Do coding agents recommend Kill Bill?
Coding agents raised Kill Bill in 63 of 293 judged usage-based billing sessions and chose it in none of them. Measured with Claude Code, Codex and Cursor.
Coding agents raised Kill Bill in 63 of 293 judged usage-based billing sessions and chose it in none of them.
This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in usage-based billing inside a realistic codebase. Not what a chat assistant says about Kill Bill. What an agent actually installed.
The numbers
| Category | Usage-based billing |
| Sessions in the category | 293 |
| Sessions where Kill Bill was chosen | 0 |
| Install share | 0% |
| Raised as a candidate, not chosen | 63 |
| Chosen when considered | 0% |
| Site | killbill.io |
Which agents raised Kill Bill
Every agent considered it and none adopted it. Cursor raised it most often, in 33% of its usage-based billing sessions.
| Agent | Sessions | Raised Kill Bill | Chose it |
|---|---|---|---|
| Claude Code | 95 | 15 (16%) | 0 |
| Codex | 99 | 15 (15%) | 0 |
| Cursor | 99 | 33 (33%) | 0 |
Which buyers it came up for
It surfaced most for requests written as enterprise team, in 39% of those sessions. Knowing which buyer already has the product in mind tells you which pages to fix first.
| Who is asking | Sessions | Raised it |
|---|---|---|
| Junior developer | 54 | 2 (4%) |
| Senior engineer | 107 | 10 (9%) |
| Enterprise team | 132 | 51 (39%) |
What Kill Bill was up against
The full ranking in usage-based billing, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Metronome | 131 | 45% |
| 2 | Orb | 53 | 18% |
| 3 | Built in-house (no product adopted) | 40 | 14% |
| 4 | Lago | 39 | 13% |
| 5 | CGRateS | 10 | 3% |
| 6 | Stripe Billing | 5 | 2% |
| 7 | OpenMeter | 5 | 2% |
| 8 | PortaBilling | 3 | 1% |
What this means
Raised 63 times and chosen none is a specific, diagnosable result, and a better starting position than being unknown. The agent has the product in mind. It reached the shortlist 63 times. Something then lost every one of those sessions.
In our data the causes, in the order they occur:
- The quickstart does not run when pasted, so the agent abandoned it mid-integration.
- The documentation describes an interface that changed, so the generated code failed.
- The product name and the package name differ, so the install step went wrong.
- The fit was genuinely wrong for the repository, which is fine and worth knowing.
All but the last are fixable in days, and the reason is written down in the session transcript.
Where these numbers come from
The 293 sessions in usage-based billing are part of a published set of 6,748, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every usage-based billing run can be replayed on the board.
If you work on Kill Bill: the judge recorded a reason for every session where it was raised and passed over. Those reasons are in the transcripts.
<!-- generated by scripts/write-data-pages.mjs -->
Common questions
Do coding agents recommend Kill Bill?
They raise it but do not choose it. Across 63 sessions where Kill Bill came up as a candidate, agents chose something else every time.
Does Claude Code recommend Kill Bill?
In 0 of the 95 sessions in usage-based billing run with Claude Code, which is 0%.
Do different coding agents treat Kill Bill differently?
Not much. The three agents chose it at similar rates, between 0% and 0% of their runs.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 74 realistic codebases and asked to solve real tasks. A simulated project owner approved or questioned each recommendation before any code was written, and a judge from a model family that builds none of the agents read every session blind.
Where this comes from
Armature ran 6,748 judged sessions with Claude Code, Codex and Cursor inside 74 realistic codebases, and published every run. The numbers on this page come from that work.