Skip to main content
skill CX Codex

lever-pricing — Claude Code skill: what it does, how to install

The lever-pricing Claude Code skill measures how optimization levers affect a GPU kernel. It tests each lever alone, in the full stack, and by removing it from that stack.

Apache-2.0 ★ 339 updated 2026-11-11

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
~/.claude/skills/lever-pricing/SKILL.md
Open on GitHub

What lever-pricing does

The skill runs a frozen measurement recipe on the best kernel tree, then gathers results for diagnosis. Each candidate lever can be tested on its own, removed from the complete set, or enabled alongside the others. Comparing those runs can reveal dependencies, including a lever that has little effect alone but matters when combined with other changes.

Put candidate levers in notes/levers.json. The driver supplies the kernel path and round count, then runs python3 notes/lever_pricing_run.py notes/levers.json. An ablation can be requested with PROBE_REQUEST: notes/<name>.json and an ablations section. The workflow needs Python 3, a GPU job, and a kernel file. It is not a student tool.

What it helps with

  • measure each optimization lever on its own
  • identify a lever that other changes depend on
  • compare the full optimization stack with versions missing individual levers
  • request an ablation through a configuration file

Example prompts for the agent

  • Measure the optimization levers in kernel.py and identify dependencies between them.
  • Set up a run for the levers in notes/levers.json on the best kernel tree.
  • Run an ablation from notes/ablation.json.

How to install lever-pricing

Manually: put the files in place

~/.claude/skills/lever-pricing/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/lever-pricing/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about lever-pricing

How do I install lever-pricing in Claude Code?

Create ~/.claude/skills/lever-pricing and place the skill file at ~/.claude/skills/lever-pricing/SKILL.md.

What does lever-pricing do?

It measures GPU kernel changes individually, as a complete set, and with individual changes removed. The results can expose dependencies between levers.

What does lever-pricing need to run?

It needs Python 3, a GPU job, a kernel file, and a lever list in notes/levers.json.

Source text

SKILL.md · Apache-2.0
# lever-pricing

Measured prices of candidate levers on the current best kernel, in one GPU job: each lever
added alone, removed alone from the full stack, and all of them on. It is the only reading
that also shows a lever worthless alone but required by the others (about zero when added,
negative when removed), or one visible only once the others are subtracted.

The teacher writes the candidates into `notes/levers.json`; the driver adds the kernel file
and the number of rounds and runs the frozen recipe on the best tree before it asks for a
diagnosis (`python3 notes/lever_pricing_run.py notes/levers.json`):

```json
{"kernel_file": "kernel.py", "rounds": 3,
 "levers": [{"name": "ring_per_stage",
             "edits": [{"old": "<exact text in the kernel file>", "new": "<replacement>"}],
             "expect": "producer refills each stage as its consumer releases it",
             "in_stack": true}],
 "variants": [{"name": "ring+lane", "levers": ["ring_per_stage", "lane_owned"],
               "question": "is lane_owned a dependency on the ring?"}]}
```

The full format (`in_stack`, `variants`, `ablations`) is in the script's docstring.

An ablation can be requested the same way with `PROBE_REQUEST: notes/<name>.json`
(`ablations` only). Not a student tool.

© OpenBMB · Apache-2.0 · OpenBMB/ForgeKernel

Similar skills

All skills for AI and ML →

From the same set8

Project sponsors

Companies that keep this analytics open