Skip to content
Stable Included in Builder

CCPP Limits

No tool result reaches the agent whole, and every token a session spends is measured.

Usage limits for coding agents: results cut into blocks and ranked by a local embedding model, the whole output kept on disk, and the bill of every session measured as it grows.

ccpp sync
ceiling per tool result
12 KB
ranked blocks, at most
8
embedding, no API call
Local
lines rewritten or summarized
0

A test run prints four thousand lines. The agent needed six. Without limits, all four thousand go into the context and are paid for on every turn that follows. CCPP Limits keeps the six, and tells the agent exactly where the rest is.

Why it matters

Pay for what is read

Each result is cut into blocks, embedded on your machine, and ranked against what the call said it expects. Only the closest come back.

Nothing is rewritten

No model summarizes your output. Every line shown is the line the tool printed, with its line numbers.

Nothing is lost

The whole result is saved to a file named in every response. The agent reads the rest by line numbers when it needs to.

How it works

Calls say what they expect in a few words. Those words and every block of the result become vectors; cosine similarity picks the blocks.

h.read_file("server.go", {prompt = "func routes GET POST handlers"})

Specifications

Result size
8 blocks of 80 lines, 12,288 characters, a 50 character summary
Whole payloads
Diffs and instructions up to 40,960 characters
Embedding
A small model on the CPU, no network call
Measurement
Tokens of every session, in the TUI and the CLI

Stop paying for dumps

CCPP Limits is included in the Builder plan.

Create an account
Every product

One account. Every tool Claude needs.

Free products come with a free account. Builder unlocks the rest, the harness first.