Occam

Deutsch · Video comparison · Install · Reproduce

Build less. Work lean. Talk less.

Occam is a 30-line rule set for coding agents: prefer existing code and standard tools, read only what matters, and keep output concise. It ships as a Claude Code plugin; the rules are also tested in Codex.

Sol 6.1 max, Fast: 8.3% fewer total tokens with Occam on the black-hole task. All three animations pass the browser checks. In the separate Claude coding benchmarks, Occam reduced task cost by 51% on Opus 5.5 max and 55% on Sonnet 5.5 max, while passing at least as many tests.

Black-hole benchmark: Sol 6.1 max

One prompt, three fresh Docker containers. Each setup creates one offline HTML animation with a black shadow, glowing accretion disk, curved light above and below it, visible motion, and Pause/Resume/Restart controls. The model is gpt-6.1-sol, reasoning max, with Fast explicitly requested in every arm.

Base → Occam → Ponytail 4.10, left to right. Ten seconds at 30 fps; the same browser, viewport, software renderer, and animation clock.

https://github.com/user-attachments/assets/e4cbba37-8562-4835-a1bf-18c8d86d133d

Watch/download the original MP4 · Still image at 5 seconds

In the still, Occam's disk forms a broad raised arc above the shadow and a curved band below it. Compare the shape, texture, and motion of all three results in the video.

Setup	Total tokens	Change vs. Base	Generation time	Browser checks
Base	1,024,912	—	11.56 min	Pass
Occam full	939,959	−8.3%	8.82 min	Pass
Ponytail 4.10 full	962,972	−6.0%	8.29 min	Pass

Occam uses 84,953 fewer tokens than Base and 2.4% fewer than Ponytail. Original HTML files and full measurements · Prompt, scoring, and reproduction.

How to interpret this: one attempt per setup on one visual task, with no confidence interval. Tokens are input + output; cached input and reasoning are included once. This is a token comparison, not a dollar-cost estimate. Fast is verified in the invocation and model catalog; the CLI does not expose the server's served tier. Visual quality can be compared in the video; an independent visual score is still pending.

Claude coding benchmarks

Five rounds, three models, 18 tasks per setup in each round. Claude loads the actual plugins; hidden tests check the resulting code. Cost changes are geometric means of matched task ratios.

Model	Effort	Occam vs. no plugin	Ponytail vs. no plugin	Tests passed / 18Base · Occam · Ponytail
Opus 5.5	max	−51%	−26%	16 · 18 · 18
Sonnet 5.5	max	−55%	−9% ¹	16 · 17 · 17
Opus 5.5	medium	−11%	+11%	17 · 18 · 18
Sonnet 5.5	medium	−3% ¹	+26%	16 · 18 · 18
Haiku 4.5	—	−2% ¹	+30%	10 · 13 · 10

¹ The 95% confidence interval includes zero. Small changes are not established savings. Cost here is the list-price estimate reported by Claude Code, including thinking and cache. These tasks differ from the visual Codex pilot.

Cost chart, methods, confidence intervals, and raw data