no_repo
2026-09-25	CC	<home>	b94c0ad6	36K	836	no_repo
2026-09-25	CC	<home>	02de3196	36K	812	no_repo
2026-09-25	CC	<home>	7b52297f	36K	852	no_repo
2026-09-25	CC	<home>	ad4c36d7	36K	750	no_repo
2026-09-25	CC	<home>	5841c6de	36K	734	no_repo
2026-09-25	CC	<home>	72cdd35a	36K	834	no_repo
2026-09-25	CC	<home>	0acc926f	36K	830	no_repo
2026-09-25	CC	<home>	c486de93	36K	798	no_repo
2026-09-25	CC	<home>	0653e172	36K	796	no_repo
2026-09-25	CC	<home>	6125d592	36K	780	no_repo
2026-09-25	CC	<home>	b9d67cf1	36K	766	no_repo
2026-09-25	CC	<home>	cb05371e	36K	746	no_repo

Generated 2026-09-26 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.