# Do coding agents recommend CGRateS? > CGRateS was chosen in 3% of 293 judged usage-based billing sessions, ranking fourth. Measured with Claude Code, Codex and Cursor. Source: https://armature.tech/library/do-coding-agents-recommend-cgrates Published: 2026-09-14 Publisher: Armature, Inc. (https://armature.tech) --- > CGRateS was chosen in 3% of 293 judged usage-based billing sessions, ranking fourth. It was also raised as a candidate in 16 further sessions without being chosen. 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 CGRateS. What an agent actually installed. One thing to read first: every one of those wins came from a **single codebase**. That is a result about one repository rather than about usage-based billing in general, and the splits below cannot separate the two. Treat them as a description of that repository. ## The numbers | | | | --- | --- | | Category | Usage-based billing | | Sessions in the category | 293 | | Sessions where CGRateS was chosen | 10 | | Install share | 3% | | Rank in category | 4 of 11 | | Codebases it won in | 1 | | Raised as a candidate, not chosen | 16 | | Chosen when considered | 38% | | Site | github.com | ## By agent With 10 wins spread across three agents, the rates below are small numbers and a difference between them is not yet a finding. They are here because the direction is worth knowing, not because the gap is established. | Agent | Sessions | Chose CGRateS | Share | | --- | --- | --- | --- | | Claude Code | 95 | 0 | 0% | | Codex | 99 | 2 | 2% | | Cursor | 99 | 8 | 8% | ## By who was asking CGRateS performs similarly across the four kinds of buyer, from 0% to 8%. That is unusual: the category leader changed with the persona in 19 of the 24 categories we measured. | Who is asking | Sessions | Chose CGRateS | Share | | --- | --- | --- | --- | | Junior developer | 54 | 0 | 0% | | Senior engineer | 107 | 0 | 0% | | Enterprise team | 132 | 10 | 8% | ## What CGRateS 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 **(this page)** | 10 | 3% | | 6 | Stripe Billing | 5 | 2% | | 7 | OpenMeter | 5 | 2% | | 8 | PortaBilling | 3 | 1% | ## What this means CGRateS was raised in 16 sessions and chosen in 10. That ratio is balanced enough that the ceiling is presence rather than integration: the product converts reasonably when it is on the table, and it is not on the table often enough. ## 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](/library/how-we-measured-this). Every usage-based billing run can be replayed on [the board](/leaderboards/usage-based-billing). If you work on CGRateS: the judge recorded a reason for every session where it was raised and passed over. Those reasons are in the transcripts. ## Common questions ### Do coding agents recommend CGRateS? Yes. CGRateS was chosen in 10 of the 293 judged sessions in usage-based billing, a 3% install share, ranking fourth in its category. ### Does Claude Code recommend CGRateS? In 0 of the 95 sessions in usage-based billing run with Claude Code, which is 0%. ### Do different coding agents treat CGRateS differently? Not much. The three agents chose it at similar rates, between 0% and 8% 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. ### How often is CGRateS considered but not chosen? It was raised as a candidate in 16 sessions without being chosen, and chosen in 10. That is a 38% conversion from considered to chosen. ## Read next - [How to get picked for usage-based billing by coding agents](https://armature.tech/library/usage-based-billing-coding-agents-playbook) (Markdown: https://armature.tech/library/usage-based-billing-coding-agents-playbook.md) - [Do coding agents recommend Metronome?](https://armature.tech/library/do-coding-agents-recommend-metronome) (Markdown: https://armature.tech/library/do-coding-agents-recommend-metronome.md) - [Do coding agents recommend Orb?](https://armature.tech/library/do-coding-agents-recommend-orb) (Markdown: https://armature.tech/library/do-coding-agents-recommend-orb.md) - [Do Claude Code, Codex and Cursor pick the same tools?](https://armature.tech/library/do-claude-code-and-codex-agree) (Markdown: https://armature.tech/library/do-claude-code-and-codex-agree.md) --- Armature helps software products get discovered and used by coding agents. Service: https://armature.tech/discoverability · Results: https://armature.tech/leaderboards/sectors · Contact: contact@armature.tech