Burn is not proof. Output is not victory. Accepted work that repeats is leverage.
las accounted for the bulk of accepted work, logging 9.1M accepted\_active\_h.memory logged 1.1M accepted\_active\_h.pal shows a 0.0 acceptance\_ratio despite having 144K unsettled\_active\_h.<home> directory has 1.5M waste\_active\_h, and its acceptance\_ratio is 0.0.pal project also shows 24K unsettled\_active\_h and 23K unsettled\_active\_h, both contributing to the 0.0 acceptance\_ratio.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 fork_amplification entry shows root: "01a04b01-5edc", 6 threads, 3 forks, max\_depth 1, charged\_h "33.8M", replay\_pct 94.3, output\_h "124K", cost\_per\_output 273.5, and was associated with agents: "Chandrasekhar", "Faraday", "Harvey", "James", "Pascal".
las + 4b15a997 + 2026-09-06 + las/.worktrees/mvp + "913K": verdict is "review" because "PR open — work in flight".las + 4b15a997 + 2026-09-05 + las/.worktrees/mvp + "645K": verdict is "review" because "open\_loop, 645K burn — worth looking".las + 4b15a997 + 2026-09-03 + las/.worktrees/mvp + "165K": verdict is "not\_useful" because "open\_loop, 165K burn — small miss".pal/templari + d33e7f08 + 2026-08-31 + pal/templari + "61K": verdict is "not\_useful" because "open\_loop, 61K burn — small miss".pal + 01a07347 + 2026-09-05 + pal + "57K": verdict is "not\_useful" because "open\_loop, 57K burn — small miss".mainstay-av + d33e7f08 + 2026-09-04 + mainstay-av + "30K": verdict is "not\_useful" because "open\_loop, 30K burn — small miss".pal + 5af22ad7 + 2026-09-01 + pal + "24K": verdict is "not\_useful" because "open\_loop, 24K burn — small miss".pal + 5af22ad7 + 2026-08-31 + pal + "23K": verdict is "not\_useful" because "open\_loop, 23K burn — small miss".The <home> directory has 1.5M waste\_active\_h, but its acceptance\_ratio is 0.0 because it is unmeasurable, as noted in its acceptance\_note.
---
Measurability caveat (generated, not model-authored): <home> (1.5M) 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 |
| 2026-08-06 | 16.5M | 592.1M | 51 | <home> (12.0M) | ?=58 |
| 2026-07-16 | 15.7M | 522.1M | 23 | <home> (15.7M) | ?=23 |
| 2026-08-12 | 7.7M | 116.0M | 25 | dreamweaver (6.5M) | ?=27 |
| 2026-08-08 | 6.1M | 358.6M | 27 | dreamweaver (3.0M) | ?=37 |
| 2026-08-07 | 6.0M | 352.8M | 28 | <home> (4.1M) | ?=35 |
| 2026-08-31 | 5.9M | 144.8M | 26 | las (5.8M) | no_repo=24 · open_loop=3 · accepted=2 · PRs #18 |
| 2026-06-15 | 5.9M | 132.6M | 9 | <home> (5.9M) | ?=9 |
| 2026-08-19 | 5.6M | 205.7M | 27 | pal (2.3M) | ?=36 |
| Project | Active | |
|---|---|---|
| las | 10.9M | |
| <home> | 1.5M | |
| memory | 1.1M | |
| pal | 144K | |
| pal/templari | 61K | |
| mainstay-av | 30K |
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 | 15.0M | 79% | |
| memory | 1.1M | 56% | |
| pal | 0 | 0% | |
| mainstay-av | 0 | 0% | |
| pal/templari | 0 | 0% | |
| templari | 0 | 0% |
| Project | Accepted | Ratio | Mix |
|---|---|---|---|
| <home> | 0 | 0% | |
| dreamweaver | 0 | 0% | |
| pal | 0 | 0% | |
| mainstay-av | 0 | 0% | |
| pal/placeholders | 0 | 0% | |
| pal/dashboards | 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 |
| 2026-08-29 | mainstay-av | 5af22ad7 | 1.6M | open_loop | .../mainstay-av/docs/entity |
| 2026-09-06 | las | 4b15a997 | 913K | committed · #21 (OPEN) | .../las/.worktrees/mvp |
| 2026-08-28 | las | d33e7f08 | 689K | open_loop | .../las |
| 2026-09-05 | las | 4b15a997 | 645K | open_loop | .../las/.worktrees/mvp |
| 2026-09-03 | las | 4b15a997 | 165K | open_loop | .../las/.worktrees/mvp |
| 2026-08-24 | las | d33e7f08 | 146K | open_loop | .../las |
| 2026-08-31 | pal/templari | d33e7f08 | 61K | open_loop | .../pal/templari |
| 2026-09-05 | pal | 01a07347 | 57K | open_loop | .../pal |
| 2026-09-04 | mainstay-av | d33e7f08 | 30K | open_loop | .../mainstay-av |
| 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 |
| 2026-09-01 | pal | 5af22ad7 | 24K | open_loop | .../pal |
| 2026-08-31 | pal | 5af22ad7 | 23K | open_loop | .../pal |
| 2026-09-04 | pal | d33e7f08 | 17K | open_loop | .../pal |
| 2026-09-05 | pal | 01a0728d | 13K | open_loop | .../pal |
| 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 |
Latest enriched rows from the JSONL (sorted by date desc, active desc as tiebreaker). M = manually labeled.
