Token Burn

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

today · in flight

451K active

13 sessions · spend 817K · Claude Code 451K
by project: <home> 451K
top session dfa9aaa2 (<home>, 35K, —)

2026-10-13
as of 2026-10-13T13:00:07Z

Stupid button · 27m ago · gemma4:e4b · 2581t in / 509t out · 61.7s

Trend vs last week

Accepted tokens are down 59K (-55.6%) vs last week.
Unsettled tokens increased by 1.6M (1.6M) with no prior-window comparison.
Waste tokens increased by 2.1M (2.1M) (247.0%) vs last week.

What worked

pal accounted for the accepted burn, totaling 47K.

What wasted tokens

dreamweaver shows a 0.0 acceptance ratio, and this is unmeasurable — ran outside any git repo, so 0.0 is the meter failing to see the work, not a judgement on it.
<home> shows a 0.0 acceptance ratio, and this is unmeasurable — ran outside any git repo, so 0.0 is the meter failing to see the work, not a judgement on it.
The largest waste volume is in <home> at 2.9M.

Why the big number is big

No agent fan-out this window.

What needs a verdict

dreamweaver + 392618c3 + 2026-10-11 + dreamweaver/.worktrees/auth-fastpath + 780K: suggested_verdict is "review" (PR open — work in flight).
pal + 392618c3 + 2026-10-10 + pal + 683K: suggested_verdict is "review" (open_loop, 683K burn — worth looking).
dreamweaver + 392618c3 + 2026-10-10 + dreamweaver + 123K: suggested_verdict is "not_useful" (open_loop, 123K burn — small miss).

One contrarian observation

The <home> project has a 2.9M waste volume but its acceptance ratio is 0.0, and this is 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> (2.9M) 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

47K accepted

unsettled 1.6M · acceptance 1%

spend 36.1M · 76 sessions · Claude Code 4.5M

Last 30 days

154K accepted

unsettled 14.4M · acceptance 1%

spend 94.9M · 403 sessions · Claude Code 17.7M / Codex 638K

Last 90 days

154K accepted

unsettled 112.4M · acceptance 0%

spend 2.89B · 522 sessions · Codex 85.0M / Claude Code 31.3M

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	20.5M	517.2M	11	<home> (20.5M)	?=11
2026-07-16	14.5M	455.7M	22	<home> (14.5M)	?=22
2026-08-06	11.1M	362.9M	27	<home> (11.1M)	?=27
2026-09-08	5.1M	47.8M	4	las (4.0M)	?=4
2026-09-11	3.8M	69.6M	6	las (3.0M)	?=6
2026-08-17	3.1M	42.5M	4	<home> (3.1M)	?=4
2026-09-09	2.7M	80.5M	1	las (2.7M)	?=1
2026-09-16	2.5M	22.4M	25	las (1.6M)	?=25
2026-09-04	1.9M	34.5M	4	las (1.3M)	?=4

By project — last 7 days

Project	Active
<home>	2.9M
dreamweaver	903K
pal	731K

By outcome — last 7 days

accepted 1

committed 1 #527 (OPEN)

open_loop 2

no_repo 76

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
dreamweaver	107K	11%
pal	47K	3%
las	0	0%
<home>	0	0%

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

Project	Accepted	Ratio
<home>	0	0%
las	0	0%
pal	47K	3%
dreamweaver	107K	11%

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
2026-10-11	dreamweaver	392618c3	780K	committed · #527 (OPEN)	.../dreamweaver/.worktrees/auth-fastpath
2026-10-10	pal	392618c3	683K	open_loop	.../pal
2026-10-10	dreamweaver	392618c3	123K	open_loop	.../dreamweaver

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
2026-10-13	CC	<home>	dfa9aaa2	35K	1K	no_repo
2026-10-13	CC	<home>	cdc38d10	35K	850	no_repo
2026-10-13	CC	<home>	0fac0796	35K	806	no_repo
2026-10-13	CC	<home>	d8c3a686	35K	786	no_repo
2026-10-13	CC	<home>	04d38fca	35K	754	no_repo
2026-10-13	CC	<home>	f24ddc26	35K	740	no_repo
2026-10-13	CC	<home>	8dceaea1	35K	704	no_repo
2026-10-13	CC	<home>	540b0ce8	35K	608	no_repo
2026-10-13	CC	<home>	093475f1	35K	586	no_repo
2026-10-13	CC	<home>	11732ef8	35K	570	no_repo
2026-10-13	CC	<home>	ce5ddcdb	35K	482	no_repo
2026-10-13	CC	<home>	0a439937	33K	596	no_repo
2026-10-12	CC	<home>	2b0393a1	35K	1K	no_repo
2026-10-12	CC	<home>	ba3e9145	35K	962	no_repo
2026-10-12	CC	<home>	c50d8a98	35K	934	no_repo
2026-10-12	CC	<home>	816661bf	35K	934	no_repo
2026-10-12	CC	<home>	482a79a6	35K	912	no_repo
2026-10-12	CC	<home>	7f0151c5	35K	834	no_repo
2026-10-12	CC	<home>	a1b676f2	35K	794	no_repo
2026-10-12	CC	<home>	b3faef42	35K	784	no_repo
2026-10-12	CC	<home>	3c349b43	35K	746	no_repo
2026-10-12	CC	<home>	ca818278	35K	748	no_repo
2026-10-12	CC	<home>	7c29dbfa	35K	714	no_repo
2026-10-12	CC	<home>	b7d4035c	35K	710	no_repo
2026-10-12	CC	<home>	467973fc	35K	692	no_repo
2026-10-12	CC	<home>	45a4d7b4	35K	680	no_repo
2026-10-12	CC	<home>	62dc1e5a	35K	650	no_repo
2026-10-12	CC	<home>	661f507d	35K	648	no_repo
2026-10-12	CC	<home>	f57e2d57	35K	636	no_repo
2026-10-12	CC	<home>	59bad12e	35K	644	no_repo

Generated 2026-10-13 13:00 UTC from ~/ideas/pal/dashboards/token_burn.jsonl (549 rows). Sources: ~/.codex/sessions/ (exact), ~/.claude/projects/-home-khoward/ (exact). No estimate lane currently active.