Burn is not proof. Output is not victory. Accepted work that repeats is leverage.
las accounted for the bulk of accepted work, totaling 12.8M accepted_active_h.mainstay-av shows a significant unsettled volume of 1.6M, with an acceptance_ratio of 0.0.<home> directory generated 1.9M in waste_active_h, which is unmeasurable because it ran outside any git repo.pal project has multiple unsettled entries, including one for 23K from 5af22ad7 on 2026-08-31 in pal with an acceptance_ratio of 0.0.A subagent spawn forks its parent, so the child starts holding the parent's whole transcript and the same conversation is charged once per fork, on every turn. The root 01a04b01-5edc involved 4 threads, 3 forks, and a max_depth of 1, charging 23.8M_h. Agents involved were Chandrasekhar, Harvey, and James.
mainstay-av + 5af22ad7 + 2026-08-29 + mainstay-av/docs/entity + 1.6M: suggested_verdict is "review" because of "open_loop, 1.6M burn — worth looking".las + d33e7f08 + 2026-08-28 + las + 689K: suggested_verdict is "review" because of "PR open — work in flight".pal/templari + d33e7f08 + 2026-08-31 + pal/templari + 61K: suggested_verdict is "not_useful" because of "open_loop, 61K burn — small miss".pal + 5af22ad7 + 2026-09-01 + pal + 24K: suggested_verdict is "not_useful" because of "open_loop, 24K burn — small miss".pal + 5af22ad7 + 2026-08-31 + pal + 23K: suggested_verdict is "not_useful" because of "open_loop, 23K burn — small miss".pal + d33e7f08 + 2026-08-31 + pal + 10K: suggested_verdict is "not_useful" because of "open_loop, 10K burn — small miss".pal/templari + d33e7f08 + 2026-08-28 + pal/templari + 4K: suggested_verdict is "not_useful" because of "open_loop, 4K burn — small miss".pal + d33e7f08 + 2026-08-28 + pal + 2K: suggested_verdict is "not_useful" because of "open_loop, 2K burn — small miss".The <home> directory generated 1.9M in waste_active_h, but its acceptance_ratio is 0.0 due to it being unmeasurable, not a judgment on quality.
---
Measurability caveat (generated, not model-authored): <home> (1.9M) 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.
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.
Each cell = one UTC day, color intensity = log10(active tokens). Hover for date + counts.
| 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 |
| 2026-08-01 | 20.3M | 1.37B | 4 | payday (6.1M) | ?=11 |
| 2026-08-06 | 16.5M | 592.1M | 51 | <home> (12.0M) | ?=58 |
| 2026-07-16 | 15.7M | 522.1M | 23 | <home> (15.7M) | ?=23 |
| 2026-07-24 | 10.3M | 399.5M | 1 | las (5.9M) | ?=3 |
| 2026-07-31 | 10.2M | 1.55B | 2 | payday (3.7M) | ?=10 |
| 2026-07-21 | 9.1M | 168.7M | 1 | <home> (9.1M) | ?=1 |
| 2026-08-12 | 7.7M | 116.0M | 25 | dreamweaver (6.5M) | ?=27 |
| 2026-08-08 | 6.1M | 358.6M | 27 | dreamweaver (3.0M) | ?=37 |
| Project | Active | |
|---|---|---|
| las | 13.4M | |
| <home> | 1.9M | |
| mainstay-av | 1.6M | |
| pal/templari | 65K | |
| pal | 59K |
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.
| Project | Accepted | Ratio | Mix |
|---|---|---|---|
| las | 14.1M | 94% | |
| pal | 2.3M | 30% | |
| pal/dashboards | 1.6M | 92% | |
| pal/templari | 134K | 27% | |
| memory | 64K | 4% | |
| mainstay-av | 0 | 0% |
| Project | Accepted | Ratio | Mix |
|---|---|---|---|
| <home> | 0 | 0% | |
| dreamweaver | 0 | 0% | |
| mainstay-av | 0 | 0% | |
| pal/placeholders | 0 | 0% | |
| tmp | 0 | 0% | |
| panacea-ai | 0 | 0% |
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 |
|---|---|---|---|---|---|
| 2026-08-24 | mainstay-av | 5af22ad7 | 1.8M | open_loop | .../mainstay-av/docs/entity |
| 2026-08-22 | mainstay-av | 5af22ad7 | 1.8M | open_loop | .../mainstay-av/docs/entity |