| Date | Tool | Project | Session | Active | Output | Outcome |
|---|---|---|---|---|---|---|
| 2026-09-06 | CC | las | 4b15a997 | 913K | 101K | committed #21 |
| 2026-09-06 | CC | <home> | 055986cf | 0 | 0 | no_repo |
| 2026-09-06 | CC | <home> | 25fcf28d | 0 | 0 | no_repo |
| 2026-09-06 | CC | <home> | 436555db | 0 | 0 | no_repo |
| 2026-09-06 | CC | <home> | 4ef5621b | 0 | 0 | no_repo |
| 2026-09-06 | CC | <home> | 5b5e8c13 | 0 | 0 | no_repo |
| 2026-09-06 | CC | <home> | 7c062c93 | 0 | 0 | no_repo |
| 2026-09-06 | CC | <home> | 90e18de4 | 0 | 0 | no_repo |
| 2026-09-06 | CC | <home> | b32d95d2 | 0 | 0 | no_repo |
| 2026-09-06 | CC | <home> | c2facd43 | 0 | 0 | no_repo |
| 2026-09-06 | CC | <home> | ce66ef10 | 0 | 0 | no_repo |
| 2026-09-06 | CC | <home> | d1545756 | 0 | 0 | no_repo |
| 2026-09-06 | CC | <home> | d190593b | 0 | 0 | no_repo |
| 2026-09-05 | CC | las | 4b15a997 | 645K | 12K | open_loop |
| 2026-09-05 | Codex | <home> | 01a07287 | 139K | 12K | no_repo |
| 2026-09-05 | Codex | <home> | 01a07329 | 128K | 6K | no_repo |
| 2026-09-05 | Codex | <home> | 01a0732b | 57K | 4K | no_repo |
| 2026-09-05 | Codex | pal | 01a07347 | 57K | 1K | open_loop |
| 2026-09-05 | Codex | <home> | 01a04b01 | 47K | 88 | no_repo |
| 2026-09-05 | Codex | pal | 01a0728d | 13K | 7 | open_loop |
| 2026-09-05 | CC | <home> | 0a19a299 | 0 | 0 | no_repo |
| 2026-09-05 | CC | <home> | 103ed8a5 | 0 | 0 | no_repo |
| 2026-09-05 | CC | <home> | 19f62206 | 0 | 0 | no_repo |
| 2026-09-05 | CC | <home> | 2dec65eb | 0 | 0 | no_repo |
| 2026-09-05 | CC | <home> | 3e9a31f7 | 0 | 0 | no_repo |
| 2026-09-05 | CC | <home> | 45e04751 | 0 | 0 | no_repo |
| 2026-09-05 | CC | <home> | 5379f2b8 | 0 | 0 | no_repo |
| 2026-09-05 | CC | <home> | 6067a19e | 0 | 0 | no_repo |
| 2026-09-05 | CC | <home> | 6290217c | 0 | 0 | no_repo |
| 2026-09-05 | CC | <home> | 7a0b538b | 0 | 0 | no_repo |
Generated 2026-09-06 13:00 UTC from ~/ideas/pal/dashboards/token_burn.jsonl (1041 rows). Sources: ~/.codex/sessions/ (exact), ~/.claude/projects/-home-khoward/ (exact). No estimate lane currently active.