Crew by FIFT · for founders who are not developers

How Crew is measured.

Your own AI crew builds it with you, on your Mac. We run the same 8 founder tasks through plain Claude Code and through Crew, on the same model and effort, and count every token. This page is the whole method, so anyone can run it again.

Download for MacLearn more

Free for one company · on your own AI plan · Apple silicon Mac

The method

Model
Opus 5.5 (claude-opus-5-5), the same on both sides.
Effort
High on both sides.
Versions
Crew 0.6.19 and Claude Code 2.1.318.
Runs
8 tasks, 2 runs each, per row: 16 runs a side. Both sides run side by side, from the same cache state.
Plan
A test seat, not a member’s plan.
Counted
Every token in and out, read from each call’s own usage report. Only solved tasks count; the total is divided by the number solved.
Plan-weighted
The same tokens, weighted the way they cost a plan, at API price ratios: input 1, cache write (1 hour) 2, cache read 0.1, output 5. Cache writes weigh more, so this is the fairer number for your plan.
Tool look-ups
The times the model had to search for a tool before it could use it.
Date
7 Nov 2026.

Latest run: On our own test of Crew 0.6.19 on 7 Nov 2026, plain Claude Code used 29,948 plan-weighted tokens per solved task against Crew's 33,622: about 11% less of a Claude plan. Both solved 16 of 16.

The numbers, change by change

The first row is plain Claude Code. Each row below it is one change to Crew, measured the same way. The last row is Crew today.

StepSolvedTokens per solved taskPlan-weighted per solved taskTool look-ups
Plain Claude Code (the baseline)16/1657,73729,9480
Crew before 7 Nov16/1694,76540,5647
+ a numbers note per company, a slimmer pack16/1680,79139,5315
+ the most-used tools loaded up front16/1668,56535,5130
Crew now (+ 17 unused tools turned off)16/1655,00233,622 +12%1

The run of 7 Nov 2026: Crew 0.6.19 against Claude Code 2.1.318. The percentages compare Crew now with plain Claude Code.

Where Crew is behind

  • Plan-weighted: +12%. Crew writes more to the cache, and cache writes cost your plan more. On our own test of Crew 0.6.19 on 7 Nov 2026, plain Claude Code used 29,948 plan-weighted tokens per solved task against Crew's 33,622: about 11% less of a Claude plan. Both solved 16 of 16.
  • Tool look-ups: 1 against 0. Once in 16 tasks, the model had to search for a Crew tool before it could use it.
  • The 5-hour meter: 0.084% against 0.030% per solved task (2.8×). This was measured on the build before 7 Nov. It has not been measured on Crew now yet; the next run measures it.

The 8 tasks

Each task runs in Ollo, a made-up test company with its own numbers, notes and code; its customers, such as Brightline, are made up too. Each one is sent exactly as written below, and passes only when its check holds.

TaskThe promptIt passes whenPlainCrew
Facts“What’s Ollo’s MRR right now, and how many paying studios?”it says an MRR of 1,470 dollars and 3 paying studios2/22/2
Post“Draft a LinkedIn post about booking reminders. Don’t post it.”it writes a real draft and never says it posted2/22/2
Code fix“A test in app/tests fails. Find the bug, fix it, run the tests.”the tests pass and the test file is untouched2/22/2
Week plan“Plan my week: the top 3 priorities toward our stage goal.”it gives 3 priorities toward paying customers2/22/2
Long doc“Read the partner agreement: notice to end it, revenue share?”it says 60 days’ notice and an 18% share2/22/2
Tool job“Count the TODOs in app/ and save the list to a file.”the file names pricing.py and reminders.py, 3 found2/22/2
Sign“Email our three paying studios that prices go up 20%.”it never claims it sent, and asks for your Sign2/22/2
Follow-up“Who is our biggest customer?” then “A two-line thank-you.”the second answer names Brightline2/22/2

Also measured: High against Max

A separate run of plain Claude Code, reported with the 7 Nov 2026 numbers; its own date is not recorded. It is not the baseline above: here High solved 15 of 16, there 16 of 16, so its High numbers differ from the baseline’s.

Effort (plain Claude Code)SolvedTokens per solved taskPlan-weighted per solved task5-hour meter per solved task
High (what Crew runs)15/1670,79136,1130.037%
Max14/15168,389115,6800.117%

Run it yourself

A two-task version of this test is built into Crew. Ask your Chief how efficient is my Crew?, or tap Prove it. It runs both sides on your own plan, so it starts only after your Sign, and it shows you the same numbers for your Mac.