Humanmaxxing
Menu

Product · Real-time analyticsDraft

See where the tokens go, minutes after they go there.

A lightweight hook installs in one paste and reports every turn: tokens, model, tool use, and which repo, branch and ticket the work was for. Prompts and code never leave the machine, only the numbers do. Joined with your tickets and pull requests, that becomes cost per PR, code quality, time saved and the full cycle time from ticket to merge, per developer and per workflow.

Book a demo

What the dashboard shows Sample data

human-paced machine-paced · every number is per repo, team or developer

Outcomes

Cost per PR

Model spend per merged pull request

$8.70-41% vs 12 wk ago

Cost per PR (USD), last 12 weeks$7.50$10.00$12.50$15.00$17.50Aug 17Nov 2

$8.70 week of Nov 2

Table
WeekUSD
Aug 17$14.80
Aug 24$13.90
Aug 31$15.20
Sep 7$12.60
Sep 14$11.90
Sep 21$12.40
Sep 28$10.80
Oct 5$10.10
Oct 12$10.60
Oct 19$9.40
Oct 26$9.10
Nov 2$8.70

Code quality

PRs merged with no rework round after human review

81%+33% vs 12 wk ago

Code quality (%), last 12 weeks60%70%80%90%Aug 17Nov 2

81% week of Nov 2

Table
Week%
Aug 1761%
Aug 2463%
Aug 3160%
Sep 766%
Sep 1469%
Sep 2171%
Sep 2870%
Oct 574%
Oct 1276%
Oct 1975%
Oct 2679%
Nov 281%

Time saved

Human hours saved per week against the pre-agent baseline

49 h+172% vs 12 wk ago

Time saved (hours), last 12 weeks0 h20 h40 h60 hAug 17Nov 2

49 h week of Nov 2

Table
Weekhours
Aug 1718 h
Aug 2422 h
Aug 3121 h
Sep 727 h
Sep 1431 h
Sep 2130 h
Sep 2836 h
Oct 538 h
Oct 1241 h
Oct 1940 h
Oct 2646 h
Nov 249 h

By agent · last 12 weeks

Cost per agent

Model spend per merged pull request, by agent

$2.86orchestrator · lowest of 10

  1. orchestrator$2.86
  2. domain investigators$1.12
  3. review-code-team$0.98
  4. review-plan-team$0.84
  5. codebase-navigator$0.76
  6. test-engineer$0.62
  7. security$0.48
  8. architecture$0.41
  9. fresh-eyes$0.33
  10. retro-writer$0.30

Reviewer cost per issue found

Model spend per confirmed finding, by reviewer agent

$1.90code-reviewer · lowest of 8

  1. code-reviewer$1.90
  2. test-engineer$2.40
  3. fresh-eyes$2.70
  4. domain experts$3.20
  5. architecture$4.80
  6. second-opinion model$5.40
  7. security$6.10
  8. performance$7.90

Reviewer performance

Confirmed issues found in the last 12 weeks, by reviewer agent

148code-reviewer · highest of 8

  1. code-reviewer148
  2. test-engineer121
  3. domain experts86
  4. fresh-eyes54
  5. architecture39
  6. security31
  7. second-opinion model27
  8. performance12

Cycle time, ticket to merge

Ticket pickup

Average time from ticket ready to work started

9.5 h-69% vs 12 wk ago

Ticket pickup (hours), last 12 weeks0 h10 h20 h30 h40 hAug 17Nov 2

9.5 h week of Nov 2

Table
Weekhours
Aug 1731 h
Aug 2428 h
Aug 3129 h
Sep 724 h
Sep 1422 h
Sep 2119 h
Sep 2818 h
Oct 515 h
Oct 1214 h
Oct 1912 h
Oct 2611 h
Nov 29.5 h

Pickup to PR

Average time from work started to pull request opened

4.1 h-55% vs 12 wk ago

Pickup to PR (hours), last 12 weeks4 h6 h8 h10 hAug 17Nov 2

4.1 h week of Nov 2

Table
Weekhours
Aug 179.2 h
Aug 248.6 h
Aug 318.9 h
Sep 77.4 h
Sep 146.8 h
Sep 216.1 h
Sep 285.9 h
Oct 55.2 h
Oct 124.9 h
Oct 194.6 h
Oct 264.3 h
Nov 24.1 h

PR to first review

Average wait from pull request opened to first human review

74 min-65% vs 12 wk ago

PR to first review (minutes), last 12 weeks50 min100 min150 min200 min250 minAug 17Nov 2

74 min week of Nov 2

Table
Weekminutes
Aug 17210 min
Aug 24190 min
Aug 31205 min
Sep 7160 min
Sep 14150 min
Sep 21135 min
Sep 28120 min
Oct 5110 min
Oct 1295 min
Oct 1990 min
Oct 2682 min
Nov 274 min

First review to merge

Average time from first human review to merge

4.6 h-60% vs 12 wk ago

First review to merge (hours), last 12 weeks2.5 h5 h7.5 h10 h13 hAug 17Nov 2

4.6 h week of Nov 2

Table
Weekhours
Aug 1712 h
Aug 2411 h
Aug 3111 h
Sep 79.4 h
Sep 148.6 h
Sep 218.1 h
Sep 287.2 h
Oct 56.6 h
Oct 126.1 h
Oct 195.4 h
Oct 265 h
Nov 24.6 h

From a turn to a chart

Machine · runs without you

Install

One paste per developer. An admin creates a project key; hooks register with the agent.

  • Session start, tool calls, permission requests, sub-agent stops, session end
  • Works with Claude Code today, other agents in a simpler view
  • One switch turns it all off

machine runs human reviews

What you get

Cost and tokens

Spend by model, skill, workflow step and team, with cache hit rate and a monthly projection.

Efficiency

Tokens per turn, lines per dollar, context size, compactions and tool outcomes.

Cycle time, stage by stage

Ticket pickup, pickup to PR, PR to first review, and first review to merge, each as its own trend.

People and teams

Spend per developer, who is getting the most from the tools, and who has not started.

Privacy by construction

Hooks send counts and identifiers, never prompts, responses or code.

Every major coding agent

Claude Code gets the full dashboard today; Codex, Cursor, Gemini and Grok report into a simpler view.

Questions

How real-time is real-time?

Events arrive per turn while the developer works. Dashboards show them within minutes, not seconds; this is not a live stream and does not need to be.

Does this replace the vendor billing page?

It reconciles against it. Vendor billing tells you the total; this tells you which repo, ticket, workflow step and reviewer the total came from.

Where does the two-clock number come from?

Human time is the gaps between agent turns where a person was reading or deciding; machine time is everything else. Both are derived from the same per-turn events.