Burn is not proof. Output is not victory. Accepted work that repeats is leverage.
<home> directory shows 0.0 acceptance ratio, and its 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 1.9M in waste tokens.las shows 0.0 acceptance ratio.mainstay-av shows 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 details are: root 01a04b01-5edc, 4 threads, 3 forks, max depth 1, charged 23.8M, replay_pct 94.6, output_h 88K, cost_per_output 271.0. Agents involved are Chandrasekhar, Harvey, and James.
mainstay-av + 5af22ad7 + 2026-08-24 + mainstay-av/docs/entity + 1.8M: suggested_verdict is "review" (open_loop, 1.8M burn — worth looking).las + 5af22ad7 + 2026-08-29 + las/.worktrees/mvp + 1.7M: suggested_verdict is "redo" (committed locally, no PR — decision needed).mainstay-av + 5af22ad7 + 2026-08-29 + mainstay-av/docs/entity + 1.6M: suggested_verdict is "review" (open_loop, 1.6M burn — worth looking).las + 5af22ad7 + 2026-08-30 + las/.worktrees/mvp + 1.4M: suggested_verdict is "redo" (committed locally, no PR — decision needed).las + d33e7f08 + 2026-08-28 + las + 689K: suggested_verdict is "review" (PR open — work in flight).las + d33e7f08 + 2026-08-24 + las + 146K: suggested_verdict is "not_useful" (open_loop, 146K burn — small miss).mainstay-av + d33e7f08 + 2026-08-24 + mainstay-av/apps/worker + 28K: suggested_verdict is "not_useful" (open_loop, 28K burn — small miss).pal + d33e7f08 + 2026-08-24 + pal + 27K: suggested_verdict is "not_useful" (open_loop, 27K burn — small miss).The <home> directory has a 0.0 acceptance ratio, but its 1.9M waste tokens are noted as unmeasurable due to running outside a git repo.
---
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 | 34.5M | 1.78B | 42 | <home> (29.6M) | ?=45 |
| 2026-08-01 | 24.5M | 1.57B | 10 | payday (6.1M) | ?=20 |
| 2026-07-16 | 23.3M | 797.0M | 24 | <home> (16.3M) | ?=27 |
| 2026-07-31 | 23.1M | 2.10B | 9 | payday (8.1M) | ?=34 |
| 2026-08-18 | 22.3M | 554.5M | 38 | <home> (21.6M) | no_repo=38 · accepted=5 · PRs #27 |
| 2026-07-30 | 19.4M | 645.3M | 26 | payday (16.5M) | ?=31 |
| 2026-07-21 | 18.3M | 337.5M | 2 | <home> (9.1M) | ?=4 |
| 2026-08-06 | 16.5M | 592.1M | 51 | <home> (12.0M) | ?=58 |
| 2026-07-29 | 11.2M | 118.2M | 25 | payday (10.8M) | ?=27 |
| 2026-07-24 | 10.3M | 401.9M | 2 | las (5.9M) | ?=4 |
| Project | Active | |
|---|---|---|
| las | 3.9M | |
| mainstay-av | 3.4M | |
| <home> | 1.9M | |
| Downloads | 83K | |
| pal | 29K | |
| templari | 27K | |
| pal/templari | 4K |
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 |
|---|---|---|---|
| pal | 2.8M | 31% | |
| pal/dashboards | 1.7M | 100% | |
| las | 1.4M | 22% | |
| pal/templari | 247K | 56% | |
| memory | 64K | 4% | |
| mainstay-av | 0 | 0% |
| Project | Accepted | Ratio | Mix |
|---|---|---|---|
| dreamweaver | 0 | 0% | |
| <home> | 0 | 0% | |
| panacea-ai | 0 | 0% | |
| payday | 0 | 0% | |
| mainstay-av | 0 | 0% | |