| 2026-08-29 | mainstay-av | 5af22ad7 | 1.6M | open_loop | .../mainstay-av/docs/entity |
| 2026-08-21 | pal | 5af22ad7 | 1.4M | open_loop | .../pal |
| 2026-08-28 | las | d33e7f08 | 689K | committed · #17 (OPEN) | .../las |
| 2026-08-20 | pal | 5af22ad7 | 476K | open_loop | .../pal |
| 2026-08-21 | mainstay-av | 5af22ad7 | 233K | open_loop | .../mainstay-av/docs/entity |
| 2026-08-24 | las | d33e7f08 | 146K | open_loop | .../las |
| 2026-08-23 | pal | d33e7f08 | 68K | open_loop | .../pal |
| 2026-08-31 | pal/templari | d33e7f08 | 61K | open_loop | .../pal/templari |
| 2026-08-24 | mainstay-av | d33e7f08 | 28K | open_loop | .../mainstay-av/apps/worker |
| 2026-08-24 | pal | d33e7f08 | 27K | open_loop | .../pal |
| 2026-08-24 | templari | d33e7f08 | 27K | open_loop | .../templari |
| 2026-08-19 | dreamweaver | 5af22ad7 | 25K | open_loop | .../dreamweaver |
| 2026-09-01 | pal | 5af22ad7 | 24K | open_loop | .../pal |
| 2026-08-23 | memory | d33e7f08 | 23K | open_loop | /home/khoward/.claude/projects/-home-khoward/memory |
| 2026-08-31 | pal | 5af22ad7 | 23K | open_loop | .../pal |
| 2026-08-23 | pal/memory | d33e7f08 | 14K | open_loop | .../pal/memory |
| 2026-08-23 | pal/templari | d33e7f08 | 11K | open_loop | .../pal/templari |
| 2026-08-31 | pal | d33e7f08 | 10K | open_loop | .../pal |
| 2026-08-28 | pal/templari | d33e7f08 | 4K | open_loop | .../pal/templari |
| 2026-08-28 | pal | d33e7f08 | 2K | open_loop | .../pal |
| 2026-08-23 | ideas | d33e7f08 | 2K | open_loop | /home/khoward/ideas |
Latest enriched rows from the JSONL (sorted by date desc, active desc as tiebreaker). M = manually labeled.
| Date | Tool | Project | Session | Active | Output | Outcome |
|---|---|---|---|---|---|---|
| 2026-09-01 | CC | las | 5af22ad7 | 996K | 88K | accepted #19 |
| 2026-09-01 | CC | <home> | 4b15a997 | 495K | 7K | no_repo |
| 2026-09-01 | CC | las | 4b15a997 | 56K | 20K | accepted #19 |
| 2026-09-01 | CC | pal | 5af22ad7 | 24K | 10K | open_loop |
| 2026-09-01 | CC | <home> | 092e5ff7 | 0 | 0 | no_repo |
| 2026-09-01 | CC | <home> | 0f39d339 | 0 | 0 | no_repo |
| 2026-09-01 | CC | <home> | 1f4fb5ba | 0 | 0 | no_repo |
| 2026-09-01 | CC | <home> | 2011b942 | 0 | 0 | no_repo |
| 2026-09-01 | CC | <home> | 66ac0a51 | 0 | 0 | no_repo |
| 2026-09-01 | CC | <home> | 7806fa60 | 0 | 0 | no_repo |
| 2026-09-01 | CC | <home> | 929b9985 | 0 | 0 | no_repo |
| 2026-09-01 | CC | <home> | a473db78 | 0 | 0 | no_repo |
| 2026-09-01 | CC | <home> | b98b6dc1 | 0 | 0 | no_repo |
| 2026-09-01 | CC | <home> | c31d4e73 | 0 | 0 | no_repo |
| 2026-09-01 | CC | <home> | ec77247c | 0 | 0 | no_repo |
| 2026-09-01 | CC | <home> | f2b131c7 | 0 | 0 | no_repo |
| 2026-08-31 | CC | las | 5af22ad7 | 5.3M | 152K | accepted #18 |
| 2026-08-31 | CC | las | d33e7f08 | 548K | 27K | accepted #18 |
| 2026-08-31 | CC | pal/templari | d33e7f08 | 61K | 23K | open_loop |
| 2026-08-31 | CC | pal | 5af22ad7 | 23K | 8K | open_loop |
| 2026-08-31 | CC | pal | d33e7f08 | 10K | 5K | open_loop |
| 2026-08-31 | CC | <home> | 01181ccb | 0 | 0 | no_repo |
| 2026-08-31 | CC | <home> | 030b8d51 | 0 | 0 | no_repo |
| 2026-08-31 | CC | <home> | 06c60690 | 0 | 0 | no_repo |
| 2026-08-31 | CC | <home> | 350b3dfa | 0 | 0 | no_repo |
| 2026-08-31 | CC | <home> | 36a64ba4 | 0 | 0 | no_repo |
| 2026-08-31 | CC | <home> | 36b470a9 | 0 | 0 | no_repo |
| 2026-08-31 | CC | <home> | 37d89803 | 0 | 0 | no_repo |
| 2026-08-31 | CC | <home> | 391cdd0f | 0 | 0 | no_repo |
| 2026-08-31 | CC | <home> | 3efd06cf | 0 | 0 | no_repo |
Generated 2026-09-01 13:00 UTC from ~/ideas/pal/dashboards/token_burn.jsonl (950 rows). Sources: ~/.codex/sessions/ (exact), ~/.claude/projects/-home-khoward/ (exact). No estimate lane currently active.