| pal/placeholders | 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 | las | 5af22ad7 | 1.7M | committed | .../las/.worktrees/mvp |
| 2026-08-29 | mainstay-av | 5af22ad7 | 1.6M | open_loop | .../mainstay-av/docs/entity |
| 2026-08-30 | las | 5af22ad7 | 1.4M | committed | .../las/.worktrees/mvp |
| 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 |
| 2026-08-17 | pal | 83ba2858 | 388K | 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 |
| 2026-08-24 | 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 |
| 2026-08-23 | memory | d33e7f08 | 23K | open_loop | /home/khoward/.claude/projects/-home-khoward/memory |
| 2026-08-23 | pal/memory | d33e7f08 | 14K | open_loop | .../pal/memory |
| 2026-08-23 | pal/templari | d33e7f08 | 11K | open_loop | .../pal/templari |
| 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 |
|---|---|---|---|---|---|---|
| 2026-08-30 | CC | las | 5af22ad7 | 1.4M | 57K | committed |
| 2026-08-30 | CC | <home> | 1f8a3754 | 0 | 0 | no_repo |
| 2026-08-30 | CC | <home> | 27b279ff | 0 | 0 | no_repo |
| 2026-08-30 | CC | <home> | 425a3025 | 0 | 0 | no_repo |
| 2026-08-30 | CC | <home> | 45fcb438 | 0 | 0 | no_repo |
| 2026-08-30 | CC | <home> | 5b1054d0 | 0 | 0 | no_repo |
| 2026-08-30 | CC | <home> | 7f365d9a | 0 | 0 | no_repo |
| 2026-08-30 | CC | <home> | 849787bd | 0 | 0 | no_repo |
| 2026-08-30 | CC | <home> | 9457f757 | 0 | 0 | no_repo |
| 2026-08-30 | CC | <home> | abb0c46f | 0 | 0 | no_repo |
| 2026-08-30 | CC | <home> | bc6ed1b7 | 0 | 0 | no_repo |
| 2026-08-30 | CC | <home> | d9fefee1 | 0 | 0 | no_repo |
| 2026-08-30 | CC | <home> | daf21c17 | 0 | 0 | no_repo |
| 2026-08-29 | CC | las | 5af22ad7 | 1.7M | 195K | committed |
| 2026-08-29 | CC | mainstay-av | 5af22ad7 | 1.6M | 5K | open_loop |
| 2026-08-29 | Codex | <home> | 01a04b02 | 436K | 23K | no_repo |
| 2026-08-29 | Codex | <home> | 01a04b04 | 363K | 22K | no_repo |
| 2026-08-29 | Codex | <home> | 01a04b02 | 258K | 25K | no_repo |
| 2026-08-29 | Codex | <home> | 01a04b01 | 230K | 17K | no_repo |
| 2026-08-29 | Codex | <home> | 01a04624 | 18K | 2K | no_repo |
| 2026-08-29 | CC | <home> | 11b483fd | 0 | 0 | no_repo |
| 2026-08-29 | CC | <home> | 1adf3173 | 0 | 0 | no_repo |
| 2026-08-29 | CC | <home> | 2763bbaa | 0 | 0 | no_repo |
| 2026-08-29 | CC | <home> | 2c855730 | 0 | 0 | no_repo |
| 2026-08-29 | CC | <home> | 3b956fdb | 0 | 0 | no_repo |
| 2026-08-29 | CC | <home> | 3c9a0a81 | 0 | 0 | no_repo |
| 2026-08-29 | CC | <home> | 4ce53931 | 0 | 0 | no_repo |
| 2026-08-29 | CC | <home> | 5dd0dd7b | 0 | 0 | no_repo |
| 2026-08-29 | CC | <home> | 5fe51598 | 0 | 0 | no_repo |
| 2026-08-29 | CC | <home> | 65c864ba | 0 | 0 | no_repo |
Generated 2026-08-30 13:00 UTC from ~/ideas/pal/dashboards/token_burn.jsonl (1033 rows). Sources: ~/.codex/sessions/ (exact), ~/.claude/projects/-home-khoward/ (exact). No estimate lane currently active.